Image Corrections

UNIT 12 IMAGE ENHANCEMENT AND

TRANSFORMATION

Structure
12.1 Introduction
Objectives
12.2 Image Enhancement
Contrast Enhancement
Spatial Enhancement
12.3 Image Transformation
Arithmetic Operations
Image Fusion
12.4 Summary
12.5 Unit End Questions
12.6 References
12.7 Further/Suggested Reading
12.8 Answers

12.1 INTRODUCTION
In the previous unit, you have learnt about the different errors affecting the
quality of remotely sensed data and image correction techniques. You can
extract usable information from an image that has been corrected for
radiometric and geometric errors.

Visual interpretation of remote sensing images is one of the most powerful

ways to retrieve information. Depending on the quality of image and human
expertise in image interpretation, many of the attributes are readily identified
by human eyes. However, at times it is required to highlight (enhance) certain
features of interest in images to make the image better interpretable. This is
achieved by techniques known as image enhancement and transformation
techniques required to increase the quality of remote sensing data.

In this unit, we will discuss about image enhancement techniques such as

contrast stretching and spatial filtering. We will also discuss about image
transformation techniques such as arithmetic operations particularly band
ratios including vegetation index, and image fusion and their importance.

Objectives
After studying this unit, you should be able to:
• define image enhancement and image transformation;
• describe the concept of commonly used image enhancement strategies;
• discuss the basics of image transformation and outline the uses of
vegetation index; and
• list uses of image fusion techniques.
23
Processing and
Classification of Remotely
Sensed Images
The term enhancement is
used to define the changes
carried out in an image to
improve its appearance for
better visual interpretation.
There are number of
image enhancement
techniques available but
no single technique can be
said to be best because
needs of users varies and
also a technique which
works for a certain image
for a particular area may
not work for other images
for the same area.
Image enhancement
techniques are also known
as radiometric enhance-
ment techniques.
24
12.2 IMAGE ENHANCEMENT
Image enhancement simply refers to the techniques used to increase the
human interpretability and ability to derive meaningful information from
remotely sensed images. It improves the quality and clarity of images. The
enhancement operations include removing blurring and noise, increasing
contrast and revealing details. For example, image enhancement of a blurred
and low contrast satellite image of the Himalayan Mountains could be made
clear by increasing contrast range and reducing blurring in the original image.
The original image might have areas of very high and very low intensity,
which mask details. The enhanced image will have improved contrast
providing details of the masked image regions.
The primary goal of image enhancement is to improve the visual
interpretability of the images. This is done by increasing the apparent
distinction between features in the image. Image enhancement involves use of
a number of statistical and image manipulation functions available in an image
processing software. Image features are enhanced by the following two
operations:
• Point Operations: In this operation, value of pixel is enhanced
independent of characteristics of neighbourhood pixels within each band.
• Local (Neighbourhood) Operations: In this operation, value of pixel is
enhanced based on neighbouring brightness values.
Image enhancement techniques based on point operations are also called as
contrast enhancement techniques and the enhancement techniques based on
neighbourhood operations are also known as spatial enhancement techniques.
We shall now discuss about the different image enhancement techniques in the
following two sections.
12.2.1 Contrast Enhancement
Before discussing about the contrast enhancement, let us first recognise the
meaning of ‘contrast’. Contrast is the difference in pixel values of two
different objects at the same wavelength. It can be defined as the ratio of
maximum intensity to the minimum intensity over an image.
C = Lmax / Lmin
where,
C = contrast,
Lmax = maximum intensity value present in an image and
Lmin = minimum intensity value present in the same image.
The images usually acquired by a digital sensor might have a limited range of
digital number (DN) to accommodate all the values of reflectance resulting in
a poor quality display of the image. Due to this reason, the image gray scale
distribution is skewed and it is very difficult to distinguish features in the
image. In order to exploit the range of data, the dynamic range of the image
pixel is increased (Fig. 12.1). This technique is known as contrast
enhancement. It involves changing the original pixel values so that more of Image Enhancement and
Transformation
the available range is used which increases contrast between features and their
backgrounds.

(a) (b)

Fig. 12.1: (a) Original image and (b) enhanced image

Commonly applied image enhancement techniques are the followings:

• gray level thresholding
• level slicing and
• contrast stretching.
We shall now discuss about each of these techniques.
Gray Level Thresholding
This method is used to segment an input image into two classes - one for those
pixels which have pixel values below an analyst defined pixel value and one
for those above this value. Thresholding can be used to prepare a binary mask
for an image as shown in Fig. 12.2 where gray level thresholding has been
carried out on near-infrared (NIR) image of LISS III data to create a binary
image showing only the land and water pixels.

(a) (b)
Fig. 12.2: An example of gray level thresholding based image enahncement. (a) A LISS
false colour composite generated from green, red and NIR bands and (b)
resultant binary image of gray level thresholding carried out on NIR band 25
Processing and Level Slicing
Classification of Remotely Level or density slicing is an enhancement technique whereby DNs distributed
Sensed Images
along the x axis of an image histogram are divided into a series of analyst
specified intervals or slices and thereby creating a new image showing select
number of slices (classes) in it.
Contrast Stretching
Image display and recording devices often operate over a range of 256 gray
levels (maximum range of numbers represented in 8 bit image data). Image
data in a single image rarely extend over this entire range. Contrast stretching
technique expands the narrow range of pixel values typically present in an
input image to over a wider range of pixel values. Contrast stretching can be
of two types, linear and non-linear.
A linear contrast stretching occurs, when pixel values of an image are
uniformly stretched across a larger display range. By expanding the range of
original input values of the image, the total dynamic range of display device
can be utilised.
Usually, original minimum and maximum gray level values are set to the
lowest and highest pixel values in the display range, respectively. For
example, if maximum pixel value in the original image is 158 and minimum
pixel value is 60 as illustrated in Fig. 12.3a, the ‘stretched’ values would be set
at 255 and 0, respectively (Fig. 12.3b). The intermediate gray level values of
original image would be similarly and proportionately set to new values. These
types of enhancements are best applied to remotely sensed images with normal
or near-normal distribution, meaning, all the brightness values fall within a
narrow range of the image histogram and only one mode is apparent. This
approach of linear contrast stretching is known as minimum-maximum stretch.

(a)

(b)

(c)
Fig. 12.3: Illustration of principle of contrast stretch. Note: with a typical application of a
linear stretch, areas that were dark-toned will appear darker and areas that were
bright toned will appear even brighter. Linear contrast enhancement also makes
26 subtle variations within data more obvious (source: redrawn after Jensen, 1996)
One major disadvantage of a linear stretch is that it assigns an equal number of Image Enhancement and
Transformation
display levels for infrequently occurring values as it does for frequently
occurring values. This can result in certain features being enhanced, while
other features, which may be of greater importance, will not be sufficiently
enhanced. In these circumstances, we use non-linear contrast enhancement
techniques as discussed below.
Contrary to the linear stretch, a non-linear stretch expands one portion of gray
scale while compressing other portions. This sort of enhancement is typically
applied with purpose of highlighting one part of the brightness range. While
spatial information is preserved, quantitative radiometric information can be
lost. Two of the most common of non-linear contract stretching methods are
discussed below:
a) Histogram Equalisation
Histogram equalisation is one of the most useful forms of non-linear contrast
enhancement. When an image’s histogram is equalised, all pixel values of the
image are re-distributed so there are approximately an equal number of pixels
to each of the user-specified output gray scale classes (e.g., 32, 64, and 256). The
contrast is increased at the most populated range of brightness values of
histogram (peaks). In Fig. 12.3c, you can see how histogram equalisation at
different thresholds increases contrast of the image. It automatically reduces
contrast in very light or dark parts of the image associated with the tails of a
normally distributed histogram. Histogram equalisation can also separate pixels
into distinct groups, if there are very few output values over a wide range.
Histogram equalisation is effective only when original image has poor contrast
to start with, otherwise histogram equalisation may degrade the image quality.
b) Logarithmic Stretch
A logarithmic or square root stretch compresses the higher brightness values
within an image and disproportionately expands the darker values. It is applied
by taking the log (square root) of original brightness values. Fig. 12.4 shows
the difference between a linear and a logarithmic stretch. Thus, the original
darker values are given a greater relative contrast than original values at the
higher end of the brightness scale. This would be done in order to allow better
visual discrimination among the darker features of the image, while
maintaining some limited recognition of brighter features. The logarithmic
stretch is a more emphatic version of the square root stretch. Each of these can
be inverted (log to inverse log; square root to squared), so as to favour the
bright end of scale instead.

Logarithmic approach
stretches DN values in
darker part of histogram
whereas inverse
logarithmic approach
stretches DN values in
brighter part.

Fig. 12.4: Logic of linear, logarithmic and inverse log contrast stretch. BV indicates
brightness value (source: redrawn after Jensen, 1996)
27
Processing and The type of non-linear enhancement technique that is chosen to be performed
Classification of Remotely
Sensed Images
on an image depends on the nature of original data and what features the
analyst is interested in. For example, water features, which are typically darker
in tone, would benefit from log or square root stretches, while the land
features, which are brighter, would still be somewhat recognisable.

12.2.2 Spatial Enhancement

Point operation based enhancement techniques operate on each pixel
individually whereas spatial enhancement techniques modify pixel values
based on the values of surrounding (neighbourhood) pixels. Spatial
enhancement deals largely with the spatial frequency. Spatial frequency is the
difference between the highest and lowest values of a contiguous set of pixels.
Jensen (1996) defines spatial frequency as “the number of changes in
brightness value per unit distance for any particular part of an image”. A low
spatial frequency image consists of a smoothly varying pixel values whereas a
high spatial frequency image consists of abruptly changing pixel values
(Fig. 12.5).

(a) (b)
Fig. 12.5: (a) Example of low frequency image and (b) example of high frequency image

Spatial frequency based on the image enhancement approach is popularly

known as spatial filtering techniques. These techniques are used to improve
the appearance of image by transforming or changing pixel values in the
image. In simple terms, image filtering is a process for removing certain image
information to get more details about particular features. All filtering
algorithms involve so-called neighbourhood processing because they are based
on the relationship between neighbouring pixels rather than a single pixel. In
general, there are three types of filtering techniques as given below:
• low pass filter is used to smooth the image display by emphasising low
frequency details in an image
• high pass filter is used to sharpen the linear appearance of the image
objects such as roads and rivers by emphasising high frequency details in
an image and
• edge detection filter is used to sharpen the edges around the objects.
Low pass filters pass only the low frequency information. They produce
images that appear smooth or blurred when compared to original data. High
pass filters pass only the high frequency information, or abrupt gray level
changes. They produce images that have high frequency information. Edge
detection filters delineate edges and makes shapes more conspicuous. In
28
another approach, band pass filters are used in which a low pass filter is first Image Enhancement and
Transformation
applied and then a high pass filter is applied on an image. The low pass filter
blocks too high frequencies and high pass filter blocks the low frequency
information. Hence the resultant image has frequencies which are neither too
low nor too high.

The most commonly used filters for digital image filtering rely on the concept
of convolution and operate in the image domain for reasons of simplicity and
processing efficiency. For example, low-pass filters are mainly used to
smoothen image features and to remove noise but often at the cost of
degrading image spatial resolution (blurring). In order to remove random noise
with the minimum degradation of resolution, various edge-preserved filters
have been developed such as the adaptive median filter.

Digital image filtering is useful for enhancing lineaments that may represent
significant geological structures such as faults, veins or dykes. It can also
enhance image texture for discrimination of lithology and drainage patterns.
Digital image filtering is used for the land use studies, highlighting textures of
urban features, road systems and agricultural areas.

Check Your Progress I

Spend
1) What is image enhancement? What are some of the commonly used 5 mins
contrast enhancement techniques?
......................................................................................................................
......................................................................................................................
......................................................................................................................
......................................................................................................................
......................................................................................................................

12.3 IMAGE TRANSFORMATION

Image transformation involves manipulation of multiple bands of data, from
a single multispectral image or from two or more images of the same area
acquired at different times. In this process, a raw image or several set of
Image transformation
images undergo some mathematical treatment to achieve a new imagery. As a method is also known as
consequence, new resultant transformed image generated from two or more spectral enhancement
sources highlights particular features or properties of interest better than method. It is important to
original input images. Hence, the transformed image may have properties that note that image
transformation techniques
make it more suited to a particular purpose than original input images.
require more than one
band of data.
Image transformation techniques are useful for compressing bands having
similar kind of information into fewer bands and also to extract new bands of
data that are more interpretable to human eye. There are number of image
transformation techniques available but we will discuss here about two kinds
of image transformation techniques:

• arithmetic operations and

• image fusion.
29
Processing and 12.3.1 Arithmetic Operations
Classification of Remotely
Sensed Images One of the techniques of image transformation is to apply simple arithmetic/
logical operations to the image data. Arithmetic operations of addition,
subtraction, multiplication and division can be performed on two or more
images of the same geographical area. The prerequisite for the operation is that
all input images should be co-registered. These input images may either be
individual bands from images acquired at different dates or separate image
bands from a single multispectral image.

Subtraction function between images is used to identify changes that have

occurred between images acquired on different dates. The subtraction reveals
differences between the images and is often used for the purpose of change
detection (Fig. 12.6). Multiplication of images is somewhat different from the
other arithmetic operations because it generally involves the use of a real
image and a binary image. The binary image having two values (0 and 1) is
used as a mask. When two images are multiplied, the image pixels in the real
image that are multiplied by zero become zero and others which are multiplied
by one remain same.

Fig. 12.6: Example of image subtraction operation showing the resultant image and its
new values obtained from subtraction of image B from image A

Image division or band ratio is probably the widely used arithmetic operation.
Band ratio is an image transformation technique that is applied to enhance the
contrast between features by dividing DN for pixels in one image band by DN
of pixels in the other image band. Band ratioing technique is generally applied
on a multispectral image. Ratio is an effective technique for selectively
enhancing spectral features as shown in Fig. 12.7. Ratio images derived from
different band pairs are often used to generate ratio colour composites in a
Red, Blue and Green (RGB) display. Many indices, such as the normalised
difference vegetation index (NDVI) have been developed based on both
differencing and ratio operations.

(a) (b)
30
 Image Enhancement and
Transformation

(c) (d)
Fig. 12.7: True colour and band ratio images. (a) Landsat TM true colour composite
(RGB); (b) Thematic Mapper band (TM) 3/TM4: This ratio has defined
barren lands and urban area uniquely but it could not define water body,
forests and croplands and (c) TM2/TM3: this ratio has distinguished
croplands, barren lands sharply but it has not separated croplands, forests
and water body. Both forests and water body have appeared as lighter tone
and barren land appeared as dark tone and it did not enhance urban area.
Since chlorophyll has strong reflectance in the band 2 (0.52 -0.60 um) region
and strong absorption in the band 3 (0.63 -0.69 um) region, vegetation has
appeared as brighter tone and (d) TM3/TM5: This ratio enhanced barren
lands, highways, street patterns within the urban areas and urban built-up or
cemented areas. It could not enhance clear water but it enhanced turbid water.
This ratio is useful for observing differences in water turbidity. Barren lands,
highways, urban and built-up areas have appeared as lighter tone and forests,
water body and croplands appeared as dark tone
Band ratio is an effective technique for suppressing topographic shadows. For
a given incident angle of solar radiation, the radiation energy received by a
land surface depends on the angle between the land surface and incident
radiation (Fig. 12.8). Therefore, solar illumination on a land surface varies
with terrain slope and aspect, which results in topographic shadows. In a
remotely sensed image, the spectral information is often occluded by sharp
variations of topographic shadowing. DNs in different spectral bands of a
multispectral image are proportional to the solar radiation received by the land
surface and its spectral reflectance.

Fig. 12.8: Ratio of pixel values in NIR region to the corresponding pixel value in the
visible red region of the spectrum. The ratios for the illuminated and shaded
slopes are very similar, although pixel value differs by a factor of more than
two. Hence, an image made up of NIR:R ratio values at pixel positions will
exhibit a much reduced shadow or topographic effect (source: redrawn after
Liu and Mason, 2009) 31
Processing and Using combination of band ratio and subtraction techniques several indices
Classification of Remotely
Sensed Images
have been developed which are widely used for geological, ecological and
other applications. Of the several indices, the vegetation indices such as
normalised differential vegetation index (NDVI) are more popular. Vegetation
index (VI) is a number that is generated by some combination of remote
sensing bands and may have some relationship to the amount of vegetation in
a given image pixel. The index is computed using several spectral bands that
are sensitive to chlorophyll concentration and photosynthetic activity.

The concept of vegetation indices is based on empirical evidence that some

algebraic combination of remotely sensed spectral bands can tell us something
about vegetation. More than 200 VIs have been mentioned in scientific
literature, however, only a few of them have been systematically studied and
have biophysical meaning. Each of VIs is designed to accentuate a particular
vegetation property. Some of the widely used VIs are listed in Table 12.1.

Table 12.1: Some commonly used vegetation indices

Vegetation Index Description
Normalised difference Normalised difference of green leaf scattering in NIR,
vegetation index chlorophyll absorption in red
Simple ratio index Ratio of green leaf scattering in NIR, chlorophyll absorption
in red
Enhanced vegetation An enhancement of NDVI to better account for soil
index background and atmospheric aerosol effects
Atmospherically An enhancement of NDVI to better account for atmospheric
resistant vegetation index scattering
Sum green index Integral of scattered light in the green spectral range is
sensitive to gaps in vegetation canopy

Of the many vegetation indices we will discuss in detail about NDVI, which is
most widely used. NDVI is the acronym for Normalised Difference Vegetation
Index. It is a numerical indicator that uses visible and NIR bands of the
electromagnetic (EM) spectrum. It is mainly adopted to analyse remote
sensing measurements and assess the ‘greenness’ of the target. NDVI is a very
important tool to study vegetation from remote sensing satellite as most of the
multispectral satellite sensors have visible and infrared channels, which can be
utilised to calculate NDVI. For example, NDVI can be calculated using the red
band and infrared band of LISS III data, by applying the formula given below:

NDVI = (NIR – Red) / (NIR + Red)

NDVI works in the following ways. The pigment in plant leaves, chlorophyll
strongly absorbs visible light (from 0.4 to 0.7 μm) for use in photosynthesis.
The cell structure of leaves, on the other hand, strongly reflects NIR light
(from 0.7 to 1.1 μm). The more leaves a plant has, more these wavelengths of
light are affected, respectively. We can measure intensity of light coming off
the Earth in visible and NIR wavelengths and quantify photosynthetic capacity
of vegetation in a given pixel of land surface. In general, if there is much more
reflected radiation in NIR wavelengths than in visible wavelengths then
vegetation in that pixel is likely to be dense and may contain some types of
forest. If there is very little difference in the intensity of visible and NIR
32
wavelengths reflected, then vegetation is probably sparse and may consist of Image Enhancement and
Transformation
grassland, tundra, or desert. Since we know the behaviour of plants across EM
spectrum, we can derive NDVI information by focusing on the satellite bands
that are most sensitive to vegetation information (NIR and red). Therefore,
bigger the difference between NIR and red reflectance, more vegetation there
has to be.

NDVI algorithm subtracts red reflectance values from NIR and divides it by
the sum of NIR and red bands as mentioned in the equation above.

This normalised index formulation allows us to cope with the fact that two
identical patches of vegetation could have different values if one were, for
example in bright sunshine and another under a cloudy sky. The bright pixels
would all have larger values and therefore, a larger absolute difference
between the bands. This is avoided by dividing by the sum of reflectance
values.

Theoretically, calculations of NDVI for a given pixel always result in a

number that ranges from minus one (–1) to plus one (+1); however, in
practice, extreme negative values represent water, values around zero
represent bare soil and values over 0.6 represent dense green vegetation.

NDVI has found a wide application in vegetative studies as it has been used to
estimate crop yields, pasture performance and rangeland carrying capacities
among others. It provides a crude estimate of vegetation health and a means of
monitoring changes in vegetation over time (Fig. 12.9). It can be used to
detect seasonal changes in green biomass but can also be used to detect
changes to human activities (logging) or natural disturbances such as wild fire.
NDVI has been found to be useful for continental or global scale vegetation
monitoring because it can compensate for changing illumination conditions,
surface slope and viewing aspect.

0.50 - 0.08 0.40 - 0.30

NDVI = = 0.72 NDVI = = 0.14
0.50 + 0.08 0.40 + 0.30
NIR - RED
Note: NDVI =
NIR + RED

Fig. 12.9: Healthy vegetation absorbs most of the visible light that hits it and reflects a
large portion of NIR light. Unhealthy or sparse vegetation reflects more visible
light and less NIR light

33
Processing and It is often directly related to other ground parameters such as percent of
Classification of Remotely
Sensed Images
ground cover, photosynthetic activity of the plant, surface water, leaf area
index and the amount of biomass.

The most popular and used satellite instrument for collecting NDVI is US
National Oceanic and Atmospheric Administration’s Advanced Very High
Resolution Radiometer (AVHRR) satellite. It is sensitive to wavelengths from
0.55 - 0.7 μm and 0.73 - 1.0 μm, both of which are idealised in NDVI
calculation. AVHRR’s detectors measure intensity of light being reflected from
the different bands. Landsat TM is also used to calculate NDVI but because its
band wavelengths differ (uses bands 3 and 4), it is most often used to create
images with greater detail covering less area. Moderate Resolution Imaging
Spectroradiometer (MODIS) sensor of NASA also has an NDVI standard
product.

Despite its several uses, there are some limitations of NDVI as listed below:
Temporal Resolution: It is important to get the right balance between
temporal resolution of data and time scale of variation in the quantity
measured e.g., maximum value composites of NDVI data are rarely less than
decadal. Consequently, NDVI should not be used to investigate short-term
events like forest fires. It is more appropriate to use NDVI data to monitor
longer-term events like the growth of vegetation through a season, or annual
rates of deforestation.

Atmospheric Interference: Light is scattered in all directions by particles in

the atmosphere. Scattering tends to increase the amount of red radiation
received by the satellite as red is more readily scattered in the atmosphere than
NIR. This has the effect of reducing NDVI values.

Land Cover Types: With the exception of very large irrigation schemes and
commercial agriculture, an NDVI pixel very rarely covers a single
homogeneous agricultural region. Instead it may cover roads, buildings, bare
soil, small water bodies, natural vegetation and agriculture, all within one
pixel. An NDVI pixel is the sum of the radiation reflected from all land cover
types within the area covered by the pixel. NDVI is an indicator of the
condition of overall vegetation in an area, including natural vegetation and
agriculture. In rain-fed agriculture, natural vegetation may follow similar
patterns to the agriculture. More often however, agriculture is more
susceptible to adverse conditions and follows different growth cycles. When
looking at NDVI, always remember that you are looking at general conditions
and not necessarily the condition of a specific crop.

Sparse Vegetation and Soil Type: Light reflected from the soil can have a
significant effect on NDVI values (changing the values by up to 20%).
Generally, greater the radiance reflected from the soil, lower NDVI values.
The soil type, therefore, is an important factor. Given two soil types, one with
a greater reflectivity but with similar vegetative conditions, soil with greater
reflectivity will on average produce lower NDVI values.

Off-Nadir Effects: As a satellite sensor scans across the Earth, there is only
one point, in the centre of the scan that is directly underneath the sensor
(called sub-point or nadir). The distance from the sensor to the ground
34
increases away from the sub-point. This results in increased atmospheric Image Enhancement and
Transformation
interference as the light must pass through more atmosphere before reaching
the sensor, and therefore reduced NDVI values.

Several other indices such as Enhanced Vegetation Index (EVI) and

Atmospherically Resistant Vegetation Index (ARVI) have been developed to
take these limiting factors into considerations.

Check Your Progress II Spend

1) What is image filtering? 5 mins

......................................................................................................................
......................................................................................................................
......................................................................................................................
......................................................................................................................
......................................................................................................................
......................................................................................................................
......................................................................................................................

12.3.2 Image Fusion

Image fusion is the process of combining relevant information of two or more
remotely sensed images of a scene into a highly informative single image. The
primary reason image fusion has gained prominence in remote sensing
application is based on the fact that the remote sensing instruments have
design or observational constrains, therefore, a single image is not sufficient
for visual or machine level information analysis. In satellite imaging, two
types of images are available. The panchromatic images acquired by satellites
have higher spatial resolution and multispectral data have coarser spatial
resolution. These two image types are merged (fused) in order to get
information of both the images in one single image. The image fusion
technique, thus, allows integration of different information sources and fused
image can have complementary spatial and spectral resolution characteristics.
In other words, fused image will have spatial information of the panchromatic
image and spectral information of multispectral image.

Image fusion involves transforming a set of low or coarse spatial resolution

multispectral (colour) images to high spatial resolution colour images by
fusing a co-registered fine spatial resolution panchromatic (gray scale) image.
Usually, three low-resolution images in the visible spectrum (blue, green and
red) are used as main inputs to produce a high-resolution natural (true) colour
image as shown in Fig. 12.10, where the image 12.10b is a natural colour
image with a spatial resolution of 29 m (which has been resampled 400%) and
image 12.10a is a panchromatic image with a spatial resolution of 4 m. By
combining these inputs, a high-resolution colour image is produced
(Fig.12.10c). The fused output retains spectral signatures of input colour
image and spatial features of input panchromatic image, and usually the best
attributes of both inputs. The final output with its high spectral and spatial
resolution is often as good as high-resolution colour aerial photographs.
35
Processing and
Classification of Remotely
Sensed Images

(a) (b)

(c)
Fig. 12.10: Illustration of image fusion (merging) of IKONOS and Landsat multispectral
image. (a) High spatial resolution IKONOS image, (b) Landsat multispectral
image of the same area and (c) Fused image having spatial information of
IKONOS image and spectral (colour) information of the Landsat image.
Note the improved clarity of features in the fused image

There are many methods which are used for image fusion. These methods can
be broadly divided into two categories - spatial and transform domain fusions.
Some of the popular spatial domain methods include intensity hue saturation
(IHS) transformation, Brovey method, principal component analysis (PCA)
and high pass filtering based methods. Wavelet transform, Laplace pyramid
and curvelet transform based methods are some of the popular transform
domain fusion methods.

In this unit, we will focus on the most widely used IHS transform method.

IHS Image Fusion Technique: It is based on RGB to IHS colour space

transformation. As you know, an image is displayed in a colour monitors
through its three colour guns which correspond to the three additive primary
colours i.e. red, green and blue (RGB). When we display three bands of a
multiband image data set, the viewed image is said to be in RGB space.
36
However, it is also possible to define an alternate colour space that uses three Image Enhancement and
Transformation
parameters namely – intensity (I), hue (H) and saturation (S) instead of RGB.
IHS colour space is advantageous in that it presents colours more similar to as
perceived by the human eye.

Intensity is the overall brightness of the scene and varies from black to white
and saturation represents the purity of colour and also varies linearly while hue
represents colour or dominant wavelength of pixel. Intensity (I) component is
similar to the panchromatic image. This peculiarity is used to produce fusion
between panchromatic data having high spatial resolution and multispectral
data characterised by a high spectral resolution and less spatial detail. The
procedure of IHS based image fusion can be summarised in the following
steps (Fig. 12.11):

Fig. 12.11: RGB-IHS encoding and decoding for image fusion (source: redrawn from
Schowengerdt, 1997)

• resampling of the multispectral image (having RGB components) to the

same pixel size of the panchromatic image, using nearest neighbour
resampling criteria. This method, unlike others (Bi-linear and Cubic),
does not introduce radiometric distortion in the images

• transformation of resampled multispectral image from RGB to IHS colour

space. This step transforms RGB values to IHS values

• replace intensity (I) component of IHS image by high resolution

panchromatic image and

• perform reverse IHS-RGB transformation. This step transforms IHS

values to RGB values.

The resultant fused image is a mixture of spectral information from the low-
resolution colour composite and high spatial resolution information from the
panchromatic image, which better shows the image features. Despite being
useful, the major limitation of these image fusion techniques is that they can
distort spectral information of multispectral data while merging. Another
major disadvantage of fusion approaches is that they produce spatial distortion
in the fused image. Spectral distortion becomes a negative factor while we go
for further processing, such as classification.

37
 Image Enhancement and
UNIT 13 IMAGE CLASSIFICATION Transformation

Structure
13.1 Introduction
Objectives
13.2 Concept of Image Classification
Approaches to Classification
Stages in Classification
13.3 Unsupervised Classification
K-Means Clustering
ISODATA Clustering
13.4 Supervised Classification
Parallelepiped Classifier
Maximum Likelihood Classifier
13.5 Signature Evaluation
Spectral Signature
Ways of Signature Evaluation
13.6 Overview of Other Classification Methods
13.7 Selection of An Appropriate Classification Method
13.8 Summary
13.9 Unit End Questions
13.10 References
13.11 Further/Suggested Reading
13.12 Answers

13.1 INTRODUCTION
In the previous unit, you have learnt about different image enhancement and
transformation techniques which help us better visualise and interpret
remotely sensed images. As mentioned earlier, all these techniques aid in
providing only better visual information and, therefore, have limited utility.

In this unit, we will move a step further and learn how to make more sense of
the landscape by dividing it into separate classes based on surface
characteristics. This process is known as image classification. It involves
conversion of raster data into finite set of classes that represent surface types
in the imagery. It may be used to identify vegetation types, anthropogenic
structures, mineral resources, etc. or transient changes in any of these features.
Additionally, classified raster image can be converted to vector features (e.g.,
polygons) in order to compare with other data sets or to calculate spatial
attributes (e.g., area, perimeter, etc). Image classification is a very active field
of study broadly related to the field of pattern recognition. In this unit, we will
discuss about different image classification methods, signature evaluation and
the guidelines for selecting a classification method.

41
Processing and Objectives
Classification of Remotely
Sensed Images After studying this unit, you should be able to:
• define image classification;
• describe different image classification approaches and algorithms used in
remote sensing;
• discuss relative advantages and limitations of commonly used
classification algorithms; and
• explain how to evaluate spectral signatures.

13.2 CONCEPT OF IMAGE CLASSIFICATION

Classification is the process of assigning spectral classes into information
classes. Spectral classes are groups of pixels that are uniform with respect to
their brightness values in the different spectral channels of data. Information
classes are categories of interest that an analyst attempts to identify in the
image on the basis of his knowledge and experience about the area. For
example, a remote sensing image contains spectral signatures of several
features present on the ground in terms of pixels of different values. An
interpreter or analyst identifies homogeneous groups of pixels having similar
values and labels the groups as information classes such as water, agriculture,
forest, etc. while generating a thematic map. When this thematic information
is extracted with the help of software, it is known as digital image
classification. It is important to note that there could be many spectral classes
within an information class depending upon the nature of features the image
represents or the purpose of the classification. In other words, different
spectral classes may be grouped under one information class.

In short, we can define image classification as a process of assigning all pixels

in the image to particular classes or themes based on spectral information
represented by the digital numbers (DNs). The classified image comprises a
mosaic of pixels, each of which belong to a particular theme and is a thematic
map of the original image.

13.2.1 Approaches to Classification

There are two general approaches to image classification:
• Supervised Classification: It is the process of identification of classes
within a remote sensing data with inputs from and as directed by the user
in the form of training data, and
• Unsupervised Classification: It is the process of automatic identification
of natural groups or structures within a remote sensing data.

Both the classification approaches differ in the way the classification is

performed. In the case of supervised classification, specific land cover types
are delineated based on statistical characterisation of data drawn from known
examples in the image (known as training sites). In unsupervised
classification, however, clustering algorithms are used to uncover the
commonly occurring land cover types, with the analyst providing
interpretations of those cover types at a later stage. Merits and demerits of
42
both the supervised and unsupervised classification methods are summarised Image Classification
in Table 13.1.

Table 13.1: Merits and demerits of supervised and unsupervised

classification methods

Supervised method Unsupervised method

• Analyst has control over the
classification
• Processing is tied to specific areas of
Merits known identity
• Errors can be detected and often
rectified
• Analyst imposes a structure on data,
which may not match reality
• Training classes are generally based on
field identification and not on spectral
properties hence spectral signatures are
forced
• Training data selected by the analyst
Demerits
may not be representative of conditions
present throughout the image
• Training data can be time-consuming
and costly
• Unable to recognise and represent
special or unique categories not
represented in the training data
• No extensive prior knowledge
of the study area is required
• Opportunity for human error is
minimised
• Unique classes are recognised
as distinct units
• Spectral classes are not
necessarily information classes
• Analyst has little control over
classes
• Spectral properties change over
time hence detailed spectral
knowledge of different features
may be necessary

Both these methods can be combined together to come up with a ‘hybrid’

approach of image classification. In the hybrid classification, firstly, an
unsupervised classification is performed, then the result is interpreted using
ground referenced information and, finally, original image is reclassified using
a supervised classification with the aid of statistics of unsupervised
classification as training knowledge. This method utilises unsupervised
classification in combination with ground referenced information as a
comprehensive training procedure and, therefore, provides more objective and
reliable results.

13.2.2 Stages in Classification

The image classification process consists of following three stages (Fig. 13.1):
training, signature evaluation and decision making.

Training is the process of generating spectral signature of each class. For

example, a forest class may be defined by minimum and maximum pixel
values in different image bands, thus defining a spectral envelope for it. This
simple statistical description of the spectral envelope is known as signature.
Training can be carried out either by an image analyst with guidance from his
experience or knowledge (i.e. supervised training) or by some statistical
clustering techniques requiring little input from image analysts (i.e.
unsupervised training).

43
Processing and
Classification of Remotely
Sensed Images
A general rule of thumb is
that training data for a
class should be 10 x n
where, n is the number of
bands. You should also
remember that minimum
number of pixels in a
training site for a class
should be n +1 (Jensen,
1986).
The term classifier is
widely used as a synonym
of the term decision rule.
Algorithm
clusters data
44
There are no specific rules regarding the number of training sites per class but
it is advisable to take several training sites for each class to be mapped. If you
take very less number of training sites then it may be difficult to obtain a
spectral signature which truly represents that class and if you take large
number of training sites then a significant time may be getting wasted in
collecting and evaluating signatures with significantly improving the final
signature.
Signature Evaluation is the checking of spectral signatures for their
representativeness of the class they attempt to describe and also to ensure a
minimum of spectral overlap between signatures of different classes. We shall
discuss in detail about signature evaluation in section 13.5.
Decision Making is the process of assigning all the image pixels into thematic
classes using evaluated signatures. It is achieved using algorithms, which are
known as decision rules. The decision rules set certain criteria. When
signature of a candidate pixel passes the criteria set for a particular class, it is
assigned to that class. Pixels failing to satisfy any criteria remain unclassified.
We shall discuss in detail about the decision rules in the next two sections.
Training Signature Evaluation Decision making
Fig. 13.1: Stages in the process of image classification
In the following sections, we will discuss unsupervised and supervised
classifications in more detail.
13.3 UNSUPERVISED CLASSIFICATION
As the name implies, this form of classification is done without interpretive
guidance from an analyst. An algorithm automatically organises similar pixel
values into groups that become the basis for different classes. This is entirely
based on the statistics of the image data distribution and is often called
clustering.
The process is automatically optimised according to cluster statistics without
the use of any knowledge-based control (i.e. ground referenced data). The
method is, therefore, objective and entirely data driven. It is particularly suited
to images of targets or areas where there is no ground knowledge. Even for a
well-mapped area, unsupervised classification may reveal some spectral
features which were not apparent beforehand. The basic steps of unsupervised
classification are shown in Fig 13.2.
Find inherent Pixel classification Spectral class Analyst labels clusters
classes based on clusters map (may involve grouping
of clusters)
Informational
class map
Fig. 13.2: Steps of unsupervised classification
The result of an unsupervised classification is an image of statistical clusters, Image Classification
where the classified image still needs interpretation based on knowledge of
thematic contents of the clusters. There are hundreds of clustering algorithms
available for unsupervised classification and their use varies by the efficiency
and purpose. K-means and ISODATA are the widely used algorithms which
are discussed here.

13.3.1 K-Means Clustering

K-means algorithm assigns each pixel to a group based on an initial selection
of mean values. The iterative re-definition of groups continues till the means
reach a threshold beyond which it does not change. Pixels belonging to the
groups are then classified using a minimum-distance to means or other
principle. K-means clustering algorithm, thus, helps split a given unknown
dataset into a fixed number (k) of user defined clusters. The objective of the
algorithm is to minimise variability within the cluster.

The data point at the center of a cluster is known as a centroid. In most of the
image processing software, each centroid is an existing data point in the given
input data set, picked at random, such that all centroids are unique. Initially, a
randomised set of clusters are produced. Each centroid is thereafter set to the
arithmetic mean of cluster it defines. The process of classification
and centroid adjustment is repeated until the values of centroids stabilise. The
final centroids are used to produce final classification or clustering of input
data, effectively turning set of initially anonymous data points into a set of
data points, each with a class identity.

Advantage
• the main advantage of this algorithm is its simplicity and speed which
allows it to run on large datasets.

Disadvantages
• it does not yield the same result with each run, since the resulting clusters
depend on the initial random assignments
• it is sensitive to outliers, so, for such datasets k-medians clustering is used Outliers in remote sensing
images represent observed
and pixel values that are
• one of the main disadvantages to k-means is the fact that one must specify significantly different from
their neighbourhood pixel
the number of clusters as an input to algorithm.
values.
13.3.2 ISODATA Clustering
ISODATA (Iterative Self-Organising Data Analysis Technique) clustering
method is an extension of k-means clustering method (ERDAS, 1999). It
represents an iterative classification algorithm and is useful when one is not
sure of the number of clusters present in an image. It is iterative because it
makes a large number of passes through the remote sensing dataset until
specified results are obtained. Good results are obtained if all bands in remote
sensing image have similar data ranges. It includes automated merging of
similar clusters and splitting of heterogeneous clusters.
The clustering method requires us to input maximum number of clusters that
you want, a convergence threshold and maximum number of iterations to be
performed. ISODATA clustering takes place in the following steps:
45
Processing and • k arbitrary cluster means are established
Classification of Remotely
Sensed Images • all pixels are relocated into the closest clusters by computing distance
between pixel and cluster
• centroids of all clusters are recalculated and above step is repeated until
the threshold convergence and
• if the number of clusters are within the specified number and distances
between the clusters meet a prescribed threshold, then only clustering is
considered complete.
Advantages
• it is good at finding “true” clusters within the data
• it is not biased to the top pixels in the image
• it does not require image data to be normally distributed and
• cluster signatures can be saved, which can be easily incorporated and
manipulated along with supervised spectral signatures.

Disadvantages
• it is time consuming and
• it requires maximum number of clusters, convergence threshold and
maximum number of iteration as an input to algorithm.

13.4 SUPERVISED CLASSIFICATION

Supervised classification, as the name implies, requires human guidance. An
analyst selects a group of contiguous pixels from part of an image known as a
training area that defines DN values in each channel for a class. A
classification algorithm computes certain properties (data attributes) of set of
training pixels, for example, mean DN for each channel (Fig. 13.3). Then, DN
values of each pixel in the image are compared with the attributes of the
training set.

Fig. 13.3: Using supervised classification, pixels are classified into different categories

46
This is based on the statistics of training areas representing different ground Image Classification
objects (Fig. 13.4) selected subjectively by users on the basis of their own
knowledge or experience. Classification is controlled by users’ knowledge but,
on the other hand, is constrained and may even be biased by their subjective
view. Classification can, therefore, be misguided by inappropriate or
inaccurate training, area information and/or incomplete user knowledge. Steps
involved in supervised classification are given in Fig. 13.5.

Fig.13.4: Training data in supervised classification

Fig. 13.5: Steps involved in supervised classification

In the following subsections, we will discuss parallelepiped and maximum

likelihood algorithms of supervised image classification.

13.4.1 Parallelepiped Classifier

Parallelepiped classifier uses the class limits stored in each class signature to
determine if a given pixel falls within the class or not. The class limits specify
the dimensions (in standard deviation units) of each side of a parallelepiped
surrounding mean of the class in feature space. If pixel falls inside the
parallelepiped, it is assigned to the class. However, if pixel falls within more
than one class, it is put in the overlap class. If pixel does not fall inside any
class, it is assigned to the null class.

In parallelepiped classifiers, an n-dimensional box is constructed around

pixels within each category of interest (Fig. 13.6). The n-dimensional space
defined by the parallelepiped delimits different categories.

47
Processing and
Classification of Remotely
Sensed Images

Fig. 13.6: Using the parallelepiped approach, pixel 1 is classified as forest and pixel 2 is
classified as urban

Classification using this classifier is carried out in the following steps:

Step 1: Define the range of values in each training area and use these ranges to
construct an n-dimensional box (a parallelepiped) around each class.
Step 2: Use multi-dimensional ranges to create different surface categories.
Notice that there can be overlap between the categories when simple method
is used. One solution to this problem is to use a stepped decision region
boundary.

Advantages
• it is a simple and computationally inexpensive method and
• it does not assume a class statistical distribution and includes class
variance.
Disadvantages
• it is least accurate method
• it does not adapt well to elongated (high-covariance) clusters
• it often produces overlapping classes, requiring a second classification
step
• it also becomes more cumbersome with increasing number of channels
and
• pixels falling outside the defined parallelepiped remain unclassified.

13.4.2 Maximum Likelihood Classifier

Maximum likelihood (MXL) classifier is one of the most widely used
classifiers in the remote sensing. In this method, a pixel is assigned to the class
for which it has maximum likelihood of membership. This classification
48
algorithm uses training data to estimate means and variances of the classes, Image Classification
which are then used to estimate probabilities of pixels to belong to different
classes. Maximum likelihood classification considers not only mean or
average values in assigning classification but also the variability of brightness
values in each class around the mean. It is the most powerful of the
classification algorithms as long as accurate training data is provided and
certain assumptions regarding the distributions of classes are valid.

An advantage of this algorithm is that it provides an estimate of overlap areas

based on statistics. This method is different from parallelepiped in that it uses
only maximum and minimum pixel values. The distribution of data in each
training set is described by a mean vector and a covariance matrix. Pixels are
assigned a posteriori probability of belonging to a given class and placed in
the most ‘‘likely’’ class. This is the only algorithm in this list that takes into
account the shape of the training set distribution.

Maximum likelihood classifiers use expected (normal) distribution of DN

values to define the probability of a pixel being within a certain class. Plotting
the number of pixels with any given DN value yields a histogram or
distribution of DN values within a particular band. Studies have shown that
for most surfaces DN values from visible or near-infrared (NIR) region of the
electromagnetic (EM) spectrum have a normal probability distribution. It
means we can define curves based on the mean and standard deviation of the
sample that describe the normal probability distribution by selecting category
that has highest statistical probability for each pixel. These concentric circles,
called equi-probability contours, are derived from an assumed normal
distribution around each training site. Equi-probability contours define the
level of statistical confidence in the classification accuracy. Smaller the
contour, higher is the statistical confidence.

Advantages
• it is one of the most accurate methods
• it overcomes unclassified pixel problem (subject to threshold values)
• it provides a consistent way to separate pixels in overlap zones between
classes and
• assignment of pixels to classes can be weighted by prior knowledge of the
likelihood that a class is correct.
Disadvantages
• cluster distributions are assumed to be Gaussian in each class and band.
Algorithm requires enough pixels in each training area to describe a
normal population and assumes class covariance matrices are similar
• classes not assigned to training sets tend to be misclassified – a particular
problem for mixtures
• it is reliant on the accuracy of training data. Changes in training set of any
one class can affect the decision boundaries with other classes
• it is relatively computationally expensive and
• it is also not practical with imaging spectrometer data.

49
Processing and
Classification of Remotely
Sensed Images
Accuracy defines
correctness and it
measures the degree of
agreement between a
standard that assumed to
be correct and a map
created from an image. A
visually interpreted map or
classified image is only
said to be highly accurate,
when it corresponds
closely with the assumed
standard.
60
Objectives
After studying this unit, you should be able to:
• define accuracy assessment;
• discuss need for accuracy assessment;
• generate a error matrix for interpreted outputs;
• explain the role of sampling size in accuracy assessment; and
• list measures for accuracy assessment.
14.2 CONCEPT OF ACCURACY ASSESSMENT
Accuracy assessment is the final step in the analysis of remote sensing data
which help us to verify how accurate our results are. It is carried out once the
interpretation/classification has been completed. Here, we are interested in
assessing accuracy of thematic maps or classified images which is known as
thematic or classification accuracy. The accuracy is concerned with the
correspondence between class label and ‘true’ class. A ‘true’ class is defined as
what is observed on the ground during field surveys. For example, a class
labeled as water on a classified image/map is actually water on the ground.
In order to perform accuracy assessment correctly, we need to compare two
sources of information which include:
• interpreted map/classified image derived from the remote sensing data and
• reference map, high resolution images or ground truth data.
Relationship between these two sets of information is commonly expressed in
two forms, namely -
• error matrix that describes the comparison of these two sources of
information and
• Kappa coefficient which consists a multivariate measure of agreement
between rows and columns of error matrix.
The error matrix and kappa coefficient have been discussed in detail in the
sections 14.4 and 14.5, respectively. However, let us first discuss what
accuracy assessment is along with its need and sources of errors.
14.2.1 Definition
Accuracy is referred to in many different contexts. In the context of image
interpretation, accuracy assessment determines the quality of information
derived from remotely sensed data. Assessment can be either qualitative or
quantitative. In qualitative assessment, you determine if a map ‘looks right’ by
comparing what you see in the map or image with what you see on the ground.
However, quantitative assessments attempt to identify and measure remote
sensing based map errors. In such assessments, you compare map data with
ground truth data, which is assumed to be 100% correct.
Accuracy of image classification is most often reported as a percentage correct
and is represented in terms of consumer’s accuracy and producer’s accuracy.
The consumer’s accuracy (CA) is computed using the number of correctly
classified pixels to the total number of pixels assigned to a particular category.
It takes errors of commission into account by telling the consumer that, for all
areas identified as category X, a certain percentage are actually correct. The Accuracy Assessment
producer’s accuracy (PA) informs the image analyst of the number of pixels
correctly classified in a particular category as a percentage of the total number The term consumer’s
of pixels actually belonging to that category in the image. Producer’s accuracy accuracy is used when a
measures errors of omission. classified image is
examined from the user’s
14.2.2 Need for Accuracy Assessment point of view. Producer’s
accuracy is used when
The need for assessing accuracy of a map generated from any remotely sensed same is viewed from
product has become a universal requirement and an integral part of any analyst’s perspective.
classification project. The user community needs to know accuracy of the
classified image data being used. Moreover, different projects have different
accuracy requirement and only those classified images which are above a
certain level of accuracy can be used. Furthermore, accuracy becomes a
critical issue while working in a Geographical Information System (GIS)
framework where you use several layers of remotely sensed data. In such
cases, it would be very important to know the overall accuracy which is
dependent upon knowing the accuracy of each of data layers.
There are a number of reasons why assessment of accuracy is so important.
Some of them are given below:
• accuracy assessment allows self-evaluation and to learn from mistakes in
the classification process
• it provides quantitative comparison of various methods, algorithms and
analysts and
• it also ensures greater reliability of the resulting maps/spatial information
to use in decision-making process.
The need for accuracy assessment is emphasised in literature as well as in
anecdotal evidence. For example, maps of wetlands from various states of
India (e.g., Jammu and Kashmir, Rajasthan, Tamil Nadu, West Bengal) have
been made by several central, state and local agencies using techniques that
included satellite images, aerial photographs and field data. Simply comparing
the various wetland maps would yield little agreement about location, size and
extent of these. In the absence of a valid accuracy assessment you may never
know which of these maps to use.
A map using remotely sensed or other spatial data cannot be regarded as the
final product without taking necessary steps towards assessing accuracy or
validity of that map.
A number of methods exist to investigate accuracy/error in spatial data
including visual inspection, non-site-specific analysis, generating difference
images, error budget analysis and quantitative accuracy assessment.

14.2.3 Sources of Errors

Classification error occurs when a pixel (or feature) belonging to one category
is assigned to another category. Errors of omission occur when a feature is left
out of the category being evaluated. Errors of commission occur when a
feature is incorrectly included in the category being evaluated. For example,
errors of omission are the allotment of errors of barren land on the ground to
the agricultural land category on the map. This has caused the removal of an
area of real barren land on the ground from the map. In the same way, errors of
commission will be the assignment an area of agricultural land on the ground 61
Processing and
Classification of Remotely
Sensed Images
In non-site-specific
accuracy, for example,
two images or maps can
be compared only on the
basis of total area in each
category as shown in Fig.
14.1a. In site-specific
accuracy two images are
compared on the basis of
pixel-by-pixel or cell-by-
cell as shown in Fig.
14.1b.
62
to the barren land on the map. Hence, an error of omission in one category will
be counted as an error of commission in another category.
As you know that accuracy assessment is performed by comparing the map
produced by remote sensing analysis to a reference map based on a different
information source. One might ask why remote sensing analysis is needed if
the reference map for comparison already exists. One of the primary purposes
of accuracy assessment and error analysis in this case is to permit quantitative
comparisons of different interpretations. Classifications done from images
acquired at different times, classified by different procedures, or produced by
different individuals can be evaluated using a pixel-by-pixel and point-by-
point comparison. The results must be considered in the context of the
application to determine which is the most correct or most useful for a
particular purpose. In order to be compared, both the map to be evaluated, the
reference map must be accurately registered geometrically to each other. They
must have been classified using same scheme and at the same level of detail.
One simple method of comparison is to calculate the total area assigned to
each category in both maps and to compare the overall figures. This type of
assessment is called non-site-specific accuracy (Fig. 14.1a). On the other
hand, site-specific accuracy is based on a comparison of the two maps at
specific locations (i.e. individual pixels in two digital images) (Fig. 14.1b). In
this type of comparison, it is obvious that the degree to which pixels in one
image spatially align with pixels in the second image contributes to the
accuracy assessment result. It is important to note that errors in classification
should be distinguished from errors in registration or positioning of
boundaries. Another useful form of site-specific accuracy assessment is to
compare field or training data at a number of locations within the image,
similar to the way spatial accuracy assessment using ground check points is
performed for digital orthophotographs and terrain models.
Fig. 14.1: (a) Non-site-specific accuracy in which two images are compared based on
their total areas. Note that the area of image 1(i.e. A+B+C) is equal to the area
of image 2 (i.e. A+B+C) and (b) site-specific accuracy in which two images are
compared on a site-by-site (i.e. cell-by-cell or pixel by pixel) (source: modified
from Campbell, 1996)