Professional Documents
Culture Documents
Lecture 1
Lecture 1
Course Description:
The course covers image sampling and quantization, color, point operations,
segmentation, morphological image processing, linear image filtering and
correlation, image transforms, multi-resolution image processing, image
compression, noise reduction and image restoration. Emphasis is on the
general principles of image processing and practical projects.
• An Introduction to
Digital Image Processing
with Matlab Notes for
SCM2511 Image
Processing
• Lecture Notes
CS451 – Digital Image Processing
Instructors:
Prof. Walid Al-Atabany w.al-atabany@nu.edu.eg
Dr. Mustafa A. Elattar melattar@nu.edu.eg
Office hours:
Sun 10:30 - 11:30
Wednesday 10:30 - 11:30
Location: (First Floor) 210
Course Grading Scheme
Quiz 10
Project 15
Assignments 15
Labs 15
Midterm 15
Final Exam 30
Total 100
Course contents
• Introduction to Image Processing
• Image representation
• Image enhancement and filtering
– Point processing
– Histogram processing
– Spatial filtering
– Edge detection
• Image enhancement and filtering in Frequency domain
• Image morphology
• Image coding and compression
• Image segmentation
• Applications
Policies
• Work groups
You must work alone on all assignments stated unless otherwise
• Submission
Assignments due will be announcement
Electronic or physical submissions (no exceptions!)
• Lateness penalties
Get penalized 10% per day
No late submission later than 3 days after due date
Today
Fundamentals of
Image Processing
What is image processing?
➢ What does it mean, to see?
➢ Vision as a computational problem
➢ Sample image processing problems
What does it mean, to see?
• vision is the process of discovering from images what is
present in the world, and where it is.” David Marr, Vision, 1982
• Our brain is able to use an image as an input, and interpret it
in terms of objects and scene structures.
Why does vision appear easy to humans?
• Our brains are specialized to do vision.
• Nearly half of the cortex in a human brain is devoted to doing
vision (motor control ~20-30%, language ~10-20%)
Visual Modules and the Information Flow
• Vision modules can be categorized into three groups according
to their functionality:
➢ Low-level vision: filtering out irrelevant image data
➢ Mid-level vision: grouping pixels or boundary fragments together
➢ High-level vision: complex cognitive processes
Fundamentals of Image Processing
• What is a digital image, how it is formed?
• How images are represented in computers?
• Why we process images?
• How we process images?
Image Formation
• What is measured in an image location?
• – brightness
• – color
Image Formation
Grouping of pixels
according to what
criteria?
• Boundary-based segmentation
• Region-based segmentation
• Unified formulations
Image Segmentation
• From contours to regions
Image Segmentation
Image Resizing
• Resize an image to arbitrary aspect ratios
Image Retargetting
• Resize an image to arbitrary aspect ratios
Image Retargetting
Image Compression
Face and Gesture recognition
Image processing and Relationship with other
Fields
Components in Digital Image Processing
isible camera
nfrared camera
eam plitter
nput scene
Light is part of the Electromagnetic wave
Combined spectra
• Different bands give totally different images of the same object
Optic
Nerve
Lateral
Geniculate
Nucleus
(LGN)
Optic
Nerve
Visual Cortex
Basic retinal processing
Image capture
Smoothing, Gain
control
Centre surround
processing
Spike coding
Hierarchy of Visual Areas
• There are many different neural connections between different
visual areas.
Figures: Nikos K. Logothetis, Vision: A Window on Consciousness, SciAm, Nov 1999F (on the left) Felleman & van Essen, 1991 (on the right)
Photoreceptors
Rod M - cone
S - cone
L - cone
Photoreceptors
• Rods
➢ night vision
➢ Low acuity
➢ Achromatic
• Cones
➢ Day vision
➢ High acuity
➢ Chromatic
➢ Three sets, with different sensitivity functions
700nm (R), 546nm (G), 435nm (B)
Eye vs. Camera
Color Representation
• Specify three primary colors directly
➢ Red, Green, Blue (RGB)
➢ Cyan, Magenta, Yellow (CMY)
• Specify the luminance and chrominance
➢ HSB or HSI (Hue, saturation, and brightness or intensity)
➢ YCbCr (used in digital color TV)
• Amplitude specification:
➢ 8 bits per color component, or 24 bits per pixel
➢ Total of 16 million colors
➢ 1kx1k true RGB color requires 3 MB memory
Digital Image Capture by CCD Array
• Continuous Scene -> Digital image
➢ Each CCD sensor averages the light intensity in a small region and output
a discretized value
Grayscale Image Specification
• Each pixel value represents the brightness of the pixel. With 8-
bit image, the pixel value of each pixel is 0 ~ 255
• Matrix representation: An image of MxN pixels is represented by
an MxN array, each element being an unsigned integer of 8 bits
Color Image Specification
• Three components
➢M = {R, G, B}
Images in Matlab
• Images represented as a matrix
• Suppose we have a NxM RGB image called “im”
➢ im(1,1,1) = top-left pixel value in R-channel
➢ im(y,x,b) = y pixels down, x pixels to right in the bth channel
➢ im(N,M,3) = bottom-right pixel in B-channel
• imread(filename) returns a uint8 image (values 0 to 255)
➢ Convert to double format (values 0 to 1) with im2double
A Brief Matrix Tutorial
• A matrix is an NxM array of numbers
➢ If M=N, A is a square matrix
➢ If N = 1, A is a row vector
➢ If M = 1, A is a column vector
➢ If N=M=1, A is a scalar
➢ aij is the element of A at row i and column j.
• Special Matrix
➢ Identity (unit) matrix I
➢ Diagonal matrix
Matrix Operations
• Addition / Subtraction of matrices.
➢ Matrices A and B are of the same order (NxM)j
Questions