WAVELET TRANSFORM BASED IMAGE RETRIEVAL

SYSTEM BY USING INTERACTIVE GENETIC ALGORITHM

Chesti Altaff Hussain*1, MIE Dr.D.Venkata Rao2, FIE Dr.S.Aruna Mastani3

1
Department of ECE, JNTU College of Engineering,Anatapuramu,chestialtaff@gmail.com
2
Principal, Narasaraopet Institute of Technology,Narasaraopet,dv2002in@yahoo.co.in
3
Assistant Professor, JNTU College of Engineering,Anantapuramu,aruna_mastani@yahoo.com

Abstract: CBIR has become an active and fast- for better retrieval of image according to the
advancing research area in image retrieval. The application. Approximation of the user’s
primary goal of the CBIR system is to construct information need for the following search in the
meaningful descriptions of physical attributes from
image database, involving user’s interaction is
images to facilitate efficient and effective retrieval. In
necessary for a CBIR system.
order to increase the accuracy of image retrieval, a
Chin-Chin Lai et.al.[23] have proposed an
content-based image retrieval system based on
interactive genetic algorithm (IGA) is proposed. The
interactive genetic algorithm (IGA) to reduce the

retrieval process is divided into two stages. In the
query stage, the feature descriptors of a query image
were extracted and then used to evaluate the
similarity between the query image and those images
in the database. In the evolution stage, the most
relevant images were retrieved by using the IGA.
IGA is employed to help the users identify the images
that are most satisfied to the users’ need. The
experimental evaluation of the system is based on a
10000 WANG color image database. Experimental
gap between the retrieval results and the users’
expectation .They have used Color attributes like
the mean value, standard deviation, and image
bitmap .They have also used texture features like
the entropy based on the gray level co-occurrence
matrix and the edge histogram. Sung-Bae Cho and
Joo-Young Lee [24] have proposed A Human-
Oriented Image Retrieval System that extracts the
features from images by wavelet transform and

results demonstrate the feasibility of the proposed
approach.
Keywords: Discrete Wavelet Transform, gray level co-
occurrence matrix, color covariance matrix, interactive
genetic algorithm
I. INTRODUCTION
Content based features are mainly divided into two
domains; Common visual features and field
specific visual features like face recognition, task
dependent applications etc. On the other hand, high
level features include semantic based image
retrieval computed from text description or by
complex algorithms of visual features [1,2]. The
mixture of these content based features is required
provides a user-friendly means to retrieve an image
from a large database when the user cannot clearly
define what the image must be. Linying Jiang
et.al[25] have proposed CBIR algorithm oriented
by Users’ Experience in order to improve the
storage efficiency, retrieval speed and accuracy of
the existing CBIR algorithm as well as to improve
the quality of user experience.
HSV is an intuitive color space in the sense that
each component contributes directly to visual
perception, and it is common for image retrieval
systems. Hue is used to distinguish colors, whereas
saturation gives a measure of the percentage of
white light added to a pure color. Value refers to
the perceived light intensity. The important
advantages of HSV color space are as follows:
good compatibility with human intuition,
separability of chromatic and achromatic either a low pass frequency operation or
components, and possibility of preferring one high pass frequency operation to the rows,
component to other. The conversion formula’s are and the second letter refers to the filter
as following: applied to the columns. The lowest
resolution level LL consists of the
1
⌊(𝑅 − 𝐺 ) + ( 𝑅 − 𝐵)⌋ approximation part of the original image.
𝐻 = cos −1 ( 2 )
√( 𝑅 − 𝐺 )2 + (𝑅 − 𝐵)(𝐺 − 𝐵) The remaining three resolution levels
consist of the detail parts and give the
3
𝑆 =1− [min( 𝑅, 𝐺, 𝐵)] vertical high (LH), horizontal high (HL) and
𝑅+𝐺+𝐵
high (HH) frequencies. Figure 1 shows
𝑅+𝐺+𝐵
𝑉= three-level wavelet decomposition of an
3
image.
Texture is an important attribute that refers to
innate surface properties of an object and their
relationship to the surrounding environment. If we
could choose appropriate texture descriptors, the
performance of the CBIR should be improved. We
use a gray level co-occurrence matrix (GLCM),
which is a simple and effective method for
representing texture.

The wavelet transform (WT) has gained

widespread acceptance in signal processing and
image compression. Because of their inherent
Figure 1: Decompsing an image
multi-resolution nature, wavelet-coding
schemes are especially suitable for applications In the field of artificial intelligence, a genetic
where scalability and tolerable degradation are algorithm (GA) is a search heuristic that mimics
important Wavelet transform decomposes a the process of natural selection. This heuristic (also
signal into a set of basis functions. These basis sometimes called a metaheuristic) is routinely used
functions are called wavelets. Wavelets are to generate useful solutions
obtained from a single prototype wavelet 𝛹(𝑡) to optimization and search problems. In a genetic
called mother wavelet by dilations and shifting: algorithm, a population of candidate
solutions (called individuals, creatures,
1𝑡−𝑏
𝛹𝑎,𝑏 (𝑡) = 𝛹( ) or phenotypes) to an optimization problem is
√𝑎 𝑎
evolved toward better solutions. Each candidate
Discrete Wavelet transform (DWT) is a solution has a set of properties
mathematical tool for hierarchically (its chromosomes or genotype) which can be
decomposing an image. The DWT mutated and altered; traditionally, solutions are
decomposes an input image into four represented in binary as strings of 0s and 1s, but
components labeled as LL, HL, LH and HH. other encodings are also possible. GAs have the
The first letter corresponds to applying following advantages over traditional search
methods: 1) They directly work with a coding of
the parameter set; 2) the search process is carried
out from a population of potential solutions; 3)
payoff information is used instead of derivatives or
auxiliary knowledge; and 4) probabilistic transition
rules are used instead of deterministic ones.

II. RELATED WORK

The color features vector of query and database

images are computed in HSV color space. The
histogram analysis of an image better in Hue
Saturation Value (HSV) space than RGB. Hence
our proposed method includes HSV mapping to
obtain the color map histogram. Figure 2 shows Fig 3: Wavelet Decomposition for Texture Based
Image Retrieval
the basic block diagram of content based image
The interactive genetic algorithm is as
retrieval system. 2D DWT is applied on the HSV
following:
mapped images with the applied 4 conditions i.e.,
LL, LH, HL, HH. Wavelet Decomposition for ALGORITHM:
Texture Based Image Retrieval is shown in figure
3. In order to reduce the size of the matrix GLCM Input : Population
For each chromosome in population
(gray level co-occurrence matrix) is applied for Do
better retrieval accuracy. Repeat
Found 0
for all the routers of current tour do
for all the edges on current tour do
if feasible insertion then
Found 1
Endif
Endfall
Endfall
If found = 1 then
Insert customer
Else if multiple route are feasible
then
Insert customer into new
Route
Else
Create new current tour
Create new first route
Endif
Until all chromosomes are routed
Repeat
endfch

Fig 2: Basic block diagram of content based image

retrieval system
 III. RESULTS ANALYSIS

We propose a new algorithm that retrieves the

images based on color, texture and metadata
features. Here, the retrieval accuracy will be
high with the two different algorithms: color
and texture based. The proximity between two
images is calculated using two different
techniques too: ED between color histograms
and ED between wavelet energies. The figures4
& 5 below shows the retrieved images in two
different phases.

Fig 5 : Image Retrieval using GA2

IV. CONCLUSION

Whatever, the size and content of the image

database is, a human being can easily recognize
images of same category. In this work, representing
and retrieving the image properties of color, texture
are used using interactive genetic algorithm (IGA)
for better approximation with user interaction.
CBIR is still a developing science the IGA can be
considered and used as a semi automated
exploration tool with the help of a user that can
navigate a complex universe of images.
Experimental results of the proposed approach
have shown the significant improvement in
Fig 4 : Image Retrieval using GA1
retrieval performance. Further work considering
comparing the retrieved results with that of
saliency mapped images is in progress.

V. REFERENCES

[1] M. Antonelli, S. G. Dellepiane, and M. Goccia, “Design and

implementation of Web-based systems for image segmentation
and CBIR,” IEEE Trans. Instrum. Meas., vol. 55, no. 6, pp.
1869–1877, Dec. 2006.
[2] N. Jhanwar, S. Chaudhuri, G. Seetharaman, and B.
Zavidovique, “Content based image retrieval using motif
cooccurrence matrix,” Image Vis. Comput., vol. 22, no. 14, pp. [24]S.-B. Cho and J.-Y. Lee, “A human-oriented image retrieval
1211–1220, Dec. 2004. system using interactive genetic
[3] J. Han, K. N. Ngan, M. Li, and H.-J. Zhang, “A memory algorithm,” IEEE Trans. Syst., Man, Cybern. A, Syst.,Humans,
learning framework for effective image retrieval,” IEEE Trans. vol. 32, no. 3, pp.
Image Process., vol. 14,no. 4, pp. 511–524, Apr. 2005. 452–458, May 2002.
[4] H. Takagi, S.-B. Cho, and T. Noda, “Evaluation of an IGA- [25] Linying Jiang, Jiefu Ren, Dancheng Li,” Content Based
based image retrieval system using wavelet coefficients,” in Image Retrieval algorithm oriented by Users’ Experience,” 7th
Proc. IEEE Int. Fuzzy Syst. Conf., 1999, vol. 3, pp. 1775–1780. International Conference on Computer Science &
[5] H. Takagi, “Interactive optimization and human evaluation,” Education (ICCSE 2012),July 14-17, 2012
Proc. IEEE, vol. 89, no. 9,pp. 1275–1296, Sep. 2001.
[6] S.-B. Cho and J.-Y. Lee, “A human-oriented image retrieval
system using interactive genetic algorithm,” IEEE Trans. Syst.,
Man, Cybern. A, Syst.,Humans, vol. 32, no. 3, pp. 452–458, May
2002.
[7] Y. Liu, D. Zhang, G. Lu, andW.-Y.Ma, “A survey of
content-based image retrieval with high-level semantics,”
Pattern Recognit., vol. 40, no. 1,pp. 262–282, Jan. 2007.
[8] A. W. M. Smeulders, M. Worring, S. Santini, A. Gupta, and
R. Jain,“Content-based image retrieval at the end of the early
years,” IEEE Trans.Pattern Anal. Mach. Intell., vol. 22, no. 12,
pp. 1349–1380, Dec. 2000.
[9] S. Antani, R. Kasturi, and R. Jain, “A survey of the use of
pattern recognition methods for abstraction, indexing and
retrieval of images and video,” Pattern Recognit., vol. 35, no. 4,
pp. 945–965, Apr. 2002.
[10] X. S. Zhou and T. S. Huang, “Relevance feedback in
content-based image retrieval: Some recent advances,” Inf. Sci.,
vol. 148, no. 1–4, pp. 129–137, Dec. 2002.
[11] H.-W. Yoo, H.-S. Park, and D.-S. Jang, “Expert system for
color image retrieval,” Expert Syst. Appl., vol. 28, no. 2, pp.
347–357, Feb. 2005.
[12] T.-C. Lu and C.-C. Chang, “Color image retrieval
technique based on color features and image bitmap,” Inf.
Process. Manage., vol. 43, no. 2,pp. 461–472, Mar. 2007.
[13] A. Vadivel, S. Sural, and A. K. Majumdar, “An integrated
color and intensity co-occurrence matrix,” Pattern Recognit.
Lett., vol. 28, no. 8, pp. 974–983, Jun. 2007.
[14] M. H. Pi, C. S. Tong, S. K. Choy, and H. Zhang, “A fast
and effective model for wavelet subband histograms and its
application in texture image retrieval,” IEEE Trans. Image
Process., vol. 15, no. 10, pp. 3078–3088,Oct. 2006.
[15] M. Kokare, P. K. Biswas, and B. N. Chatterji, “Texture
image retrieval using new rotated complex wavelet filters,”
IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 35, no. 6, pp.
1168–1178, Dec. 2005.
[16] M. Pi and H. Li, “Fractal indexing with the joint statistical
properties and its application in texture image retrieval,” IET
Image Process., vol. 2,no. 4, pp. 218–230, Aug. 2008.
[17] S. Liapis and G. Tziritas, “Color and texture image retrieval
using chromaticity histograms and wavelet frames,” IEEE
Trans. Multimedia, vol. 6, no. 5, pp. 676–686, Oct. 2004.
[18] Y. D. Chun, N. C. Kim, and I. H. Jang, “Content-based
image retrieval using multiresolution color and texture features,”
IEEE Trans. Multimedia, vol. 10, no. 6, pp. 1073–1084, Oct.
2008.
[19] S.-B. Cho, “Towards creative evolutionary systems with
interactive genetic algorithm,” Appl. Intell., vol. 16, no. 2, pp.
129–138, Mar. 2002.
[20] S.-F. Wang, X.-F. Wang, and J. Xue, “An improved
interactive genetic algorithm incorporating relevant feedback,”
in Proc. 4th Int. Conf. Mach. Learn. Cybern., Guangzhou,
China, 2005, pp. 2996–3001.
[21] M. Arevalillo-Herráez, F. H. Ferri, and S. Moreno-Picot,
“Distance-based relevance feedback using a hybrid interactive
genetic algorithm for image retrieval,” Appl. Soft Comput., vol.
11, no. 2, pp. 1782–1791, Mar. 2011,DOI:
10.1016/j.asoc.2010.05.022.
[22] S. Shi, J.-Z. Li, and L. Lin, “Face image retrieval method
based on improved IGA and SVM,” in Proc. ICIC, vol. 4681,
LNCS, D.-S. Huang, L. Heutte, and M. Loog, Eds., 2007, pp.
767–774.
[23]Chih-Chin Lai, "A User-Oriented Image Retrieval System
Based on Interactive Genetic Algorithm,"IEEE
TRANSACTIONS ON INSTRUMENTATION AND
MEASUREMENT/0018-9456/2011.