International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882

Volume 5, Issue 12, December 2016

Content Based Image Retrieval using Color feature

Brunda S1, Chaitra H.K2,
1

Student, Computer Science and Engineering, SJB Institute of Technology, Karnataka, India
Assistant professor, Computer Science and Engineering, SJB Institute of Technology, Karnataka, India

Abstract

2. LITERATURE SURVEY

Content-based image retrieval is a very important area of

research nowadays. Content-Based Image Retrieval
(CBIR) uses the visual contents of an image such as
color, shape, texture, and spatial layout to represent and
index the image. Active research in CBIR is geared
towards the development of methodologies for
analyzing, interpreting cataloging and indexing image
databases. In addition to their development, efforts are
also being made to evaluate the performance of image
retrieval systems. The quality of response is heavily
dependent on the choice of the method used to generate
feature vectors and similarity measure for comparison of
features. In this paper color analysis has shown and the
information about object location, shape, and texture is
discarded. Thus the images retrieved by using the mat
lab tool.

2.1 The growth of digital imaging

The use of images in human communication is
hardly new cave-dwelling ancestors painted pictures on
the walls of their caves, and the use of maps and
building plans to convey information almost certainly
dates back to pre-Roman times. But the twentieth
century has witnessed unparalleled growth in the
number, availability and importance of images in all
walks of life. Images now play a crucial role in fields as
diverse as medicine, journalism, advertising, design,
education and entertainment [1].

1.1 Content Based Image Retrieval

Technology, in the form of inventions such as

photography and television, has played a major role in
facilitating the capture and communication of image
data. But the real engine of the imaging revolution has
been the computer, bringing with it a range of techniques
for digital image capture, processing, storage and
transmission which would surely have startled even
pioneers like John Logie Baird [2]. The involvement of
computers in imaging can be dated back to 1965, with
Ivan Sutherlands Sketchpad paper, which demonstrated
the feasibility of computerized creation, manipulation
and storage of images, though the high cost of hardware
limited their use until the mid-1980s [3].

Content-based image retrieval (CBIR), also

known as query by image content (QBIC) and contentbased visual information retrieval (CBVIR) is the
application of computer vision to the image retrieval
problem, that is, the problem of searching for digital
images in large databases. "Content-based" means that
the search will analyze the actual contents of the image.
The term 'content' in this context might refer colors,
shapes, textures, or any other information that can be
derived from the image itself. Without the ability to
examine image content, searches must rely on metadata
such as captions or keywords. Such metadata must be
generated by a human and stored alongside each image
in the database.

Once computerized imaging became affordable

(thanks largely to the development of a mass market for
computer games), it soon penetrated into areas
traditionally depending heavily on images for
communication, such as engineering, architecture and
medicine [4]. Photograph libraries, art galleries and
museums, too, began to see the advantages of making
their collections available in electronic form. The
creation of the World-Wide Web in the early 1990s,
enabling users to access data in a variety of media from
anywhere on the planet, has provided a further massive
stimulus to the exploitation of digital images. The
number of images available on the Web was recently
estimated to be between 10 and 30 million [Scarf et al,

Keywords: - Content Based Image Retrieval, Shape,

Color Coherence Vector, Centroid, Segmentation

1. INTRODUCTION

www.ijsret.org

580

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 5, Issue 12, December 2016

1997] a figure which some observers consider to be a

significant underestimate [5].

this area include defining 3-D shape similarity measures,

and providing a means for users to formulate 3-D shape
queries.

2.2 Current level 1 CBIR techniques

2.3 Motivational factors
2.2.1

Color retrieval
2.3.1 Social factors:

Several methods for retrieving images on the

basis of color similarity have been described in the
literature, but most are variations on the same basic idea.
Each image added to the collection is analyzed to
compute a color histogram which shows the proportion
of pixels of each color within the image. The color
histogram for each image is then stored in the database.
At search time, the user can either specify the desired
proportion of each color (75% olive green and 25% red,
for example), or submit an example image from which a
color histogram is calculated. Either way, the matching
process then retrieves those images whose color
histograms match those of the query most closely. The
matching technique most commonly used, histogram
intersection, was first developed by Swain and Ballard
[1991]. Variants of this technique are now used in a high
proportion of current CBIR systems.
2.2.2

Texture retrieval

The ability to retrieve images on the basis of

texture similarity may not seem very useful. But the
ability to match on texture similarity can often be useful
in distinguishing between areas of images with similar
color. Alternative methods of texture analysis for
retrieval include the use of Gabor filters and fractals. A
recent extension of the technique is the texture thesaurus,
which retrieves textured regions in images on the basis
of similarity to automatically-derived code words
representing important classes of texture within the
collection.

It is a truism to observe that images are currently

used in all walks of life. The influence of television and
video games in todays society is clear for all to see. The
commonest single reason for storing, transmitting and
displaying images is probably for recreational use,
though this category includes a wide variety of different
attitudes and interaction styles, from passively watching
the latest episode of a soap opera to actively analyzing a
tennis stars shots in the hope of improving ones own
game. Images are increasingly used to convey
information, in areas as diverse as map-making, weather
forecasting and mail-order shopping, and to persuade or
convey a mood, as in advertising. They can also be
appreciated in their own right, as works of art.
2.3.2 Industrial factors:
In the realm of professional image use, the
situation is rather different. Some groups of people use
images in their job on a daily basis, such as graphic
designers and illustrators, whilst others may never be
required to use them, such as bank managers and
accountants. There is a wide range of professions lying
between these two extremes, including medicine and
law. Other groups of workers, such as librarians and
museum curators, may be required to find images on
behalf of clients rather than for themselves. It is
impossible to give a full picture here of the uses being
made of visual information. The following examples
should be interpreted as being merely a snapshot of the
situation.

2.2.3 Shape retrieval

2.3.3 Crime prevention:
Shape matching of three-dimensional objects is
a more challenging task particularly where only a
single 2-D view of the object in question is available.
While no general solution to this problem is possible,
some useful inroads have been made into the problem of
identifying at least some instances of a given object from
different viewpoints. One approach has been to build up
a set of plausible 3-D models from the available 2-D
image, and match them with other models in the
database. Another is to generate a series of alternative 2D views of each database object, each of which is
matched with the query image. Related research issues in

The police use visual information to identify

people or to record the scenes of crime for evidence;
over the course of time, these photographic records
become a valuable archive. In the UK, it is common
practice to photograph everyone who is arrested and to
take their fingerprints. In a computer-based system, the
photograph will be digitized and linked to the
corresponding textual records. Until convicted, access to
photographic information is restricted and, if the accused
is acquitted, all photographs and fingerprints are deleted.
If convicted, the fingerprints are passed to the National

www.ijsret.org

581

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 5, Issue 12, December 2016

Fingerprint Bureau. Currently, there is a national

initiative investigating a networked Automated
Fingerprint Recognition system involving BT and over
thirty regional police forces. Other uses of images in law
enforcement include face recognition DNA matching,
shoe sole impressions, and surveillance systems. The
Metropolitan Police Force in London is involved with a
paper which is setting up an international database of the
images of stolen objects

modeling are also extensively used in architectural

design, with 3-D modeling and other visualization
techniques increasingly being used for communicating
with clients. A recent survey of IT in architectural firms
emphasized the dominance of CAD (especially 2-D) in
the design process, though it concluded that objectbased, intelligent 3-D modeling systems will become
more important in the future.

2.3.4 Medicine:

3. IMPLEMENTATION

The medical and related health professions use

and store visual information in the form of X-rays,
ultrasound or other scanned images, for diagnosis and
monitoring purposes. There are strict rules on
confidentiality of such information. The images are kept
with the patients health records which are, in the main,
manual files, stored by unique identifier (NI number).
Visual information, provided it is rendered anonymous,
may be used for research and teaching purposes. Much
of the research effort related to images is undertaken in
the medical physics area. Aspects of concern include
effective image processing (e.g. boundary/feature
detection) systems which aid the practitioner in detecting
and diagnosing lesions and tumors and tracking
progress/growth.

MATLAB is a software package for highperformance numerical computation and visualization. It

provides an interactive environment with hundreds of
built-in functions for technical computation, graphics
and animation. It also provides easy extensibility with its
own high level programming language. The name
MATLAB stands for Matrix Laboratory. MATLAB is an
efficient program for vector and matrix data processing.
It contains ready functions for matrix manipulations and
image visualization and allows a program to have
modular structure. Because of these facts MATLAB has
been chosen as prototyping software.

2.3.5 Fashion and graphic design:

Imagery is very important for graphic, fashion
and industrial designers. Visualization seems to be part
of the creative process. Whilst there will be individual
differences in the way designers approach their task,
many use images of previous designs in the form of
pictures, photographs and graphics, as well as objects
and other visual information from the real world, to
provide inspiration and to visualize the end product. 2-D
sketches, and, increasingly, 3-D geometric models are
used to present ideas to clients and other colleagues.
There is also a need to represent the way garments hang
and flow.
2.3.6 Architectural and engineering design:
Photographs are used in architecture to record
finished paper, including interior and exterior shots of
buildings as well particular features of the design.
The images used in most branches of engineering
include drawings, plans, machine parts, and so on.
Computer Aided Design (CAD) is used extensively in
the design process. Hence many engineering firms
maintain extensive design archives. CAD and 2-D

MATLAB provides a suitable environment for

image processing. Although MATLAB is slower than
some languages (such as C), its built in functions and
syntax makes it a more versatile and faster programming
environment for image processing. Once an algorithm is
finalized in MATLAB, the programmer can change it to
C (or another faster language) to make the program run
faster.
3.1 Image Representation in MATLAB
An image is stored as a matrix using standard
Mat lab matrix conventions. There are five basic types of
images supported by Mat lab:
1.
2.
3.
4.
5.

Indexed images
Intensity images
Binary images
RGB images
8-bit images

MATLAB handles images as matrices. This

involves breaking each pixel of an image down into the
elements of a matrix. MATLAB distinguishes between
color and grayscale images and therefore their resulting
image matrices differ slightly.

www.ijsret.org

582

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 5, Issue 12, December 2016

Fig: 3.1.1 Color image representation and RGB

matrix

Fig 3.2.1: RGB coordinates system

A color is a composite of some basic colors.

MATLAB therefore breaks each individual pixel of a
color image (termed true color) down into Red, Green
and Blue values. What it get as a result, for the entire
image, are 3 matrices, one representing each color. The
three matrices are stacked next to each other creating a 3
dimensional m by n by 3 matrixes. For an image which
has a height of 5 pixels and width of 10 pixels the
resulting in MATLAB would be a 5 by 10 by 3 matrixes
for a true color image.
A grayscale image is a mixture of black and
white colors. These colors, or as some may term as
shades, are not composed of Red, Green or Blue
colors. But instead they contain various increments of
colors between white and black. Therefore to represent
this one range, only one color channel is needed. Thus
only need a 2 dimensional matrix, m by n by 1.
MATLAB terms this type of matrix as an Intensity
Matrix, because the values of such a matrix represent
intensities of one color.

Figure 3.2.2 is a view of the RGB color model

looking down from "White" to origin.

Fig 3.2.2: RGB color model

3.3 HSV Color Model
The HSV stands for the Hue, Saturation, and Value
based on the artists (Tint, Shade, and Tone). The
coordinate system in a hexagon in Figure 3.3.1 And
Figure 3.3.2 a view of the HSV color model. Hue
and saturation components are intimately related to
the way human eye perceives color resulting in
image processing algorithms with physiological
basis.

For an image which as height of 5 pixels and

width of 10 pixels the resulting matrix would be a 5 by
10 matrix for grayscale image.

Fig: 3.1.2 Grayscale image representation

3.2 RGB color model

Fig 3.3.1: HSV coordinates system

The RGB color model is composed of the primary

colors Red, Green, and Blue. This system defines the
color model that is used in most color CRT monitors
and color raster graphics. They are considered the
"additive primaries" since the colors are added
together to produce the desired color. In Figure
3.2.1. Notice the diagonal from (0, 0, 0) black to (1,
1, 1) white which represents the grey-scale.

As saturation varies from 0 to 1.0, the corresponding

colors (hues) vary from unsaturated (shades of gray) to
fully saturated (no white component). As value, or
brightness, varies from 0 to 1.0, the corresponding colors
become increasingly brighter.

www.ijsret.org

583

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 5, Issue 12, December 2016

4.2 Used MATLAB tool to HSV

Fig3.3.2: HSV color model

4. RESULT
4.1 GRB conversion using MATLAB
Fig 4.2.1: HSV

5. CONCLUSION

Fig 4.1.1: red conversion

Fig 4.1.2: green conversion

The extent to which CBIR technology is currently in

routine use is clearly still very limited. In particular,
CBIR technology has so far had little impact on the more
general applications of image searching, such as
journalism or home entertainment. Only in very
specialist areas such as crime prevention has CBIR
technology been adopted to any significant extent. This
is no coincidence while the problems of image
retrieval in a general context have not yet been
satisfactorily
solved,
the
well-known artificial
intelligence principle of exploiting natural constraints
has been successfully adopted by system designers
working within restricted domains where shape, color or
texture features play an important part in retrieval.
The process of designing of CBIR system has been
successfully carried out and the expected outcome is
achieved. The main functions that a CBIRS should
perform are:

Constructing feature vectors from the image

based on its content and storing it in the
database.

Similarity comparison and segmentation.

Retrieving the images based on the feature

vectors.
The above mentioned functions are thoroughly
checked using software called MATLAB. Also the
design is very simple and easy to implement.

Fig 4.1.3: blue conversion

www.ijsret.org

584

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 0882
Volume 5, Issue 12, December 2016

FUTURE ENHANCEMENTS
Developments and studies are going on for
further improvements in design and performance of
CONTENT
BASED
IMAGE
RETRIEVAL
SYSTEMS.
In this paper image is retrieved using color
feature has proved and the information about object
location, shape, and texture is discarded. Thus this paper
showed that images retrieved by using the above
mentioned methods may not be semantically related
even though they share similar color distribution in some
results.
In the future enhancements can implement:
Shape and Texture analysis.
Color Image histogram.
Image ranking in Euclidean Distance method.

[7] A. Vellaikal and C. C. J. Kuo, Content Based

Image Retrieval using Multiresolution Histogram
Representation, SPIE - Digital Image Storage and
Archiving Systems, Vol. 2606, pp. 312-323, 1995.
[8] H. J. Zhang, Y. Gong, C. Y. Low and S. W. Smoliar,
Image Retrieval Based on Color Feature: An Evaluation
Study, SPIE - Digital Image Storage and Archiving
Systems, vol. 2606, pp. 212-220, 1995.
[9] Shamik Sural, Gang Qian and Sakti Pramanik,
Segmentation and Histogram Generation Using the HSV
Color Space for Image Retrieval, International
Conference on Image processing, Vol. 2, pp. 589-592,
2002.
[10] Xiaoqian Xu, Dah-Jye Lee, Sameer Antani, and L.
Rodney Long, A Spine X-Ray Image Retrieval System
Using Partial Shape Matching, IEEE
BIOGRAPHIES

REFERENCES
[1] Y. A. Aslandogan and C. T. Yu, "Techniques and
Systems for Image and Video Retrieval," IEEE
Transactions on Knowledge and Data Engineering, Vol.
11, Issue 1, pp. 56-63, Jan/Feb 1999.
[2] 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 Transactions on
Pattern Analysis and Machine Intelligence, Vol. 22,
Issue 12, pp. 1349-1380, December 2000.
[3] M. J. Swain and D. H. Ballard, Color indexing,
International Journal of Computer Vision, vol. 7, Issue 1,
pp. 11-32, 1991.

Prof. Chaitra H.K. received BE degree in

Computer
Science
and
Engineering
form
proudadevaraya Institute of Technology, Hosepete in
2005 and received MTech in Computer Science and
Engineering from RVCE, Bangalore in 2011. Pursueing
Phd in web mining. She is currently working as an
assistant professor in SJBIT College, Bangalore.

[4] Irena Valova, Boris Rachev and Michael

Vassilakopoulos, Optimization of the Algorithm for
Image Retrieval by Color Features, International
Conference on Computer Systems and TechnologiesCompSysTech, pp 1-4, 2006.
[5] Sarfraz and M. Ridha Content-Based Image
Retrieval Using Multiple Shape Descriptors, IEEE/ACS
International Conference On Computer Systems and
Applications, pp. 730-737, 2007.
[6] G. Pass and R. Zabih, Histogram Refinement for
Content-Based Image Retrieval, 3rd IEEE Workshop
on Applications of Computer
Vision, pp. 96-102, 1996.

Brunda Shivaram received the B.E. degree in

Computer Science and engineering from SJB Institute of
technology, Bangalore in 2014 and pursuing MTech
degree in Computer Science and Engineering at SJB
institute of technology, Bangalore.

www.ijsret.org

585