IJCST Vol. 2, Issue 4, Oct. - Dec. 2011
ISSN : 0976-8491(Online) | ISSN : 2229-4333(Print)
Image Retrieval and Similarity Measurement based
on Image Feature
1
R. Venkata Ramana Chary, 2Dr. D. Rajya Lakshmi, 3Dr. K. V. N Sunitha
Padmasri Dr. B. V Raju Institute of Technology, Hyderabad, AP, India
2
GITAM Institute of Technology, Visakhapatnam, AP, India
3
G. Narayanamma Institute of Technology and Science, Hyderabad, AP, India
1
Abstract
User interactive systems have attracted a lot of research interest
in recent years, especially for content-based image retrieval
systems. Contrary to the early systems, which focused on fully
automatic strategies, recent approaches have introduced
human-computer interaction , Assuming that a user is looking
for a set of images with similar feature using the query concept
within a database . Proposed system focus on the retrieval of
images within a huge image collection based on customized
IRM and color histogram technologies. this technique obtained
fast and efficient results comparatively previous methods. the
aim is to build a fast and efficient strategy to retrieve the query
Concept.
Keywords
Color Histogram, IRM, RGB Projection, Annotation , Retrieval,
Query.
I. Introduction
The term content based image retrieval (CBIR) [1] also known
as query by image content (QBIC) [4] and content-based
information retrieval (CBVIR) [13] is the application of computer
vision techniques to the image retrieval problemseems to have
originated in 1992, when it was used by T. Kato to describe
experiments into automatic retrieval of images from a large
collection database, based on the colors, shapes present
and image features [1]. The techniques, tools and algorithms
that are used originate from fields such as statistics, pattern
recognition [4-5], signal processing, and computer vision.
There is a growing interest in CBIR because of the limitations
inherent in metadata-based systems, as well as the large
range of possible uses for efficient image retrieval. Textual
information [7, 31] about images can be easily searched using
existing technology, but requires humans to personally describe
every image in the database. This is impractical for very large
databases, or for images that are generated automatically,
e.g. from surveillance cameras [33]. It is also possible to miss
images that use different synonyms in their descriptions.
Systems based on categorizing images in semantic [2, 9]
classes like “cat” as a subclass of “animal” avoid this problem
but still face the same scaling issues.
Content-Based Image Retrieval (CBIR) According to the usersupplied bottom characteristics, directly find out images
containing specific content from the image library The basic
process: First of all, do appropriate pre-processing of images,
and then extract image characteristics needed from the
image according to the contents of images to keep in the
database. When we retrieve to identify the image, extract the
corresponding features [6-7] from a known image and then
retrieve the image database to identify the images which are
similar with it, also we can give some of the characteristics
based on a queried requirement , then retrieve out the required
images based on the given Eigen values. In the whole retrieval
w w w. i j c s t. c o m
process, feature extraction is crucial; it is closely related to all
aspects of the future, such as color, shape, texture and space,
in recent years.
A. Color
computing distance measures [15-16] based on color similarity
is achieved by computing a color histogram for each image
that identifies the proportion of pixels within an image holding
specific values. Current research is attempting to segment
color proportion by region and by spatial relationship among
several color regions. Examining images based on the colors
they contain is one of the most widely used techniques because
it does not depend on image size or orientation. Color searches
will usually involve comparing color histograms.
B. Texture
Fig: 1
Texture measures look for visual patterns [5] in images and
how they are spatially defined. Textures are represented by
texels which are then placed into a number of sets, depending
on how many textures are detected in the image. These sets
not only define the texture, but also where in the image the
texture is located.
C. Shape
Fig. 2:
shape does not refer to the shape of an image but to the shape
of a particular region [17] that is being sought out. Shapes
will often be determined first applying segmentation or edge
detection to an image. Other methods like use shape filters to
identify given shapes of an image. In some case accurate shape
detection will require human intervention because methods
like segmentation [17, 23] are very difficult to completely
automate.
International Journal of Computer Science & Technology 385
IJCST Vol. 2, Issue 4, Oct. - Dec. 2011
D. Applications of CBIR
• Art collections
• Jab recruitments
• Photograph archives
• Reservation system
• Retail catalogs
• Medical diagnosis
• Crime prevention
• The military
• Intellectual property
• Architectural and engineering design
• Geographical information and remote sensing systems
II. Problem Description
An image retrieval system is a computer system for browsing,
searching and retrieving images from a large database of
digital images [34]. Most traditional and common methods
of image retrieval utilize some method of adding metadata
such as captioning, keywords, or descriptions to the images
so that retrieval can be performed over the annotation words.
Manual image annotation is time-consuming, laborious and
expensive. To address this, there has been a large amount of
research done on automatic image annotation. Additionally, the
increase in social web applications and the semantic web[9]
have inspired the development of several web-based image
annotation tools.Content-based means that the search will
analyze the actual contents of the image. The term ‘content’
in this context might refer to 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, which maybe
laborious or expensive to produce.
ISSN : 0976-8491 (Online) | ISSN : 2229-4333(Print)
the images in database.
A. System Architecture
Fig. 4: Image Retrieval System Architecture
In fig. 4, it is showing about image similarity measurements
and flow of the system.
IV. Related work
Image retrieval implemented in following steps
A. RGB Projections
The RGB color model is an additive color model in which red,
green, and blue light are added together in various ways to
reproduce a broad array of colors. The name of the model
comes from the initials of the three additive primary colors,
red, green, and blue. Main purpose of the RGB color model
is for the sensing, representation, and display of images in
electronic systems. An image histogram is a type of histogram
that acts as a graphical representation of the tonal distribution
in a digital image. It plots the number of pixels for each tonal
value. By looking at the histogram [3] for a specific image a
viewer will be able to judge the entire tonal distribution at a
glance. RGB Projections is used to find the size of the image
vertically and horizontally.
B. Image Service
Whenever minimizing the error of classification is interesting
for CBIR, this criterion does not completely reflect the user
satisfaction. Other image service criteria closer to this, such
as precision, should provide more efficient selections.
Fig. 3:
III. Proposed System
• Proposed system uses modified IRM (Integrated Region
Matching) [6, 25] and color feature which overcomes the
problem description.
• Proposed system implemented features like color
histogram, symmetry features [29] etc.
• Proposed work provides an interface where user can give
query images as input, which uses the
• visual contents of an image such as color, shape, texture
and spatial layout to represent the image compared with
386
International Journal of Computer Science & Technology
C. Comparable Image
Reselection technique used to speed up the selection process,
which leads to a learning process. All these components are
integrated in retrieval system, the user gives new labels for
images and they are compared to the current classification.
If the user mostly gives relevant labels, the system should
propose new images for labeling around a higher rank to get
more irrelevant labels.
D. Similarity Measure
The results in terms of mean average precision according to
the training set huge image databases. classification-based
methods [10] gives the best results, showing the power of
statistical methods over geometrical approaches.
w w w. i j c s t. c o m
IJCST Vol. 2, Issue 4, Oct. - Dec. 2011
ISSN : 0976-8491(Online) | ISSN : 2229-4333(Print)
E. Integrated Region Matching
This method computes histograms of every image in the
database and takes one input image to search from the
database. It gives feasible solution consisting finite number
of images (like ‘IM’) having minimum IRM distance [25].Then
by taking minimum IRM distance image (Say‘N’, where N IM)
as input and remaining images in the feasible solution set as
a database of images applies region matching technique using
color. Hence, it computes single image having minimum IRM
distance with ‘N’. after finding the minimum distances related
image is deciding as a similar to the query image.
F. Performance Measures
1. Precision
Precision [14] is the fraction of the images retrieved that are
relevant to the user’s information need.
Recall is the fraction of the images that are relevant to the
query that are successfully retrieved.
2. Mean Average Precision
Mean average precision for a set of queries is the mean of the
average precision scores for each query.
where Q is the number of queries.
V. Result Analysis
Finally, the image will take the relevant image what the user
search. One can see that we have selected concepts of
different levels of complexities. The performances go from few
percentages of Mean average precision to 89%. The concepts
that are the most difficult to retrieve are very small and/or have
a much diversified visual content. The method which aims at
minimizing the error of generalization is the less efficient active
learning method. The most efficient method is the precisionoriented method.
A. Graph
To determine relationships between the two Images. The
precision and recall values are measured by simulating retrieval
scenario. For each simulation, an image category is randomly
chosen. Next, 300 images are selected using active learning
and labeled according to the chosen category. These labeled
images are used to train a classifier, which returns a ranking
of the database. The average precision is then computed using
the ranking. These simulations are repeated 1000 times, and
all values are averaged to get the Mean average precision.
Next, we repeat ten times these simulations to get the mean
and the standard deviation of the map .
B. Experimental Results
The image will take the relevant image what the user search.
one can see that we have selected concepts of different levels
of complexities. The performances go from few percentages
of Mean average precision to 89%. The concepts that are the
most difficult to retrieve are very small and/or have a very
diversified visual content.
w w w. i j c s t. c o m
Fig. 5: Retrieved Images With Graphs
The above fig. 5, is a screenshot which appears when we click
on search button. It is not only shows the selected image with
the retrieved image from the specified folder but also shows
the percentage of matching as well as the histogram graph is
display in the screen.
Fig. 6: Similarity Comparison
The above fig. 6, is a screenshot which appears when we click
on other images after the system retrieves the images from the
specified folder. It is not only shows the selected image with
the retrieved image from the specified folder but also shows
the percentage of matching as well as the graph depicting
the match.
VI. Future Enhancement
As found in the literature, most Internet-based prototype ContentBased Image Retrieval (CBIR) systems focus on stock photo
collections and do not address challenges of large specialized
image collections and topics such as semantic information
International Journal of Computer Science & Technology 387
IJCST Vol. 2, Issue 4, Oct. - Dec. 2011
retrieval by image content.
As a next step design and developed an Internet-based
semantic tool and a CBIR retrieval tool that can remotely
connect to database. The retrieval tool supports hybrid text
and image queries and also provides partial shape annotation
for pathology -specific querying [19].
VII. Conclusion
This is fast and efficient method which is used to retrieve the
images from the huge data base .in this work we compared
all images and retrieved similarities percentage ranging from
ranging from maximum to minimum like 100% to 0%.Even
though This research area is growing very rapidly Current
systems are still in prototype stage and lack of reliability Current
techniques are based on low level features and there is a huge
semantic gap existing. Coming days more research work is
needed with a reliable and semantically competent system.
References
[1] R.Datta, D.Joshi, J.Li, J.Z.Wang, “Image Retrieval, ideas ,
Influences, and Trends of the New Age”, ACM Transactions
on Computing Surveys, Vol. 40, No. 2, 2008.
[2] Najlae Idrissi,“Bridging the Semantic Gap for Texture based
Image Retrieval and Navigation, Journal Of Multimedia”,
Vol.4, No.5, 2009.
[3] M. L. Kherfi, D. Ziou, A. Benard, “Image retrieval from the
World Wide Web: Issues, techniques and systems”, ACM
Computing Surveys, 36(1), pp. 35-67, 2004
[4] 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, 22(12), pp. 1349-1380, 2000.
[5] Smeulders, A.W.M., Worring, M., Santini, S., Gupta, A., Jain,
R., “Content based image retrieval at the end of the early
years”, IEEE Trans. Pattern Anal. Intell. 22, pp. 1349–1380
2000.
[6] Wei Jiang, Kap luk chan, Mingjing Li., "Mapping low level
features to high level semantic concept in region based
image retrieval”, IEEE CVPR05, 2005 .
[7] Chuan yu chang, hung jen wang, chi fang li,“Semantic
analysisof real world images using support vectormachine”,
Expert systems with application: An interntation journal
2009.ACM
[8] Y. Y. Lin, T.L. Liu, H.T. Chen, “Semantic manifold learning for
image retrieval”, In Proceedings of the ACM International
Conference on Multimedia, 2005.
[9] Janghyun Yoon, Nikil Jayant, “Relevance Feedback for
semantics based Image retrieval”.
[10]P.L. Stanchev, D. Green Jr., B. Dimitrov, “High level color
similarity retrieval”, Int. J. Inf. Theories Appl. 10 (3), 2003
pp. 363–369.
[11]V. Mezaris, I. Kompatsiaris, M.G. Strintzis, “An ontology
approach to object based image retrieval”, Proceedings
of the ICIP, vol. II, 2003, pp. 511–514 .
[12]Huan Wang, Song Liu, liang tien chia, “Image retrieval with
a multimodality ontology”, Multimedia System, 2008.
[13]Aigrain, P et al, “Content-based representation and retrieval
of visual media, a state-of-the-art review”, Multimedia
Tools and Applications 3(3), pp. 179-202, 1996.
388
International Journal of Computer Science & Technology
ISSN : 0976-8491 (Online) | ISSN : 2229-4333(Print)
[14]Stricker, M, Orengo, M, “Similarity of color images”, in
Storage and Retrieval for Image and Video Databases
III (Niblack, W R and Jain, R C, eds), Proc SPIE 2420, pp.
381-392, 1995.
[15] Androutsas, D et al,“Image retrieval using directional detail
histograms”, in Storage and Retrieval for Image and Video
Databases VI, Proc SPIE 3312, pp. 129-137, 1998.
[16]D. Mahidhar, "MVSN, Maheswar A NOVEL APPROACH FOR
RETRIEVING AN IMAGE USING CBIR", International Journal
of computer science and information technologies vol.
1(5), 2010, pp. 329-331
[17]Del Bimbo, A et al, “Image retrieval by elastic matching of
shapes and image patterns”, in Proceedings of Multimedia
‘96, pp. 215-218, 1996.
[18]Bird, C et al, “User interfaces for content-based image
retrieval”, in Proceedings of IEE Colloquium on Intelligent
Image Databases, IEE, London, 8/1-8/4, 1996.
[19]Carson C S et al, “Region-based image querying”, in
Proceedings of IEEE Workshop on Content-Based Access
of Image and Video Libraries, San Juan, Puerto Rico, pp.
42-49, 1997.
[20]Chan, Y, Kung, S Y, “A hierarchical algorithm for image
retrieval by sketch” in First IEEE Workshop on Multimedia
Signal Processing, pp. 564-569, 1997.
[21]Chang N S, Fu K S, “Picture query languages for pictorial
data-base systems”, IEEE Computer 14(11) pp. 23-33,
1981.
[22]Ritendra Datta, Dhiraj Joshi, Jia Li, James Wang, “Image
Retrieval: Ideas, Influences, and Trends of the New
Age”, Proceedings of the 7th ACM SIGMM international
workshop on Multimedia informationretrieval, November
10-11, 2005, Hilton, Singapore.
[23]C. Carson, S. Belongie, H. Greenspan, Malik,“Blobworld:
Image Segmentation Using Expectation-Maximization and
Its Application to Image Querying”, in IEEE Trans. On PAMI,
vol. 24, No.8, pp. 1026-1038, 2002.
[24]Y. Chen, J. Z. Wang, “A Region-Based Fuzzy Feature
Matching Approach to Content-Based Image Retrieval”,
in IEEE Trans. on PAMI, vol. 24, No.9, pp. 1252-1267,
2002.
[25]A. Natsev, R. Rastogi, K. Shim, “WALRUS: A Similarity
Retrieval Algorithm for Image Databases”, in Proc. ACM
SIGMOD Int. Conf. Management of Data, pp. 395–406,
1999.
[26]J. Li, J.Z. Wang, and G. Wiederhold, “IRM: Integrated Region
Matching for Image Retrieval,” in Proc. of the 8th ACM Int.
Conf. on Multimedia, pp. 147-156, 2000.
[27]V. Mezaris, I. Kompatsiaris, M. G. Strintzis, “Region-based
Image Retrieval Using an Object Ontology and Relevance
Feedback”, in Eurasip Journal on Applied Signal Processing,
vol. 2004, No. 6, pp. 886-901, 2004.
[28]Gudivada V N, aghavan V V, “Content-based image retrieval
systems”, IEEE Computer 28 (9), pp. 18-22, 1995a.
[29]Chang, S F et al, “Semantic visual templates: linking visual
features to semantics”, in IEEE International Conference
on Image Processing (ICIP’98), Chicago, Illinois, pp. 531535, 1998
[30]Chang, S K et al, “An intelligent image database system”,
IEEE Transactions on Pattern Analysis and Machine
Intelligence, 14(5), pp. 681-688, 1988.
w w w. i j c s t. c o m
ISSN : 0976-8491(Online) | ISSN : 2229-4333(Print)
IJCST Vol. 2, Issue 4, Oct. - Dec. 2011
[31]Chans, Y et al, “A feature-based approach for image
retrieval by sketch”, in Multimedia Storage and Archiving
Systems II (Kuo, C C J et al, eds), Proc SPIE 3229, pp.
220-231, 1997.
[32]“Image Retrieval by Image Attention based on Region
Layout Analysis and Relevance Feedback”, in Proc. ICACC
2007 International Conference, Madurai, India, pp. 417420, 9-10 Febuary, 2007.
[33][Online] Available: http://www.en.wikipedia.org/wiki/
Content-based_image_retrieval
[34]R. Venkata Ramana Chary, Dr. K. V. N Sunitha, Dr. D. Rajya
Lakshmi, “Quality Measures on Multispectral Images” ,
International Journal of Image Processing and Applications,
2(1), 2011, pp. 101-105 of the journal in the, 2011.
[35][Online] Available: http://www.computer.org/portal/web/
csdl/ doi/10.1109/2.410146.
R.Vekata Ramana Chary working as a
Associate professor In BVRIT College
narsapur medak dist A.P. Presently he
was pursuing Ph.D, from GITAM university,
AP, india. His research interest in image
processing ,performance measurements,
algorithms analysis and programming
Techniques. He was having 15 years of
teaching and research experience .
Dr. D. Rajya Lakshmi is working as Professor
and HOD in the department of IT at GITAM
university Visakhapatnam, AP, India. Her
research areas includes Image processing,
Data mining. She has about 17 years of
teaching and research experience. Her
Ph.D, awarded from JNTUH Hyderabad AP
in the area of Image Processing.
Dr. K.V.N. Sunitha is working as a
Professor and HOD in G. Narayanamma
Institute of Technology and Science (for
Women) In Hyderabad, AP, Her Ph.D.
awarded from JNTUH Hyderabad AP.
she is having 18 years of teaching and
research experience in the computer field
. Her research interest is Compilers, NLP,
Speech Recognition, Computer Networks,
Image Processing.
w w w. i j c s t. c o m
International Journal of Computer Science & Technology 389