+ All Categories
Home > Documents > NAVIGATION-PATTERN-BASED RELEVANCE FEEDBACK ......Satyanarayana Mummana 1, Swathi Koundinya 2 1 Asst...

NAVIGATION-PATTERN-BASED RELEVANCE FEEDBACK ......Satyanarayana Mummana 1, Swathi Koundinya 2 1 Asst...

Date post: 20-Jul-2021
Category:
Upload: others
View: 1 times
Download: 0 times
Share this document with a friend
5
SATYANARAYANA MUMMANA* et al. ISSN: 22503676 [IJESAT] INTERNATIONAL JOURNAL OF ENGINEERING SCIENCE & ADVANCED TECHNOLOGY Volume-2, Issue-5, 1241 1246 IJESAT | Sep-Oct 2012 Available online @ http://www.ijesat.org 1241 NAVIGATION-PATTERN-BASED RELEVANCE FEEDBACK FOR CONTENT BASED IMAGE RETRIEVAL Satyanarayana Mummana 1 , Swathi Koundinya 2 1 Asst Professor, Dept of Computer Science and Engineering, Avanthi Institute of Engineering & Technology, Visakhapatnam, Andhra Pradesh. 2 Final M.Tech Student, Dept of Computer Science and Engineering, Avanthi Institute of Engineering & Technology, Visakhapatnam, Andhra Pradesh. Abstract The current day scenario demands drastic enhancement in information search engines. The quest for information or representation of information is more compact and precise to point when represented as image than a near text. As a result image search has gained an intense popularity. Searching or retrieving image based on its content is called content based image retrieval. There are various synch methods so far implemented and all of these methods are also support by feedback system from the user to fine tune the search results. But still because of intelligence modules implemented and time factors those methods are impractical away for real applications. Thus this work proposes a new user navigation pattern based feedback system to support content based image retrieval. Index Terms: Navigation, Image Retrieval, -----------------------------------------------------------------------***----------------------------------------------------------------------- 1. INTRODUCTION The growing multimedia quest has raised the interest of mining multimedia content recently. The image retrieval from large multimedia repository is a difficult but interesting task. The searches use the image annotation captions for text based search quest and thus content base image retrieval gains access to the requisition. These suffer from two major drawback large caption annotation required and captions are expected to be as relevant as possible to the image description. As a result, a number of powerful image retrieval algorithms have been proposed to deal with such problems over the past few years. Content-Based mage Retrieval (CBIR) is the mainstay of current image retrieval systems. In general, the purpose of CBIR is to present an image conceptually, with a set of low-level visual features such as color, texture, and shape. That is, existing methods refine the query again and again by analyzing the specific relevant images picked up by the users. Especially for the compound and complex images, the users might go through a long series of feedbacks to obtain the desired images using current RF approaches. Fig. 1.Motivating example for the problem of exploration convergence The involved problem, so-called visual diversity, is shown in Fig. 2. In this case, if the compound concept to aim at consists of “car,” “sunset,” and “sunset and car,” it is not easy for traditional CBIR methods to capture the user’s intention. Especially for query point movement methods, this problem will result in that the features would converge toward the specific point in the feature space during the query session. Hence, it is still hard to cover the concepts of “car,” “sunset,” and “sunset and car” even by performing the weighted K- Nearest Neighbors (KNNs) search.
Transcript
Page 1: NAVIGATION-PATTERN-BASED RELEVANCE FEEDBACK ......Satyanarayana Mummana 1, Swathi Koundinya 2 1 Asst Professor, Dept of Computer Science and Engineering,Avanthi Institute of Engineering

SATYANARAYANA MUMMANA* et al. ISSN: 2250–3676

[IJESAT] INTERNATIONAL JOURNAL OF ENGINEERING SCIENCE & ADVANCED TECHNOLOGY Volume-2, Issue-5, 1241 – 1246

IJESAT | Sep-Oct 2012

Available online @ http://www.ijesat.org 1241

NAVIGATION-PATTERN-BASED RELEVANCE FEEDBACK FOR CONTENT

BASED IMAGE RETRIEVAL

Satyanarayana Mummana 1

, Swathi Koundinya 2

1

Asst Professor, Dept of Computer Science and Engineering, Avanthi Institute of Engineering & Technology,

Visakhapatnam, Andhra Pradesh.

2 Final M.Tech Student,

Dept of Computer Science and Engineering, Avanthi Institute of Engineering & Technology,

Visakhapatnam, Andhra Pradesh.

Abstract The current day scenario demands drastic enhancement in information search engines. The quest for information or representation of

information is more compact and precise to point when represented as image than a near text. As a result image search has gained an

intense popularity. Searching or retrieving image based on its content is called content based image retrieval. There are various

synch methods so far implemented and all of these methods are also support by feedback system from the user to fine tune the search

results. But still because of intelligence modules implemented and time factors those methods are impractical away for real

applications. Thus this work proposes a new user navigation pattern based feedback system to support content based image retrieval.

Index Terms: Navigation, Image Retrieval,

-----------------------------------------------------------------------***-----------------------------------------------------------------------

1. INTRODUCTION

The growing multimedia quest has raised the interest of

mining multimedia content recently. The image retrieval from

large multimedia repository is a difficult but interesting task.

The searches use the image annotation captions for text based

search quest and thus content base image retrieval gains access

to the requisition. These suffer from two major drawback large

caption annotation required and captions are expected to be as

relevant as possible to the image description.

As a result, a number of powerful image retrieval algorithms

have been proposed to deal with such problems over the past

few years. Content-Based mage Retrieval (CBIR) is the

mainstay of current image retrieval systems. In general, the

purpose of CBIR is to present an image conceptually, with a

set of low-level visual features such as color, texture, and

shape. That is, existing methods refine the query again and

again by analyzing the specific relevant images picked up by

the users. Especially for the compound and complex images,

the users might go through a long series of feedbacks to obtain

the desired images using current RF approaches.

Fig. 1.Motivating example for the problem of exploration

convergence

The involved problem, so-called visual diversity, is shown in

Fig. 2. In this case, if the compound concept to aim at consists

of “car,” “sunset,” and “sunset and car,” it is not easy for

traditional CBIR methods to capture the user’s intention.

Especially for query point movement methods, this problem

will result in that the features would converge toward the

specific point in the feature space during the query session.

Hence, it is still hard to cover the concepts of “car,” “sunset,”

and “sunset and car” even by performing the weighted K-

Nearest Neighbors (KNNs) search.

Page 2: NAVIGATION-PATTERN-BASED RELEVANCE FEEDBACK ......Satyanarayana Mummana 1, Swathi Koundinya 2 1 Asst Professor, Dept of Computer Science and Engineering,Avanthi Institute of Engineering

SATYANARAYANA MUMMANA* et al. ISSN: 2250–3676

[IJESAT] INTERNATIONAL JOURNAL OF ENGINEERING SCIENCE & ADVANCED TECHNOLOGY Volume-2, Issue-5, 1241 – 1246

IJESAT | Sep-Oct 2012

Available online @ http://www.ijesat.org 1242

The rest of this work is so organized that the Section 2 briefly

shares the related contributions so far occurred in this field

and the Section 3 exposes our proposed method and that

followed by the conclusion.

Fig. 2. Example of visual diversity

2. RELATED CONTRIBUTIONS

Some previous work keeps an eye on investigating what visual

features are important for those images (positive examples)

picked up by the users at each feedback (also called iteration

in this paper).

Fig. 3. Relevance feedback with generalized QR technique

In this work, the feature weights are dynamically updated to

connect low-level visual features and high-level human

concepts. NNEW, developed by You et al. [24], learns the

user’s query from positive and negative examples by

weighting the important features. For this kind of approach, no

matter how the weighted or generalized distance function is

adapted, the diverse visual features extremely limit the effort

of image retrieval. Fig. 4 illustrates this limitation that

although the search area is continuously updated by

reweighting the features, some targets could be lost.

Then the user can obtain a set of most relevant web images

according to the metadata or the browsing log. However, if the

result does not satisfy the user, the query refinement can be

easily incorporated into the query procedure

In fact, usage mining has been made on how to generate users’

browsing patterns to facilitate the web pages retrieval.

Similarly, for web image retrieval, the user has to submit a

query term to the search engine, so-called textual-based image

search.

This is why CBIR using RF has been the focus of the

researchers in the field of image retrieval. As far as the usage

log of CBIR is concerned, the challenge mainly lies on: how

to generate and utilize the discovered patterns. In this paper,

we develop a navigation-pattern based data structure

permeated by the query point movement aspect, which has

never been proposed by past studies. Through the special data

structure, the user’s intention can be caught more quickly and

precisely.

3. THE NAVIGATION PATTERN BASED

RELEVANCE FEEDBACK

This section is designed to state focus on the proposed

algorithm. This section evolves the problem statement and

formulates the algorithm application.

Fig.4. Example of navigation pattern trees.

Indeed, these unsolved problems result in large limitation in

RF. Perhaps, the aged hybrid systems fusing the results

generated by multiple query refinement systems can look for

the better results than individual systems. After eliminating

the redundant patterns, the trimmed navigation pattern tree

reduces the search cost significantly. Based on the navigation

pattern tree, the desired images can be captured more

promptly without repeating the scan of the whole image

database at each feedback, especially for the large-scale image

data. Nevertheless, the expensive computation cost makes it

impractical in real applications.

Page 3: NAVIGATION-PATTERN-BASED RELEVANCE FEEDBACK ......Satyanarayana Mummana 1, Swathi Koundinya 2 1 Asst Professor, Dept of Computer Science and Engineering,Avanthi Institute of Engineering

SATYANARAYANA MUMMANA* et al. ISSN: 2250–3676

[IJESAT] INTERNATIONAL JOURNAL OF ENGINEERING SCIENCE & ADVANCED TECHNOLOGY Volume-2, Issue-5, 1241 – 1246

IJESAT | Sep-Oct 2012

Available online @ http://www.ijesat.org 1243

The basic idea of this operation is to find the images not only

with the specific similarity function. By recursively modifying

the query point, the search direction can move toward the

targets gradually. Assume that a set of images is found by the

query point qpold at the preceding feedback.

By performing a weighted KNN search, QEX-like procedure

first determines the nearest query seed to each of G, called

positive query seed, and the nearest query seed to each of N,

called negative query seed.

Additionally, the slight loss of the information embedded in

the negative examples is also deliberated in this paper. In

theory, if the negative query seeds are all dropped at each

feedback, the desired results could be captured more precisely.

However, there exist some query seeds belonging to both of

the positive query seed set and the negative query seed set at

each feedback. Dropping the negative query seeds would lead

to the loss of positive query seeds. Lines 5-8 of Fig. 10 show

how to find the positive and negative query seed sets. As a

result, a set of positive query seeds is selected to be the start of

potential search paths.

Page 4: NAVIGATION-PATTERN-BASED RELEVANCE FEEDBACK ......Satyanarayana Mummana 1, Swathi Koundinya 2 1 Asst Professor, Dept of Computer Science and Engineering,Avanthi Institute of Engineering

SATYANARAYANA MUMMANA* et al. ISSN: 2250–3676

[IJESAT] INTERNATIONAL JOURNAL OF ENGINEERING SCIENCE & ADVANCED TECHNOLOGY Volume-2, Issue-5, 1241 – 1246

IJESAT | Sep-Oct 2012

Available online @ http://www.ijesat.org 1244

That is, these dropped negative seeds may be the start of good

search paths. To take account of both positive and negative

information simultaneously, every seed has its own token

rth.chk. If the seed owns the maximum number of negative

examples or owns no positive example, it will be tokenized as

a bad manner, i.e., rth:chk ¼ 0, as shown in lines 4 and 15 of

above algorithm. Otherwise, rth.chk is 1 for any good manner.

4. RESULTS AND CONCLUSION

Before discussing the experimental results the below is the

sample representation of user navigation patterns.

The dataset consumed for the experimentation is as below

Various simulation regression efforts of this proposed system

as been tested with various bench marks functions and

databases and are graphitized below.

Fig. 6. The average precisions of different s for data set 3.

In most former approaches, an important limitation for image

retrieval is that the explosive growth of images leads to poor

and unstable performance. This further proves that our

approach is very robust in the success of RF for the large-scale

image data

Fig. 7. The precisions of different approaches for data set 7.

Finally to precise, the main feature of NPRF is to efficiently

optimize the retrieval quality of interactive CBIR. On one

hand, the navigation patterns derived from the users’ long

term browsing behaviors are used as a good support for. First,

in view of very large data sets, we will scale our proposed

method by utilizing parallel and distributed computing

techniques

Page 5: NAVIGATION-PATTERN-BASED RELEVANCE FEEDBACK ......Satyanarayana Mummana 1, Swathi Koundinya 2 1 Asst Professor, Dept of Computer Science and Engineering,Avanthi Institute of Engineering

SATYANARAYANA MUMMANA* et al. ISSN: 2250–3676

[IJESAT] INTERNATIONAL JOURNAL OF ENGINEERING SCIENCE & ADVANCED TECHNOLOGY Volume-2, Issue-5, 1241 – 1246

IJESAT | Sep-Oct 2012

Available online @ http://www.ijesat.org 1245

The experimental results reveal that the proposed approach

NPRF is very effective in terms of precision and coverage.

Within a very short term of relevance feedback, the navigation

patterns can assist the users in obtaining the global optimal

results. Moreover, the new search algorithm NPRFSearch can

bring out more accurate results than other well-known

approaches.

5. REFERENCES

[1] M.D. Flickner, H. Sawhney, W. Niblack, J. Ashley, Q.

Huang, B.Dom, M. Gorkani, J. Hafner, D. Lee, D.

Steele, and P. Yanker, “Query by Image and Video

Content: The QBIC System,” Computer, vol. 28, no. 9,

pp. 23-32, Sept. 1995.

[2] R. Fagin, “Combining Fuzzy Information from Multiple

Systems,” Proc. Symp. Principles of Database Systems

(PODS), pp. 216-226, June 1996.

[3] R. Fagin, “Fuzzy Queries in Multimedia Database

Systems,” Proc. Symp. Principles of Database Systems

(PODS), pp. 1-10, June 1998.

[4] J. French and X-Y. Jin, “An Empirical Investigation of the

Scalability of a Multiple Viewpoint CBIR System,”

Proc. Int’l Conf. Image and Video Retrieval (CIVR), pp.

252-260, July 2004.

[5] D. Harman, “Relevance Feedback Revisited,” Proc. 15th

Ann. Int’l ACM SIGIR Conf. Research and

Development in Information Retrieval, pp. 1-10, 1992.

[6] Y. Ishikawa, R. Subramanya, and C. Faloutsos,

“MindReader: Querying Databases through Multiple

Examples,” Proc. 24th Int’l Conf. Very Large Data

Bases (VLDB), pp. 218-227, 1998.

[7] X. Jin and J.C. French, “Improving Image Retrieval

Effectiveness via Multiple Queries,” Multimedia Tools

and Applications, vol. 26, pp. 221-245, June 2005.

[8] D.H. Kim and C.W. Chung, “Qcluster: Relevance

Feedback Using Adaptive Clustering for Content-Based

Image Retrieval,” Proc. ACM SIGMOD, pp. 599-610,

2003.

[9] K. Porkaew, K. Chakrabarti, and S. Mehrotra, “Query

Refinement for Multimedia Similarity Retrieval in

MARS,” Proc. ACM Int’l Multimedia Conf.

(ACMMM), pp. 235-238, 1999.

[10] J. Liu, Z. Li, M. Li, H. Lu, and S. Ma, “Human Behaviour

Consistent Relevance Feedback Model for Image

Retrieval,” Proc. 15th Int’l Conf. Multimedia, pp. 269-

272, Sept. 2007.

[11] A. Pentalnd, R.W. Picard, and S. Sclaroff, “Photobook:

Content- Based Manipulation of Image Databases,” Int’l

J. Computer Vision (IJCV), vol. 18, no. 3, pp. 233-254,

June 1996.

[12] T. Qin, X.D. Zhang, T.Y. Liu, D.S. Wang, W.Y. Ma, and

H.J. Zhang, “An Active Feedback Framework for Image

Retrieval,” Pattern Recognition Letters, vol. 29, pp. 637-

646, Apr. 2008.

[13] J.J. Rocchio, “Relevance Feedback in Information

Retrieval,” The SMART Retrieval System—

Experiments in Automatic Document Processing, pp.

313-323, Prentice Hall, 1971.

[14] Y. Rui, T. Huang, and S. Mehrotra, “Content-Based

Image Retrieval with Relevance Feedback in MARS,”

Proc. IEEE Int’l Conf. Image Processing, pp. 815-818,

Oct. 1997.

[15] Y. Rui, T. Huang, M. Ortega, and S. Mehrotra,

“Relevance Feedback: A Power Tool for Interactive

Content-Based Image Retrieval,” IEEE Trans. Circuits

and Systems for Video Technology, vol. 8, no. 5, pp.

644-655, Sept. 1998.

BIOGRAPHIES

Satyanarayana Mummana is working as

an Asst. Professor in Avanthi Institute of

Engineering & Technology,

Visakhapatnam, Andhra Pradesh. He has

received his Masters degree (MCA) from

Gandhi Institute of Technology and

Management (GITAM), Visakhapatnam

and M.Tech (CSE) from Avanthi Institute

of Engineering & Technology, Visakhapatnam. Andhra

Pradesh. His research areas include Image Processing,

Computer Networks, Data Mining, Distributed Systems,

Cloud Computing.

Swathi Koundinya Completed her BTech

and pursuing MTech in from Avanthi

Institute of Engineering & Technology,

Visakhapatnam. Andhra Pradesh Interesting

areas are data mining and .net technologies

and MySQL database


Recommended