Abstract




 
   

IJE TRANSACTIONS A: Basics Vol. 27, No. 1 (January 2014) 7-14   

downloaded Downloaded: 235   viewed Viewed: 1742

  DOCUMENT IMAGE RETRIEVAL BASED ON KEYWORD SPOTTING USING RELEVANCE FEEDBACK
 
M. Keyvanpour, R. Tavoli and S. Mozaffari
 
( Received: March 15, 2013 – Accepted: June 20, 2013 )
 
 

Abstract    Keyword Spotting is a well-known method in document image retrieval. In this method, Search in document images is based on query word image. In this Paper, an approach for document image retrieval based on keyword spotting has been proposed. In proposed method, a framework using relevance feedback is presented. Relevance feedback, an interactive and efficient method is used in this paper to improve performance of document image retrieval System (DIRS). In the proposed method we compare several strategies of positive and negative feedback which include “Only Positive Feedback”, “Only Negative Feedback” and “Positive and Negative Feedback”. Experiments show that using relevance Feedback in DIR achieves better performance than common DIR.

 

Keywords    Relevance Feedback, Document Image, Information Retrieval, Keyword Spotting.

 

چکیده    کشف کلمه يکي از روش­های معروف در بازيابي تصاوير اسناد است. در اين روش، جستجو در مجموعه­ای از تصاوير اسناد بر اساس پرس و جوی تصوير کلمه صورت می­گيرد. در اين مقاله يک روش برای بازيابي تصاوير اسناد مبتني بر کلمه­ی کليدی پيشنهاد شده است. در روش پيشنهادی، يک معماری با استفاده از بازخورد مرتبط ارائه می­شود. بازخورد مرتبط, يک روش تعاملي و موثر است که کارايي سيستم بازيابي تصاوير اسناد را افزايش می­دهد. در روش پيشنهادی ما چندين استراتژی از بازخوردهای مثبت و منفي شامل \"تنها بازخورد مثبت\", \"تنها بازخورد منفي\" و \"بازخورد مثبت ومنفي\" را با هم مقايسه می­نماييم. نتايج نشان می­دهد که با استفاده از بازخورد مرتبط در بازيابي تصاوير اسناد کارايي بهتري نسبت به بازيابي تصاوير اسناد معمولي بدست می­آيد.

References   

 

1.     Doermann, D., "The indexing and retrieval of document images: A survey", Computer Vision and Image Understanding,  Vol. 70, No. 3, (1998), 287-298.

2.     Kokare, M. B. and Shirdhonkar, M., "Document image retrieval: An overview", International Journal of Computer Applications,  Vol. 1, No. 7, (2010), 114-119.

3.     Keyvanpour, M. and Tavoli, R., "Document image retrieval: Algorithms, analysis and promising directions", International Journal of Software Engineering and Its Applications,  Vol. 7, No. 1, (2013), 93-106.

4.     Zagoris, K., Ergina, K. and Papamarkos, N., "A document image retrieval system", Engineering Applications of Artificial Intelligence,  Vol. 23, No. 6, (2010), 872-879.

5.     Bai, S., Li, L. and Tan, C. L., "Keyword spotting in document images through word shape coding", in Document Analysis and Recognition, 2009. ICDAR'09. 10th International Conference on, IEEE. (2009), 331-335.

6.     Lu, Y. and Tan, C. L., "Information retrieval in document image databases", Knowledge and Data Engineering, IEEE Transactions on,  Vol. 16, No. 11, (2004), 1398-1410.

7.     Meshesha, M. and Jawahar, C., "Matching word images for content-based retrieval from printed document images", International Journal of Document Analysis and Recognition (IJDAR),  Vol. 11, No. 1, (2008), 29-38.

8.     Leydier, Y., LeBourgeois, F. and Emptoz, H., "Textual indexation of ancient documents", in Proceedings of the 2005 ACM symposium on Document engineering, ACM. (2005), 111-117.

9.     Lu, S., Li, L. and Tan, C. L., "Document image retrieval through word shape coding", Pattern Analysis and Machine Intelligence, IEEE Transactions on,  Vol. 30, No. 11, (2008), 1913-1918.

10.   Zagoris, K., Papamarkos, N. and Chamzas, C., "Web document image retrieval system based on word spotting", in Image Processing, 2006 IEEE International Conference on, IEEE. (2006), 477-480.

11.   Keyvanpour, M. and Tavoli, R., "Feature weighting for improving document image retrieval system performance", IJCSI International Journal of Computer Science Issues,  Vol. 9, No. 3, (2012), 125-130..

12.   MacArthur, S. D., Brodley, C. E., Kak, A. C. and Broderick, L. S., "Interactive content-based image retrieval using relevance feedback", Computer Vision and Image Understanding,  Vol. 88, No. 2, (2002), 55-75.

13.   Zhou, X. S. and Huang, T. S., "Relevance feedback in image retrieval: A comprehensive review", Multimedia Systems,  Vol. 8, No. 6, (2003), 536-544.

14.   Rota Bulò, S., Rabbi, M. and Pelillo, M., "Content-based image retrieval with relevance feedback using random walks", Pattern Recognition,  Vol. 44, No. 9, (2011), 2109-2122.

15.   Su, Z., Zhang, H., Li, S. and Ma, S., "Relevance feedback in content-based image retrieval: Bayesian framework, feature subspaces, and progressive learning", Image Processing, IEEE Transactions on,  Vol. 12, No. 8, (2003), 924-937.

16.   Manning, C. D., Raghavan, P. and Schütze, H., "Introduction to information retrieval", Cambridge University Press Cambridge,  Vol. 1,  (2008).

17.   Tan, C. L., Huang, W., Yu, Z. and Xu, Y., "Imaged document text retrieval without OCR", Pattern Analysis and Machine Intelligence, IEEE Transactions on,  Vol. 24, No. 6, (2002), 838-844.

18.           Keyvanpour, M. and Moghadam Charkari, N., "Interactive retrieval of natural images using multiple instance learning", Journal of Iranian Association of Electrical and Electronics Engineers,  Vol. 6, No. 1, (2009) 19-35.   





International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir