research-article

Towards more effective distance functions for word image matching

Authors:

C. V. JawaharAuthors Info & Claims

DAS '10: Proceedings of the 9th IAPR International Workshop on Document Analysis Systems

Pages 363 - 370

https://doi.org/10.1145/1815330.1815377

Published: 09 June 2010 Publication History

Abstract

Matching word images has many applications in document recognition and retrieval systems. Dynamic Time Warping (DTW) is popularly used to estimate the similarity between word images. Word images are represented as sequences of feature vectors, and the cost associated with dynamic programming based alignment is considered as the dissimilarity between them. However, such approaches are computationally costly when compared to fixed length matching schemes. In this paper, we explore systematic methods for identifying appropriate distance metrics for a given database or language. This is achieved by learning query specific distance functions which can be computed online efficiently. We show that a weighted Euclidean distance can outperform DTW for matching word images. This class of distance functions are also ideal for scalability and large scale matching. Our results are validated with mean Average Precision (mAP) on a fully annotated data set of 160K word images. We then show that the learnt distance functions can even be extended to a new database to obtain accurate retrieval.

References

[1]

Digital library of india. http://dli.iiit.ac.in/.

[2]

S. Aksoy, R. M. Haralick, F. A. Cheikh, and M. Gabbouj. A weighted distance approach to relevance feedback. In ICPR, pages 4812--4815, 2000.

Digital Library

[3]

A. Balasubramanian, M. Meshesha, and C. V. Jawahar. Retrieval from document image collections. In Document Analysis Systems, pages 1--12, 2006.

Digital Library

[4]

A. Bar-Hillel, T. Hertz, N. Shental, and D. Weinshall. Learning a mahalanobis metric from equivalence constraints. Journal of Machine Learning Research, 6:937--965, 2005.

Digital Library

[5]

C. Böhm, S. Berchtold, and D. A. Keim. Searching in high-dimensional spaces: Index structures for improving the performance of multimedia databases. ACM Computing Surveys., 33(3):322--373, 2001.

Digital Library

[6]

T. E. de Campos, B. R. Babu, and M. Varma. Character recognition in natural images. In VISSAPP (2), pages 273--280, 2009.

[7]

T. Deselaers, R. Paredes, E. Vidal, and H. Ney. Learning weighted distances for relevance feedback in image retrieval. In ICPR, pages 1--4, 2008.

[8]

D. S. Doermann. The indexing and retrieval of document images: A survey. Computer Vision and Image Understanding, 70(3):287--298, 1998.

Digital Library

[9]

A. Franco, A. Lumini, and D. Maio. A new approach for relevance feedback through positive and negative samples. In ICPR (4), pages 905--908, 2004.

Digital Library

[10]

A. Frome, Y. Singer, and J. Malik. Image retrieval and classification using local distance functions. In NIPS, pages 417--424, 2006.

[11]

T. Hong, T., and J. J. Hull. Algorithms for postprocessing ocr results with visual inter-word constraints. In ICIP, 1995.

Digital Library

[12]

T. Konidaris, B. Gatos, K. Ntzios, I. Pratikakis, S. Theodoridis, and S. J. Perantonis. Keyword-guided word spotting in historical printed documents using synthetic data and user feedback. IJDAR, 2007.

Digital Library

[13]

A. Kumar, C. V. Jawahar, and R. Manmatha. Efficient search in document image collections. In ACCV (1), pages 586--595, 2007.

Digital Library

[14]

V. Lavrenko, T. M. Rath, and R. Manmatha. Holistic word recognition for handwritten historical documents. In DIAL, pages 278--287, 2004.

Digital Library

[15]

D. Lowe. Object recognition from local scale-invariant features. In ICCV, pages 1150--1157, 1999.

Digital Library

[16]

Y. Lu, C. L. Tan, W. Huang, and L. Fan. An approach to word image matching based on weighted hausdorff distance. ICDAR, 2001.

[17]

R. Manmatha, C. Han, and E. M. Riseman. Word spotting: A new approach to indexing handwriting. In CVPR, pages 631--637, 1996.

Digital Library

[18]

M. Meshesha and C. V. Jawahar. Matching word images for content-based retrieval from printed document images. IJDAR, 11(1):29--38, 2008.

Digital Library

[19]

V. Rasagna, A. Kumar, C. V. Jawahar, and R. Manmatha. Robust recognition of documents by fusing results of word clusters. In ICDAR, 2009.

Digital Library

[20]

T. M. Rath and R. Manmatha. Word image matching using dynamic time warping. In CVPR (2), pages 521--527, 2003.

[21]

T. M. Rath and R. Manmatha. Word spotting for historical documents. IJDAR, 9(2--4):139--152, 2007.

Digital Library

[22]

J. Rodriguez-Serrano, F. Perronnin, J. Llados, and G. Sanchez. A similarity measure between vector sequences with application to handwritten word image retrieval. CVPR, 2009.

[23]

Y. Seiji and O. Takashi. Document retrieval using relevance feedback. CICSJ Bull, 21(1):32--36, 2004.

[24]

J. B. Tenenbaum and W. T. Freeman. Separating style and content with bilinear models. Neural Computing, 12(6):1247--1283, 2000.

Digital Library

[25]

C. J. van Rijsbergen. Information Retrieval. Butterworth, 1979.

Digital Library

[26]

K. Q. Weinberger, J. Blitzer, and L. K. Saul. Distance metric learning for large margin nearest neighbor classification. In NIPS, 2005.

Digital Library

[27]

Q. Zheng and T. Kanungo. Morphological degradation models and their use in document image restoration. In ICIP (1), pages 193--196, 2001.

[28]

X. S. Zhou and T. S. Huang. Relevance feedback in image retrieval: A comprehensive review. Multimedia System, 8(6):536--544, 2003.

Cited By

Nadendla HSrikrishna ARao K(2022) FSOA‐DNFNet : Incremental indexing and image classification using hybrid optimization‐based deep neuro Fuzzy network Concurrency and Computation: Practice and Experience10.1002/cpe.704934:19Online publication date: 10-May-2022
https://doi.org/10.1002/cpe.7049
Kumari LSharma A(2021)A Review of Deep Learning Techniques in Document Image Word SpottingArchives of Computational Methods in Engineering10.1007/s11831-021-09605-7Online publication date: 17-May-2021
https://doi.org/10.1007/s11831-021-09605-7
Vidal EToselli APuigcerver J(2015)High performance Query-by-Example keyword spotting using Query-by-String techniquesProceedings of the 2015 13th International Conference on Document Analysis and Recognition (ICDAR)10.1109/ICDAR.2015.7333860(741-745)Online publication date: 23-Aug-2015
https://dl.acm.org/doi/10.1109/ICDAR.2015.7333860
Show More Cited By

Recommendations

An Approach to Word Image Matching Based on Weighted Hausforff Distance
ICDAR '01: Proceedings of the Sixth International Conference on Document Analysis and Recognition

Abstract: An approach to word image matching based on weighted Hausdorff distance (WHD) is proposed in this paper to facilitate the detection and location of the user-specified words in the document images. Preprocessing such as eliminating the space ...
A new Hausdorff distance for image matching

Object matching in two-dimensional images has been an important topic in computer vision, object recognition, and image analysis. The Hausdorff distance plays an important role in image matching. In order to deal with image matching problems in random ...
Hybrid image matching combining Hausdorff distance with normalized gradient matching

Image matching has been a central problem in computer vision and image processing for decades. Most of the previous approaches to image matching can be categorized into the intensity-based and edge-based comparison. Hausdorff distance has been widely ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

DAS '10: Proceedings of the 9th IAPR International Workshop on Document Analysis Systems

June 2010

490 pages

ISBN:9781605587738

DOI:10.1145/1815330

General Chairs:
David Doermann
University of Maryland, College Park
,
Venu Govindaraju
University at Buffalo, SUNY
,
Daniel Lopresti
Lehigh University
,
Prem Natarajan
Raytheon BBN Technologies

Copyright © 2010 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 09 June 2010

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Research-article

Conference

DAS '10

DAS '10: The Eighth IAPR International Workshop on Document Analysis Systems

June 9 - 11, 2010

Massachusetts, Boston, USA

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
154
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 02 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Nadendla HSrikrishna ARao K(2022) FSOA‐DNFNet : Incremental indexing and image classification using hybrid optimization‐based deep neuro Fuzzy network Concurrency and Computation: Practice and Experience10.1002/cpe.704934:19Online publication date: 10-May-2022
https://doi.org/10.1002/cpe.7049
Kumari LSharma A(2021)A Review of Deep Learning Techniques in Document Image Word SpottingArchives of Computational Methods in Engineering10.1007/s11831-021-09605-7Online publication date: 17-May-2021
https://doi.org/10.1007/s11831-021-09605-7
Vidal EToselli APuigcerver J(2015)High performance Query-by-Example keyword spotting using Query-by-String techniquesProceedings of the 2015 13th International Conference on Document Analysis and Recognition (ICDAR)10.1109/ICDAR.2015.7333860(741-745)Online publication date: 23-Aug-2015
https://dl.acm.org/doi/10.1109/ICDAR.2015.7333860
Rodriguez-Serrano JGordo APerronnin F(2015)Label EmbeddingInternational Journal of Computer Vision10.1007/s11263-014-0793-6113:3(193-207)Online publication date: 1-Jul-2015
https://dl.acm.org/doi/10.1007/s11263-014-0793-6
Ranjan VHarit GJawahar C(2014)Enhancing Word Image Retrieval in Presence of Font Variations2014 22nd International Conference on Pattern Recognition10.1109/ICPR.2014.468(2709-2714)Online publication date: Aug-2014
https://doi.org/10.1109/ICPR.2014.468

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten