A modular approach for query spotting in document images and its optimization using genetic algorithms

Query spotting in document images is a subclass of Content-Based Image Retrieval (CBIR) algorithms concerned with detecting occurrences of a query in a document image. Due to noise and complexity of document images, spotting can be a challenging task and easily prone to false positives and partially incorrect matches, thereby reducing the overall precision of the algorithm. A robust and accurate spotting algorithm is essential to our current research on sketch-based retrieval of digitized lecture materials. We have recently proposed a modular spotting algorithm in [1]. Compared to existing methods, our algorithm is both application-independent and segmentation-free. However, it faces the same challenges of noise and complexity of images. In this paper, inspired by our earlier research on optimizing parameter settings for CBIR using an evolutionary algorithm [2][3], we introduce a Genetic Algorithm-based optimization step in our spotting algorithm to improve each spotting result. Experiments using an image dataset of journal pages reveal promising performance, in that the precision is significantly improved but without compromising the recall of the overall spotting result.

[1]  Keisuke Kameyama,et al.  Content-Based Image Retrieval of Cultural Heritage Symbols by Interaction of Visual Perspectives , 2011, Int. J. Pattern Recognit. Artif. Intell..

[2]  Toufik SARI,et al.  A search engine for Arabic documents , 2008 .

[3]  Tomohiro Yoshikawa,et al.  A Study on Document Retrieval System Based on Visualization to Manage OCR Documents , 2013, HCI.

[4]  Kirmene Marzouki,et al.  A novel approach of Content Based Medical Images Indexing System Based on Spatial Distribution of Vector Descriptors , 2013, 10th International Multi-Conferences on Systems, Signals & Devices 2013 (SSD13).

[5]  Patrick Gros,et al.  Robust content-based image searches for copyright protection , 2003, MMDB '03.

[6]  V. Patil,et al.  An effective content Based Image Retrieval (CBIR) system based on evolutionary programming (EP) , 2012, 2012 IEEE International Conference on Advanced Communication Control and Computing Technologies (ICACCCT).

[7]  Il-Seok Oh,et al.  Segmentation-free word spotting using SIFT , 2012, 2012 IEEE Southwest Symposium on Image Analysis and Interpretation.

[8]  Houssem Chatbri,et al.  Sketch-based image retrieval by shape points description in support regions , 2013, 2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP).

[9]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[10]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[11]  Junbin Gao,et al.  Parallel model of independent component analysis constrained by reference curves for HPLC-DAD and its solution by multi-areas genetic algorithm , 2013, 2013 IEEE International Conference on Bioinformatics and Biomedicine.

[12]  Keisuke Kameyama,et al.  Content-Based Image Retrieval of Kaou Images by Relaxation Matching of Region Features , 2006, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[13]  Andries P. Engelbrecht,et al.  Computational Intelligence: An Introduction , 2002 .

[14]  Edward A. Fox,et al.  A genetic programming framework for content-based image retrieval , 2009, Pattern Recognit..

[15]  Keisuke Kameyama,et al.  Relevance Optimization in Image Database Using Feature Space Preference Mapping and Particle Swarm Optimization , 2007, ICONIP.

[16]  Chew Lim Tan,et al.  Keyword Spotting in Document Images through Word Shape Coding , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[17]  Ying Liu,et al.  A survey of content-based image retrieval with high-level semantics , 2007, Pattern Recognit..

[18]  Antoine Geissbühler,et al.  A Review of Content{Based Image Retrieval Systems in Medical Applications { Clinical Bene(cid:12)ts and Future Directions , 2022 .

[19]  Robert M. Haralick,et al.  Recursive X-Y cut using bounding boxes of connected components , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[20]  Keisuke Kameyama,et al.  Optimal Parameter Selection in Image Similarity Evaluation Algorithms Using Particle Swarm Optimization , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[21]  Ching Y. Suen,et al.  WORD SPOTTING TECHNIQUES IN DOCUMENT ANALYSIS AND RETRIEVAL — A COMPREHENSIVE SURVEY , 2009 .

[22]  Keisuke Kameyama,et al.  Particle Swarm Optimization - A Survey , 2009, IEICE Trans. Inf. Syst..

[23]  Colin G. Johnson.  Search-based evolutionary operators for extensionally-defined search spaces: Applications to image search , 2012, 2012 IEEE Congress on Evolutionary Computation.

[24]  Moncef Gabbouj,et al.  Multi-dimensional evolutionary feature synthesis for content-based image retrieval , 2011, 2011 18th IEEE International Conference on Image Processing.

[25]  Erik G. Learned-Miller,et al.  Learning on the Fly: Font-Free Approaches to Difficult OCR Problems , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[26]  Keisuke Kameyama,et al.  Sketch-Based Image Retrieval by Size-Adaptive and Noise-Robust Feature Description , 2013, 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[27]  Mindy Bokser,et al.  Omnidocument technologies , 1992, Proc. IEEE.

[28]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[29]  Keisuke Kameyama,et al.  An Application-Independent and Segmentation-Free Approach for Spotting Queries in Document Images , 2014, 2014 22nd International Conference on Pattern Recognition.

[30]  Dhavachelvan Ponnurangam,et al.  A survey of keyword spotting techniques for printed document images , 2010, Artificial Intelligence Review.

[31]  Li Yu,et al.  Math Spotting: Retrieving Math in Technical Documents Using Handwritten Query Images , 2011, 2011 International Conference on Document Analysis and Recognition.

[32]  Yue Lu,et al.  Word spotting in Chinese document images without layout analysis , 2002, Object recognition supported by user interaction for service robots.

[33]  Hamid Abrishami Moghaddam,et al.  A Novel Evolutionary Approach for Optimizing Content-Based Image Indexing Algorithms , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[34]  Marcel Worring,et al.  Content-Based Image Retrieval at the End of the Early Years , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[35]  Xiaojun Wu,et al.  A novel contour descriptor for 2D shape matching and its application to image retrieval , 2011, Image Vis. Comput..

[36]  Keisuke Kameyama,et al.  Using scale space filtering to make thinning algorithms robust against noise in sketch images , 2014, Pattern Recognit. Lett..

[37]  Keisuke Kameyama,et al.  Towards making thinning algorithms robust against noise in sketch images , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[38]  Keisuke Kameyama,et al.  On a relaxation-labeling algorithm for real-time contour-based image similarity retrieval , 2003, Image Vis. Comput..

[39]  Keisuke Kameyama,et al.  Trademark retrieval by relaxation matching on fluency function approximated image contours , 2001, 2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (IEEE Cat. No.01CH37233).

[40]  R. Manmatha,et al.  Word spotting for historical documents , 2006, International Journal of Document Analysis and Recognition (IJDAR).

[41]  Edward M. Riseman,et al.  Word spotting: a new approach to indexing handwriting , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[42]  Keisuke Kameyama,et al.  Constructive Relaxation Matching Involving Dynamical Model Switching and Its Application to Shape Matching , 2002, Int. J. Image Graph..