The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.10 - Oct. (2013 vol.35)
pp: 2323-2339
Eric Saund , Palo Alto Research Center, Palo Alto
ABSTRACT
Effective object and scene classification and indexing depend on extraction of informative image features. This paper shows how large families of complex image features in the form of subgraphs can be built out of simpler ones through construction of a graph lattice--a hierarchy of related subgraphs linked in a lattice. Robustness is achieved by matching many overlapping and redundant subgraphs, which allows the use of inexpensive exact graph matching, instead of relying on expensive error-tolerant graph matching to a minimal set of ideal model graphs. Efficiency in exact matching is gained by exploitation of the graph lattice data structure. Additionally, the graph lattice enables methods for adaptively growing a feature space of subgraphs tailored to observed data. We develop the approach in the domain of rectilinear line art, specifically for the practical problem of document forms recognition. We are especially interested in methods that require only one or very few labeled training examples per category. We demonstrate two approaches to using the subgraph features for this purpose. Using a bag-of-words feature vector we achieve essentially single-instance learning on a benchmark forms database, following an unsupervised clustering stage. Further performance gains are achieved on a more difficult dataset using a feature voting method and feature selection procedure.
INDEX TERMS
Junctions, Lattices, NIST, Vocabulary, Vectors, Histograms, Support vector machine classification, weighted voting, Graph lattice, subgraph matching, document classification, line-art analysis, CMD distance
CITATION
Eric Saund, "A Graph Lattice Approach to Maintaining and Learning Dense Collections of Subgraphs as Image Features", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.35, no. 10, pp. 2323-2339, Oct. 2013, doi:10.1109/TPAMI.2012.267
REFERENCES
[1] Y. Amit and D.Y. Geman, "Shape Quantization and Recognition with Randomized Trees," Neural Computation, vol. 9, pp. 1545-1588, 1997.
[2] A.D. Bagdanov and M. Worring, "Fine-Grained Document Genre Classification Using First Order Random Graphs," Proc. Sixth Int'l Conf. Document Analysis and Recognition, pp. 79-83, 2001.
[3] G. Brown, "A New Perspective for Information Theoretic Feature Selection," Proc. 12th Int'l Conf. Artificial Intelligence and Statistics, Apr. 2009.
[4] H. Bunke, "Graph Matching: Theoretical Foundations, Algorithms, and Applications," Proc. Int'l Conf. Vision Interface, pp. 82-88, 2000.
[5] N. Chen and D. Blostein, "A Survey of Document Image Classification: Problem Statement, Classifier Architecture and Performance Evaluation," Int'l J. Document Analysis and Recognition, vol. 10, pp. 1-16, 2007.
[6] D. Conte, P. Foggia, C. Sansone, and M. Vento, "How and Why Pattern Recogntion and Computer Vision Applications Use Graphs," Applied Graph Theory in Computer Vision and Pattern Recognition, A. Kandel, H. Bunke, and M. Last, eds., pp. 85-135, Springer, 2007.
[7] L.P. Cordella, P. Foggia, C. Sansone, and M. Vento, "A (Sub)Graph Isomorphism Algorithm for Matching Large Graphs," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 10, pp. 1367-1372, Oct. 2004.
[8] D. Dimmick, M. Garris, and C. Wilson, "Structured Forms Database," Technical Report Special Database 2, Nat'l Inst. of Standards and Technology, SFRS, Dec. 2001.
[9] S. Feng and R. Manmatha, "A Discrete Direct Retrieval Model for Image and Video Retrieval," Proc. Int'l Conf. Content-Based Image and Video Retrieval, pp. 427-436, July 2008.
[10] B. Julesz, E. Gilbert, and J. Victor, "Visual Discrimination of Textures with Identical Third-Order Statistics," Biological Cybernetics, vol. 31, no. 3, pp. 137-140, 1978.
[11] J. Llados, E. Marti, and J. Villanueva, "Symbol Recognition by Error-Tolerant Subgraph Matching between Region Adjacency Graphs," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 10, pp. 1137-1143, Oct. 2001.
[12] U. Manber, "Finding Similar Files in a Large File System," Proc. USENIX Winter Technical Conf., p. 2, 1994.
[13] B.T. Messmer and H. Bunke, "A New Algorithm for Error-Tolerant Subgraph Isomorphosm Detection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 5, pp. 493-504, May 1998.
[14] B.T. Messmer and H. Bunke, "Efficient Subgraph Isomorphism Detection: A Decomposition Approach," IEEE Trans. Knowledge and Data Eng., vol. 12, no. 2, pp. 307-323, Mar./Apr. 2000.
[15] T. Nakai, K. Kise, and M. Iwamura, "Use of Affine Invariants in Locally Likely Arrangement Hashing for Camera-Based Document Image Retrieval," Proc. Seventh Int'l Workshop Document Analysis Systems, pp. 541-552, 2006.
[16] D. Neogi, S.K. Ladd, and V. Govindaraju, "Systems and Methods for Classifying Electronic Documents by Extracting and Recognizing Text and Image Features Indicative of Document Categories," United States Patent Application 20090116757, May 2009.
[17] D. Nister and H. Stewenius, "Scalable Recognition with a Vocabulary Tree," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 2161-2168, 2006.
[18] A. Pizano, "Extracting Line Features from Images of Business Forms and Tables," Proc. 11th IAPR Int'l Conf. Pattern Recognition, vol. III, pp. 399-403, 1992.
[19] K.U. Reddy and V. Govindaraju, "Form Classification," Document Recognition and Retrieval XV, Yanikoglu and Berkner, eds., SPIE 2008.
[20] P. Sarkar, "Image Classification: Classifying Distributions of Visual Features," Proc. 18th Int'l Conf. Pattern Recognition, pp. 472-475, Aug. 2006.
[21] E. Saund, "Ama Dental Forms Line Art Corpus," http://www2.parc.com/isl/groups/pda/data DentalFormsLineArt DataSet.zip, 2012.
[22] E. Saund, "A Graph Lattice Approach to Maintaining Dense Collections of Subgraphs as Image Features," Proc. 11th Int'l Conf. Document Analysis and Recognition, pp. 1069-1074, 2011.
[23] N. Shervashidze, S. Vishwanathan, T. Petri, K. Mehlhorn, and K. Borgwardt, "Efficient Graphlet Kernels for Large Graph Comparison," Proc. 12th Int'l Conf. Artificial Intelligence and Statistics, pp. 488-495, 2009.
[24] C. Shin, D. Doermann, and A. Rosenfeld, "Classification of Document Pages Using Structure-Based Features," Int'l J. Document Analysis and Recognition, vol. 3, no. 4, pp. 232-247, 2001.
[25] N. Sidere, P. Heroux, and J.-Y. Ramel, "Vector Representation of Graphs: Application to the Classification of Symbols and Letters," Proc. 10th Int'l Conf. Document Analysis and Recognition, pp. 681-685, 2009.
[26] J. Sivic and A. Zisserman, "Video Google: A Text Retrieval Approach to Object Matching in Videos," Proc. Ninth IEEE Int'l Conf. Computer Vision, pp. 1470-1477, 2003.
[27] J. Yang, Y.-G. Jiang, A.G. Hauptmann, and C.-W. Ngo, "Evaluating Bag-of-Visual-Words Representations in Scene Classification," Proc. Ninth ACM Int'l Workshop Multimedia Information Retrieval, pp. 197-206, 2007.
[28] L. Zhu, Y. Chen, A. Torralba, W. Freeman, and A. Yuille, "Part and Appearance Sharing: Recursive Compositional Models for Multi-View Multi-Object Detection," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1919-1926, 2010.
6 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool