Inducing a perceptual relevance shape classifier

ABSTRACT

In this paper, we develop a system to classify the outputs of image segmentation algorithms as perceptually relevant or perceptually irrelevant with respect to human perception. The work is aimed at figurative images. We previously investigated human visual perception of trademark images and established a body of ground truth data in the form of trademark images and their respective human segmentations. The work indicated that there is a core set of segmentations for each image that people perceive. Here we use this core set of segmentations to train a classifier to classify closed shapes output from an image segmentation algorithm so that the method returns the image segments that match those produced by people. We demonstrate that a perceptual relevance classifier is attainable and identify a good methodology to achieve this. The paper compares MLP, SVM, Bayes and regression classifiers for classifying shapes. MLPs perform best with an overall accuracy of 96.4%.

REFERENCES

• 1: Alwis, S. Content-Based Retrieval of Trademark Images, PhD Thesis, Dept. of Computer Science, University of York, UK, 1999
• 2: Beucher, S. Watersheds of Functions and Picture Segmentation, Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'82. pp. 1928--1931, 1982.
• 3: Borgelt, C. Machine Learning Algorithms Implemented in C, 2006, Note: Software available at http://fuzzy.cs.unimagdeburg.de/~borgelt/software.html
• 4: David Yuk-Ming Chan , Irwin King, Genetic Algorithm for Weights Assignment in Dissimilarity Function for Trademark Retrieval, Proceedings of the Third International Conference on Visual Information and Information Systems, p.557-565, June 02-04, 1999
• 5: Chang, C.-C. and Lin, C.-J. LIBSVM: a library for support vector machines, 2001, Note: Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
• 6: Desolneux, A., Moisan, L., and Morel, J.-M. A theory of digital image analysis. 2004. Book in preparation
• 7: Joachim Diederich, Explanation and artificial neural networks, International Journal of Man-Machine Studies, v.37 n.3, p.335-355, Sept. 1992 [doi>10.1016/0020-7373(92)90058-S]
• 8: Eakins, J. P. Riley, K. J. and Edwards, J. D. Shape Feature Matching for Trademark Image Retrieval, In, Image and Video Retrieval: Second International Conference, CIVR 2003. LNCS, vol. 2728, Jan 2003, Pages 28--38.
• 9: Myron Flickner , Harpreet Sawhney , Wayne Niblack , Jonathan Ashley , Qian Huang , Byron Dom , Monika Gorkani , Jim Hafner , Denis Lee , Dragutin Petkovic , David Steele , Peter Yanker, Query by Image and Video Content: The QBIC System, Computer, v.28 n.9, p.23-32, September 1995 [doi>10.1109/2.410146]
• 10: Hodge, V. J., Eakins, J. & Austin, J. Eliciting Perceptual Ground Truth for Image Segmentation. Technical Report YCS 401(2006), Department of Computer Science, University of York.
• 11: Hodge, V. J., Hollier, G., Eakins, J. & Austin, J. Eliciting Perceptual Ground Truth for Image Segmentation. In Proceedings International Conference on Image and Video Retrieval (CIVR2006). Tempe, Arizona, July 13--15, 2006.
• 12: Hu, M.-K. Visual Pattern Recognition by Moment Invariants. IRE Transactions on Information Theory, IT 8:179--187, 1962.
• 13: Hui Jiang , Chong-Wah Ngo , Hung-Khoon Tan, Gestalt-based feature similarity measure in trademark database, Pattern Recognition, v.39 n.5, p.988-1001, May, 2006 [doi>10.1016/j.patcog.2005.08.012]
• 14: John, G. H. and Langley, P. Estimating Continuous Distributions in Bayesian Classifiers. Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence. pp. 338--345. Morgan Kaufmann, San Mateo, 1995.
• 15: Koffka, K. Principles of Gestalt Psychology. Harcourt Brace. New York, 1963.
• 16: D G Lowe, Three-dimensional object recognition from single two-dimensional images, Artificial Intelligence, v.31 n.3, p.355-395, March 1987 [doi>10.1016/0004-3702(87)90070-1]
• 17: Ren, M., Eakins, J. P. and Briggs, P. Human perception of trademark images: implications for retrieval system design. Journal of Electronic Imaging, 9 (4):564--575, 2000.
• 18: Measuring Shape: Ellipticity, Rectangularity, and Triangularity, Proceedings of the International Conference on Pattern Recognition, p.1952, September 03-08, 2000
• 19: J. L. McClelland , D. E. Rumelhart , G. E. Hinton, The appeal of parallel distributed processing, Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations, MIT Press, Cambridge, MA, 1986
• 20: Sagata Regression v1.0 Copyright © 2002-2003 Sagata, Ltd. www.sagata.com
• 21: Sudeep Sarkar , Kim L. Boyer, On Optimal Infinite Impulse Response Edge Detection Filters, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.13 n.11, p.1154-1171, November 1991 [doi>10.1109/34.103275]
• 22: Eric Saund, Finding Perceptually Closed Paths in Sketches and Drawings, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.25 n.4, p.475-491, April 2003 [doi>10.1109/TPAMI.2003.1190573]
• 23: Tzanetakis, G., Traka, M. and Tziritas, G. Motion estimation based on affine moment invariants. In Proc. European Signal Processing Conference (Euspico), Rhodes, Greece, 1998
• 24: Vladimir N. Vapnik, The nature of statistical learning theory, Springer-Verlag New York, Inc., New York, NY, 1995
• 25: Wertheimer, M. Laws of Organization in Perceptual Forms (1923). In, Ellis (ed) A Source Book of Gestalt Psychology, Routledge & Kegan Paul, London 1938.
• 26: Ian H. Witten , Eibe Frank, Data mining: practical machine learning tools and techniques with Java implementations, Morgan Kaufmann Publishers Inc., San Francisco, CA, 2000
• 27: Daniel M. Wuescher , Kim L. Boyer, Robust Contour Decomposition Using a Constant Curvature Criterion, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.13 n.1, p.41-51, January 1991 [doi>10.1109/34.67629]
• 28: Zucker, S. W. Region Growing: Childhood and Adolescence, Computer Graphics & Image Processing: 5:382--399, 1976

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.4 Applications
          Subjects: Computer vision

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.10 Vision and Scene Understanding
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.6 Segmentation
          Subjects: Edge and feature detection
      I.4.7 Feature Measurement
  I.5 PATTERN RECOGNITION
      I.5.1 Models

General Terms:
Experimentation, Human Factors, Performance, Verification

Keywords:
classification, human image segmentation, image segmentation, perceptual classifier, perceptual relevance