Abstract
Current learning approaches to computer vision have mainly focussed on low-level image processing and object recognition, while tending to ignore high-level processing such as understanding. Here we propose an approach to object recognition that facilitates the transition from recognition to understanding. The proposed approach embraces the synergistic spirit of soft computing, exploiting the global search powers of genetic programming to determine fuzzy probabilistic models. It begins by segmenting the images into regions using standard image processing approaches, which are subsequently classified using a discovered fuzzy Cartesian granule feature classifier. Understanding is made possible through the transparent and succinct nature of the discovered models. The recognition of roads in images is taken as an illustrative problem in the vision domain. The discovered fuzzy models while providing high levels of accuracy (97%), also provide understanding of the problem domain through the transparency of the learnt models. The learning step in the proposed approach is compared with other techniques such as decision trees, naïve Bayes and neural networks using a variety of performance criteria such as accuracy, understandability and efficiency.
Similar content being viewed by others
References
Almuallim, H. and Dietterich, T. G.: 1991, Learning with irrelevant features, in: AAAI-91, Anaheim, CA, pp. 547-552.
Baldwin, J. F.: 1991a, Combining evidences for evidential reasoning, Internat. J. Intelligent Systems 6(6), 569-616.
Baldwin, J. F.: 1991b, A theory of mass assignments for artificial intelligence, in: A. L. Ralescu (ed.), IJCAI '91 Workshops on Fuzzy Logic and Fuzzy Control, Sydney, Australia, Lecture Notes in Artificial Intelligence, pp. 22-34.
Baldwin, J. F.: 1992, Fuzzy and probabilistic uncertainties, in: Shapiro (ed.), Encyclopaedia of AI, 2nd edn, pp. 528-537.
Baldwin, J. F.: 1993a, Evidential support logic, FRIL and cased base reasoning, Internat. J. Intelligent Systems 8(9), 939-961.
Baldwin, J. F.: 1993b, Probabilistic, fuzzy and evidential reasoning in FRIL (fuzzy relational inference language), in: Two Decades of Fuzzy Control, IEE, London, pp. 7/1-7/4.
Baldwin, J. F., Lawry, J., and Martin, T. P.: 1996, Efficient algorithms for semantic unification, in: IPMU, Granada, Spain, pp. 527-532.
Baldwin, J. F., Martin, T. P., and Pilsworth, B. W.: 1995, FRIL-Fuzzy and Evidential Reasoning in A.I., Research Studies Press, Wiley ISBN 086380159 5.
Baldwin, J. F., Martin, T. P., and Shanahan, J. G.: 1996, Modelling with words using Cartesian granule features, in: ITRC 246, Dept. of Engineering Maths, University of Bristol, UK.
Baldwin, J. F., Martin, T. P., and Shanahan, J. G.: 1997, Modelling with words using Cartesian granule features, in: FUZZ-IEEE, Barcelona, Spain, pp. 1295-1300.
Baldwin, J. F., Martin, T. P., and Shanahan, J. G.: 1998a, Aggregation in Cartesian granule feature models, IPMU, Paris, 6.
Baldwin, J. F., Martin, T. P., and Shanahan, J. G.: 1998b, System identification of fuzzy Cartesian granule feature models using genetic programming, in: A. L. Ralescu and J. G. Shanahan (eds), IJCAI Workshop on Fuzzy Logic in Artificial Intelligence, Lecture Notes in Artificial Intelligence, Vol. 1566, Springer, Berlin, p. 26.
Bastian, A.: 1995, Modelling and identifying fuzzy systems under varying user knowledge, PhD Thesis, Meiji University, Tokyo.
Blum, A. L. and Langley, P.: 1997, Selection of relevant features and examples in machine learning, Artificial Intelligence 97, 245-271.
Bovlik, A. C., Clark, M., and Geisler, W. S.: 1990, Multichannel texture analysis using localised spatial filters, IEEE Trans. on PAMI 12(1), 55-73.
Brooks, R. A.: 1987, Model-based three-dimensional interpretations of two-dimensional images, in: M. A. Fischler and O. Firschein (eds), Readings in Computer Vision: Issues, Problems, Principles, and Paradigms, Kaufmann Publishers, Los Altos, CA, USA, pp. 360-370.
Caelli, T. and Reye, D.: 1993, On the classification of image regions by colour, texture and shape, Pattern Recognition 26(4), 461-470.
Campbell, F.W. and Robson, J. G.: 1968, Application of Fourier analysis to the visibility of gratings, Journal of Physiology 197, 551-566.
Campbell, N. W., Mackeown, W. P. J., Thomas, B. T., and Troscianko, T.: 1997, Interpreting image databases by region classification, Pattern Recognition 30(4), 555-563.
Campbell, N. W., Thomas, B. T., and Troscianko, T.: 1997, Automatic segmentation and classification of outdoor images using neural networks, Internat. J. of Neural Systems 8(1), 137-144.
Connell, J. H. and Brady, M.: 1987, Generating and generalising models of visual objects, Artificial Intelligence 34, 159-183.
Cootes, T. F. and Taylor, C. J.: 1995, Combining point distributions with shape models based on finite-element analysis, Image Vision Computation 13(5), 403-409.
Cootes, T. F., Taylor, C. J., Cooper, D. H., and Graham, J.: 1992, Training models of shape from sets of examples, in: British Machine Vision Conference, Leeds, UK, pp. 9-18.
Daugman, J. G.: 1985, Uncertainty relation for resolution in space, spatial, frequency, and orientation optimised by two-dimensional visual cortical filters, J. Optical Soc. Am. 2(7), 1160-1169.
Devijer, P. A. and Kittler, J.: 1982, Pattern Recognition: A Statistical Approach, Prentice-Hall, Englewood Cliffs, NJ.
Dietterich, T. G. and Michalski, R. S.: 1983, A comparative review of selected methods for learning from examples, in: R. S. Michalski, J. G. Carbonell, and T.M. Mitchell (eds), Machine Learning: An Artificial Intelligence Approach, Springer, Berlin, pp. 41-81.
Draper, B. A., Collins, R. T., Brolio, J., Hanson, A. R., and Riseman, E. M.: 1989, The schema system, Internat. J. Computer Vision 2, 209-250.
Dubois, D. and Prade, H.: 1991, Fuzzy sets in approximate reasoning 1-inference with possibility distributions, Fuzzy Sets and Systems 40, 143-202.
Fischler, M. A. and Firschein, O.: 1987, Readings in Computer Vision: Issues, Problems, Principles, and Paradigms, Kaufmann Publishers, Los Altos, CA, USA, pp. 765-768.
Frawley, W. J., Piatetsky-Shapiro, G., and Matheus, C. J.: 1991, Knowledge discovery in databases: An overview, in: G. Piatetsky-Shapiro and W. J. Frawley (eds), Knowledge Discovery in Databases, AAAI Press/MIT Press, Cambridge, MA, USA, pp. 1-27.
Glassner, A. S.: 1995, Principles of Digital Image Synthesis, Morgan Kaufmann, San Francisco.
Good, I. J.: 1965, The Estimation of Probabilities: An Essay on Modern Bayesian Methods, MIT Press, Cambridge, MA.
Grimson, W. E. L. and Lozano-Perez, T.: 1984, Model-based recognition and localization from sparse range or tactile data, Internat. J. Robotics Res. 3(3), 3-35.
Jain, A. K., Ratha, N. K., and Lakshmanan, S.: 1997, Object detection using Gabor filters, Pattern Recognition 30(2), 295-309.
Jolliffe, I. T.: 1986, Principal Component Analysis, Springer, New York.
Kira, K. and Rendell, L.: 1992, A practical approach to feature selection, in: 9th Conference in Machine Learning, Aberdeen, Scotland, pp. 249-256.
Klir, G. J. and Yuan, B.: 1995, Fuzzy Sets and Fuzzy Logic, Theory and Applications, Prentice-Hall, Englewood Cliffs, NJ.
Kohavi, R. and John, G. H.: 1997, Wrappers for feature selection, Artificial Intelligence 97, 273-324.
Kononenko, I. and Hong, S. J.: 1997, Attribute selection for modelling, FGCS Special Issue in Data Mining (Fall), 34-55.
Kosako, A., Ralescu, A. L., and Shanahan, J. G.: 1994, Fuzzy techniques in image understanding, in: ISCIE Joint Conf. for Automatic Control, Osaka, Japan, pp. 17-22.
Koza, J. R.: 1992, Genetic Programming, MIT Press, Cambridge, MA.
Koza, J. R.: 1994, Genetic Programming II, MIT Press, Cambridge, MA.
Mackeown, W. P. J., Greenway, P., Thomas, B. T., and Wright, W. A.: 1994, Contextual image labelling with a neural network, IEE Vision, Speech and Signal Processing, 238-244.
Malik, I. and Perona, P.: 1990, Preattentive texture discrimination with early vision mechanisms, J. Opt. Society Am. A 7, 923-932.
Michalski, R. S. and Chilausky, R. L.: 1980, Learning by being told and by examples, Internat. J. Policy Analysis and Information Systems 4, 125-161.
Michalski, R. S., Rosenfeld, A., Duric, Z., Maloof, M., and Zhang, Q.: 1998a, Data mining and knowledge discovery: A review of issues and a multistrategy approach, in: R. S. Michalski, I. Bratko, and M. Kubat (eds), Machine Learning and Data Mining, Wiley, New York, pp. 71-112.
Michalski, R. S., Rosenfeld, A., Duric, Z., Maloof, M., and Zhang, Q.: 1998b, Learning patterns in images, in: R. S. Michalski, I. Bratko, and M. Kubat (eds), Machine Learning and Data Mining, Wiley, New York, pp. 241-268.
Mirmehdi, M., Palmer, P. L., Kittler, J., and Dabis, H.: 1999, Feedback control strategies for object recognition, IEEE Trans. Image Processing 8(8), 1084-1101.
Moller, M. F.: 1993, A scaled conjugate gradient algorithm for fast supervised learning, Neural Networks 6, 525-533.
Mukunoki, M., Minoh, M., and Ikeda, K.: 1994, Retrieval of images using pixel based object models, in: IPMU, Paris, France, pp. 1127-1132.
Murase, H. and Nayar, S. K.: 1993, Learning and recognition of 3D objects from appearance, in: IEEE 2nd Qualitative Vision Workshop, New York, pp. 39-50.
Murphy, S. K., Kasif, S., and Salzburg, S.: 1994, A system for induction of oblique decision trees, J. Artificial Intelligence Res. 2, 1-33.
Quinlan, J. R.: 1986, Induction of decision trees, Machine Learning 1(1), 86-106.
Quinlan, J. R.: 1993, C4.5: Programs for Machine Learning, Morgan Kaufmann, San Mateo, CA.
Ralescu, A. L. and Hartani, R.: 1995, Some issues in fuzzy and linguistic modelling, in: Workshop on Linguistic Modelling, FUZZ-IEEE, Yokohama, Japan.
Ralescu, A. L. and Shanahan, J. G.: 1995, Line structure inference in fuzzy perceptual grouping, in: NSF Workshop on Computer Vision, Islamabad, Pakistan, pp. 225-239.
Ralescu, A. L. and Shanahan, J. G.: 1999, Fuzzy perceptual organisation of image structures, Pattern Recognition 32, 1923-1933.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J.: 1986, Learning internal representations by error propagation, in: D. E. Rumelhart and J. L. McClelland (eds), Parallel Distributed Processing, Vol. 1, MIT Press, Cambridge, USA.
Ruspini, E. H.: 1969, A new approach to clustering, Inform. Control 15(1), 22-32.
Schweizer, B. and Sklar, A.: 1961, Associative functions and statistical triangle inequalities, Publ. Math. Debrecen 8, 169-186.
Shanahan, J. G.: 1998, Cartesian granule features: Knowledge discovery of additive models for classification and prediction, PhD Thesis, Dept. of Engineering Maths, University of Bristol, Bristol, UK.
Shanahan, J. G., Baldwin, J. F., Campbell, N., Martin, T. P., Mirmehdi, M., and Thomas, B. T.: 1999, Road recognition using fuzzy classifiers, in: British Machine Vision Conference (BMVC), Nottingham, UK, pp. 432-442.
Shepherd, B. A.: 1983, An appraisal of a decision tree approach to image classification, Internat. Joint Conf. on AI, pp. 473-475.
Strat, T. M.: 1992, Natural Object Recognition, Springer, New York, USA.
Sudkamp, T.: 1992, On probability-possibility transformation, Fuzzy Sets and Systems 51, 73-81.
Syswerda, G.: 1989, Uniform crossover in genetic algorithms, in: J. D. Schaffer (ed.), Third Internat. Conf. on Genetic Algorithms, Morgan Kaufmann, San Francisco, pp. 989-995.
Turk, M. A. and Pentland, A. P.: 1991, Face recognition using eigenfaces, in: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 586-591.
Valois, L. R. D. and Valois, K. K. D.: 1993, A multi-stage color model, Vision Research 33(8), 1053-1065.
Valois, R. L. D., Albreacht, D. G., and Thorell, L. G.: 1982, Spatial-frequency selectivity of cells in macaque visual cortex, Visual Research 22, 545-559.
Winston, P. H.: 1975, The Psychology of Computer Vision, McGraw-Hill, New York.
Wood, M. E. J., Campbell, N.W., and Thomas, B. T.: 1997, Searching large image databases using radial basis function neural networks, in: Internat. Conf. on Image Processing and its Applications, London, UK, pp. 116-120.
Zadeh, L. A.: 1968, Probability measures of fuzzy events, J. Math. Analysis Appl. 23, 421-427.
Zadeh, L. A.: 1975a, The concept of a linguistic variable and its application to approximate reasoning. Part 1, Inform. Sci. 8, 199-249.
Zadeh, L. A.: 1975b, The concept of a linguistic variable and its application to approximate reasoning. Part 2, Inform. Sci. 8, 301-357.
Zadeh, L. A.: 1975c, The concept of a linguistic variable and its application to approximate reasoning. Part 3, Inform. Sci. 9, 43-80.
Zadeh, L. A.: 1994, Soft computing and fuzzy logic, IEEE Software 11(6), 48-56.
Zadeh, L. A.: 1996, Fuzzy logic=computing with words, IEEE Trans. Fuzzy Systems 4(2), 103-111.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Shanahan, J., Thomas, B., Mirmehdi, M. et al. A Soft Computing Approach to Road Classification. Journal of Intelligent and Robotic Systems 29, 349–387 (2000). https://doi.org/10.1023/A:1008158907779
Issue Date:
DOI: https://doi.org/10.1023/A:1008158907779