Neuro-fuzzy synergism to the intelligent system for edge detection and enhancement

The paper presents a fuzzy neural network system for edge detection and enhancement. The system can both: (a) obtain edges and (b) enhance edges by recovering missing edges and eliminate false edges caused by noise. The research is comprised of three stages, namely, adaptive fuzzification which is employed to fuzzify the input patterns, edge detection by a three-layer feedforward fuzzy neural network, and edge enhancement by a modified Hopfield neural network. The typical sample patterns are first fuzzified. Then they are used to train the proposed fuzzy neural network. After that, the trained network is able to determine the edge elements with eight orientations. Pixels having high edge membership are traced for further processing. Based on constraint satisfaction and the competitive mechanism, interconnections among neurons are determined in the Hopfield neural network. A criterion is provided to find the final stable result that contains the enhanced edge measurement. The proposed neural networks are simulated on a SUN Sparc station. One hundred and twenty-three training samples are well chosen to cover all the edge and non-edge cases and the performance of the system will not be improved by adding more training samples. Test images are degraded by random noise up to 30% of the original images. Compared with standard edge detection operators and enhancement techniques, the proposed system based on the neuro-fuzzy synergism obtains very good results.

[1]  Azriel Rosenfeld,et al.  Picture Processing and Psychopictorics , 1970 .

[2]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[3]  Ching-Yu Tyan,et al.  Image processing-enhancement, filtering and edge detection using the fuzzy logic approach , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[4]  Sankar K. Pal,et al.  Fuzzy models for pattern recognition , 1992 .

[5]  Chin-Teng Lin,et al.  Neural fuzzy systems , 1994 .

[6]  Patrick K. Simpson,et al.  Fuzzy min-max neural networks - Part 2: Clustering , 1993, IEEE Trans. Fuzzy Syst..

[7]  Azriel Rosenfeld,et al.  Scene Labeling by Relaxation Operations , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  Ling Guan,et al.  A neural learning approach for adaptive image restoration using a fuzzy model-based network architecture , 2001, IEEE Trans. Neural Networks.

[9]  Josef Kittler,et al.  Edge-Labeling Using Dictionary-Based Relaxation , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Svetha Venkatesh,et al.  Modeling Edges at Subpixel Accuracy Using the Local Energy Approach , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[12]  Sankar K. Pal,et al.  Self-organization for object extraction using a multilayer neural network and fuzziness measures , 1993, IEEE Trans. Fuzzy Syst..

[13]  Azriel Rosenfeld,et al.  Computer Methods in Image Analysis , 1977 .

[14]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Lawrence G. Roberts,et al.  Machine Perception of Three-Dimensional Solids , 1963, Outstanding Dissertations in the Computer Sciences.

[16]  Larry S. Davis,et al.  A survey of edge detection techniques , 1975 .

[17]  W. Thompson,et al.  A fuzzy if-then approach to edge detection , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[18]  Sudeep Sarkar,et al.  Comparison of edge detectors: a methodology and initial study , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Lionel Pelkowitz,et al.  A continuous relaxation labeling algorithm for Markov random fields , 1990, IEEE Trans. Syst. Man Cybern..

[20]  Edwin R. Hancock,et al.  A label error process for discrete relaxation , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[21]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[22]  Peter Meer,et al.  Edge Detection with Embedded Confidence , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  F. R. Hansen,et al.  Image segmentation using simple markov field models , 1982, Computer Graphics and Image Processing.

[24]  Siwei Lu,et al.  Hierarchical artificial neural networks for edge enhancement , 1993, Pattern Recognit..

[25]  Jun Shen,et al.  An optimal linear operator for step edge detection , 1992, CVGIP Graph. Model. Image Process..

[26]  Nikolaos G. Bourbakis,et al.  A Fuzzy-Like Approach for Smoothing and Edge Detection in Color Images , 1998, Int. J. Pattern Recognit. Artif. Intell..

[27]  Ramakant Nevatia.  Evaluation of a simplified Hueckel edge-line detector , 1977 .

[28]  Woo Young Choi,et al.  A new interpretation of the compass gradient edge operators , 1989, Comput. Vis. Graph. Image Process..

[29]  G. S. Robinson.  Edge detection by compass gradient masks , 1977 .

[30]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[31]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[32]  Josef Kittler,et al.  Discrete relaxation , 1990, Pattern Recognit..

[33]  S. Sitharama Iyengar,et al.  A New Probabilistic Relaxation Scheme and Its Application to Edge Detection , 1996, IEEE Trans. Pattern Anal. Mach. Intell..