Adaptive integrated image segmentation and object recognition

The paper presents a general approach to image segmentation and object recognition that can adapt the image segmentation algorithm parameters to the changing environmental conditions. Segmentation parameters are represented by a team of generalized stochastic learning automata and learned using connectionist reinforcement learning techniques. The edge-border coincidence measure is first used as reinforcement for segmentation evaluation to reduce computational expenses associated with model matching during the early stage of adaptation. This measure alone, however, cannot reliably predict the outcome of object recognition. Therefore, it is used in conjunction with model matching where the matching confidence is used as a reinforcement signal to provide optimal segmentation evaluation in a closed-loop object recognition system. The adaptation alternates between global and local segmentation processes in order to achieve optimal recognition performance. Results are presented for both indoor and outdoor color images where the performance improvement over time is shown for both image segmentation and object recognition.

[1]  Yoshua Bengio,et al.  Reading checks with multilayer graph transformer networks , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Y. Le Cun,et al.  Shortest path segmentation: a method for training a neural network to recognize character strings , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[3]  Takeo Kanade,et al.  Recursive region segmentation by analysis of histograms , 1982, ICASSP.

[4]  Emanuele Trucco,et al.  Computer and Robot Vision , 1995 .

[5]  David L. Milgram,et al.  Region extraction using convergent evidence , 1979 .

[6]  Linda G. Shapiro,et al.  Image Segmentation Techniques , 1984, Other Conferences.

[7]  R. J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[8]  Keith Price,et al.  Picture Segmentation Using a Recursive Region Splitting Method , 1998 .

[9]  Marco Colombetti,et al.  Robot Shaping: Developing Autonomous Agents Through Learning , 1994, Artif. Intell..

[10]  John H. Holland,et al.  Escaping brittleness: the possibilities of general-purpose learning algorithms applied to parallel rule-based systems , 1995 .

[11]  Sebastian Thrun,et al.  Finding Structure in Reinforcement Learning , 1994, NIPS.

[12]  Bir Bhanu,et al.  Recognition of occluded objects: A cluster-structure algorithm , 1987, Pattern Recognit..

[13]  Yoshua Bengio,et al.  Word normalization for on-line handwritten word recognition , 1994 .

[14]  Bir Bhanu,et al.  Closed-loop object recognition using reinforcement learning , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .

[16]  Jude W. Shavlik,et al.  Creating advice-taking reinforcement learners , 1998 .

[17]  Takashi Matsuyama.  Expert systems for image processing: Knowledge-based composition of image analysis processes , 1989, Comput. Vis. Graph. Image Process..

[18]  Steven A. Shafer,et al.  The Phoenix Image Segmentation System: Description and Evaluation , 1982 .

[19]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[20]  Bir Bhanu,et al.  Adaptive image segmentation using a genetic algorithm , 1989, IEEE Transactions on Systems, Man, and Cybernetics.

[21]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[22]  B. Bhanu,et al.  Image understanding research for automatic target recognition , 1993, IEEE Aerospace and Electronic Systems Magazine.

[23]  Jing Peng,et al.  Function Optimization using Connectionist Reinforcement Learning Algorithms , 1991 .

[24]  Bir Bhanu,et al.  Closed-Loop Object Recognition Using Reinforcement Learning , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Yoshua Bengio,et al.  Word normalization for online handwritten word recognition , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[26]  Bir Bhanu,et al.  Delayed reinforcement learning for adaptive image segmentation and feature extraction , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[27]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[28]  B. Bhanu,et al.  Adaptive image segmentation using genetic and hybrid search methods , 1995, IEEE Transactions on Aerospace and Electronic Systems.