This Article 
 Bibliographic References 
 Add to: 
A Flexible Vision-Based Algorithm for a Book Sorting System
May 1988 (vol. 10 no. 3)
pp. 393-399

A flexible vision-based algorithm for a book sorting system is presented. The algorithm is based on a discrimination model that is adaptively generated for the current object classes by learning. The algorithm consists of an image normalization process, a feature element extraction process, a learning process, and a recognition process. The image normalization process extracts the contour of the object in an image, and geometrically normalizes the image. The feature extraction process converts the normalized image to the pyramidal representation, and the feature element is extracted from each resolution level. The learning process generates a discrimination model, which represents the differences between classes, based on hierarchical clustering. In the recognition process, the input images are hierarchically discriminated under the control of the decision tree. To evaluate the algorithm, a simulation system was implemented on a general-purpose computer and an image processor was developed.

[1] T. Ozaki, T. Gotoh, T. Toriu, and M. Yoshida, "Automatic visual inspection system for industrial printing," inProc. SPIE Cambridge Symp. Advances in Intelligent Robotics Systems, 1986, pp. 730-733.
[2] H. Iwase, T. Mima, and T. Toriu, "Automatic verification of seal impression," inProc. IEE 2nd Int. Conf. Image Processing and Its Applications, 1986, pp. 25-29.
[3] T. Toriu, T. Gotoh, and M. Yoshida, "An investigation of adaptable vision system for factory automation," inProc. IEEE Computer Vision and Pattern Recognition, 1985, pp. 222-224.
[4] M. L. Baird, "SIGHT-I: A computer vision system for automatic IC chip manufacture,"IEEE Trans. Syst., Man, Cybern., vol. SMC-8, no. 2, pp. 133-139, 1978.
[5] H. Harada, Y. Itoh, and M. Ishii, "Recognition of freehand drawings in chemical plant engineering," inProc. IEEE Workshop Computer Architecture for Pattern Analysis and Image Database Management, 1985, pp. 146-153.
[6] A. Kulkarni and L. Kanal, "An optimization approach to hierarchical classifier design," inProc. 3rd IJCPR, 1976, pp. 459-466.
[7] O. Argentiero, R. Chin, and P. Beaudet, "An automated approach to the design of decision tree classifiers,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-4, pp. 51-57, 1982.
[8] T. Hai, Y. Kabuyama, and E. Yamamoto, "A method for handwritten Knji character recognition: Recognition method by multiple standpoint and particular shape extraction" (in Japanese),Trans. Inst. Electron. Commun. Eng. Japan, vol. J68-D, no. 4, pp. 773-780, 1985.
[9] S. L. Tanimoto and T. Pavlidis, "A hierarchical structure for picture processing,"Comput. Graphics Image Processing, vol. 4, pp. 104- 119, 1975.
[10] J. T. Tou, "Feature selection for pattern recognition systems," inMethodologies of Pattern Recognition, S. Watanabe, Ed. New York: Academic, 1969.
[11] T. Gotoh, T. Toriu, and E. Yamamoto, "Analysis of median filter characteristics and its application to contour extraction," inProc. IEEE 7th ICPR, 1984, pp. 1098-1099.
[12] R. O. Duda and P. E. Hart,Pattern Classification and Scene Analysis. New York: Wiley-Interscience, 1973.

Index Terms:
computerised picture processing; computerised pattern recognition; computer vision; flexible vision-based algorithm; book sorting system; image normalization; feature element extraction; learning process; discrimination model; hierarchical clustering; computer vision; computerised pattern recognition; computerised picture processing; learning systems
T. Gotoh, T. Toriu, S. Sasaki, M. Yoshida, "A Flexible Vision-Based Algorithm for a Book Sorting System," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, no. 3, pp. 393-399, May 1988, doi:10.1109/34.3903
Usage of this product signifies your acceptance of the Terms of Use.