Abstract
An image-recognition system was implemented with a set of eight algorithmically dedicated integrated circuits to recognize two-dimensional objects that are characterized by their closed outer contours. The complete system operates at rates up to 15 frames/second using a standard workstation as a controller. The recognition system achieved a 97% recognition rate for over 10,000 trials of recognition of eight objects over a wide range of orientation and size variations. A 100% recognition rate was achieved if size variations were eliminated. The set of 4-micron NMOS image processor chips operates on 10-megahertz 8-bit video data (512 × 512 images) in real time. The processors include: a 3 × 3 linear convolver, a 3 × 3 sorting filter, a 7 × 7 logical convolver, a contour tracer, a feature extractor, a look-up table ROM, and two post-processors for the linear convolver. Each chip was designed using an architecture that is dedicated to the particular image processing task being performed. The design time for all of the chips was kept to 1.5 man-years by developing a set of design guidelines. The relationship between the algorithms that were implemented and the silicon implementation is discussed.
Similar content being viewed by others
References
Bandyopadhyay A (Oct 1984) Interest points, disparities, and correspondence. Proceedings of the Image Understanding Workshop: 184–187, DARPA
Barnard ST et al (June 1983) Three-dimensional shape from line drawings. Proceedings of the Image Understanding Workshop: 282–284, DARPA
Demassieux N et al (1985) VLSI architecture for a onechip video median filter. Proceedings of ICASSP: International Conference on Acoustics Speech and Signal Processing 26.7.1–26.7.4
Gonzalez RC, Wintz P (1977) Digital Image Processing. Addison-Wesley, Reading, Mass: p 352
Granlund GH (Feb 1972) Fourier preprocessing for hand print character recognition. IEEE Trans. Computers C-21: 195–201
Healy G, Sanz JLC (Jan 1985) CONTAM: An edge-based approach to segmenting images with irregular objects. IBM Research Report, Almeden Research Center
Hu M-K (1962) Visual pattern recognition by moment invariants. IRE Transactions of Information Theory IT-8: 179–187
Kavaler R et al (Mar 1984) A dynamic time warp IC for a one-thousand word recognition system. Proceedings of ICASSP 2: 25B.6.1–25B.6.4
Ketonen J (June 1983) Deducing facts about scenes from images. Proceedings of the Image Understanding Workshop: 182–183
Kitchin PW et al (1983) Processing of binary images. In: Robot Vision. IFS Ltd, UK, London
Magee M (June 1985) A rule-based system for pattern recognition that exploits topological constraints. Proceedings of the CVPR 85: 62–67
Narendra PM (1985) A separable median filter for image noise smoothing. In: Digital Image Processing and Analysis. Vol 1: Digital Image Processing: 450–459, IEEE Computer Society, Los Angeles
Petajan ED (June 1985) Automatic lipreading to enhance speech recognition. Proceedings of the CVPR 85: 40–47
Pratt WK (1978a) Digital Image Processing. Wiley, New York: p 526
Ruetz P (May 1986) Architectures and Design Techniques for Real-Time Image Processing ICs. UCB/ERL Memorandum No. M86/37, Berkeley, Calif
Ruetz P, Brodersen R (Feb 1986) A real-time imageprocessing chip set. IEEE International Solid State Circuits Conference Digest of Technical Papers: 148–149
Ruetz P, Jain R, Shunc C, Rabast J, Jacobs G, Broderson R (May 1986) Automatic layout generation of real-time digital image-processing circuits. 1986 Custom Integrated Circuits Conference Proceedings: 111–115
Skolnick MM (June 1985) Automatic comparison of 2-D electrophoretic gels. Proceedings of the CVPR 85: 48–54
Weymouth TE et al (June 1983) Rule-bases strategies for image interpretation. Proceedings of the Image Understanding Workshop: 193–202
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Ruetz, P.A., Brodersen, R.W. An image-recognition system using algorithmically dedicated integrated circuits. Machine Vis. Apps. 1, 3–22 (1988). https://doi.org/10.1007/BF01212309
Issue Date:
DOI: https://doi.org/10.1007/BF01212309