Abstract
We have developed a vision system which learns to recognize many kinds of two-dimensional objects in many kinds of images. Image processing program modules are classified based on functions in the library. First, the user can teach the system the way to recognize objects in the image interactively testing the effectiveness of each program by trial and error. The system stores what it learns in the long-term memory calledmodel. The model is improved by analyzing training images in the same way. Once the model is completed, the system can automatically analyze images in the same category and recognize the expected objects in a top-down way driven by the model. Since a model is built for images in each category, the system can recognize various kinds of images simply by retrieving the corresponding models.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Matsuyama T (1986) Expert systems for image processing: An overview. In: IT Young et al. (Eds.), Signal processing III. Elsevier, New York, 869–872
Michalski RS et al. (1983) Machine learning Tioga
Ramsey RG (1981) Neuroradiology with computed tomography. Saunders, Philadelphia
Tamura H et al. (1983) Design and implementation of SPI-DER-A transportable image processing software package. Computer Graphics and Image Processing, 2, 23, 273–294
Tomita F (1981) Hierarchical description of textures. Proceedings of the 7th International Joint Conference on Artificial Intelligence, 728–733
Winston PH (1975) Learning structure descriptions from Examples. In: PH Winston (Ed.), The psychology of computer vision. McGraw Hill, New York, 157–210
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Tomita, F. Interactive and automatic image recognition system. Machine Vis. Apps. 1, 59–69 (1988). https://doi.org/10.1007/BF01212312
Issue Date:
DOI: https://doi.org/10.1007/BF01212312