A Learning Vision System for 2D Object Recognition
Proceedings of the Eighth International Joint Conference on Artificial Intelligence. Vision. Pages 1132-1134.
Abstract
The IMARS (Interactive Modeling and Automatic Recognition System) has been developed to recognize 2D objects in many kinds of images. Functionally necessary image processing programs are moduled in the library. Interactively testing the effectiveness of each program, the user can teach the system what objects should be recognized, how they are extracted from the image,what features should be measured for classifying them, and what feature values they have. The system stores what it learned in the model . Once the model is completed, the system can automatically analyze the same kind of image and recognize the expected objects in a top-down direction driven by the model. Since a model can be built for each kind of image, the systemcan analyze different kinds of images simply by changing the model.
@inproceedings{ijcai1983p263,
title = {A Learning Vision System for 2D Object Recognition},
author = {Tomita, Fumiaki},
booktitle = {Proceedings of the Eighth International Joint Conference on
Artificial Intelligence, {IJCAI-83}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Alan Bundy},
pages = {1132--1134},
year = {1983},
note = {Vision},
url = {https://ijcai.org/proceedings/1983/263},
}
TY - CPAPER TI - A Learning Vision System for 2D Object Recognition AU - Tomita, Fumiaki T2 - Proceedings of the Eighth International Joint Conference on Artificial Intelligence, IJCAI-83 PB - International Joint Conferences on Artificial Intelligence PY - 1983 SP - 1132 EP - 1134 UR - https://ijcai.org/proceedings/1983/263 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
