A Multi-Level Perception Approach to Reading Cursive Script
Proceedings of the Tenth International Joint Conference on Artificial Intelligence. Perception. Pages 844-846.
Abstract
Reading cursive script involves elements of visual perception at one level of processing and those of language perception and understanding at a higher level. The problem is approached as one in which a word image is transformed through a representational hierarchy of levels based on descriptions that use points, contours, features, letters, and words. Global control is hierarchical until an intermediate level after which it is heterarchical. Two modes of learning are defined: supervised training with user feedback and unsupervised adaptation to the writer.
@inproceedings{ijcai1987p177,
title = {A Multi-Level Perception Approach to Reading Cursive Script},
author = {Srihari, Sargur N. and Bozinovic, Radmilo M.},
booktitle = {Proceedings of the Tenth International Joint Conference on
Artificial Intelligence, {IJCAI-87}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {John McDermott},
pages = {844--846},
year = {1987},
note = {Perception},
url = {https://ijcai.org/proceedings/1987/177},
}
TY - CPAPER TI - A Multi-Level Perception Approach to Reading Cursive Script AU - Srihari, Sargur N. AU - Bozinovic, Radmilo M. T2 - Proceedings of the Tenth International Joint Conference on Artificial Intelligence, IJCAI-87 PB - International Joint Conferences on Artificial Intelligence PY - 1987 SP - 844 EP - 846 UR - https://ijcai.org/proceedings/1987/177 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
