Uncertainty Reduction Paradigm Using Structural Knowledge in Line-Drawing Understanding

Ariki, Yasuo; Morimoto, Masashi; Sakai, Toshiyuki

Uncertainty Reduction Paradigm Using Structural Knowledge in Line-Drawing Understanding

Yasuo Ariki, Masashi Morimoto, Toshiyuki Sakai

Download BibTeX Cite

Proceedings of the Tenth International Joint Conference on Artificial Intelligence. Perception. Pages 783-785.

Abstract

In this paper, we investigate the problem of interpretation uncertainty caused by the conventional deterministic approaches to drawing image understanding from the three view points of homograph, heuristic knowledge and data ambiguity. To reduce these three factors of uncertainties, we propose new paradigm with context-sensitive and hierarchical interpretation for homograph, multiple-interpretation for heuristic knowledge, and fmally a certainty factor for data ambiguity. The validity of this paradigm is investigated by establishing a structure analysis system for drawing images with five hierarchical levels. The interpretation proceeds from the lower level to the higher level in bottom-up manner using heuristic knowledge described as rules in a production system. The heuristic knowledge is effectively used to compute or modify the certainty factor of multipleinterpretation in context-sensitive manner.

Yasuo Ariki, Masashi Morimoto, and Toshiyuki Sakai. 1987. Uncertainty Reduction Paradigm Using Structural Knowledge in Line-Drawing Understanding. In Proceedings of the Tenth International Joint Conference on Artificial Intelligence, IJCAI-87. IJCAI, 783–785. https://ijcai.org/proceedings/1987/160

@inproceedings{ijcai1987p160,
  title     = {Uncertainty Reduction Paradigm Using Structural Knowledge in Line-Drawing Understanding},
  author    = {Ariki, Yasuo and Morimoto, Masashi and Sakai, Toshiyuki},
  booktitle = {Proceedings of the Tenth International Joint Conference on
               Artificial Intelligence, {IJCAI-87}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {John McDermott},
  pages     = {783--785},
  year      = {1987},
  note      = {Perception},
  url       = {https://ijcai.org/proceedings/1987/160},
}

TY  - CPAPER
TI  - Uncertainty Reduction Paradigm Using Structural Knowledge in Line-Drawing Understanding
AU  - Ariki, Yasuo
AU  - Morimoto, Masashi
AU  - Sakai, Toshiyuki
T2  - Proceedings of the Tenth International Joint Conference on Artificial Intelligence, IJCAI-87
PB  - International Joint Conferences on Artificial Intelligence
PY  - 1987
SP  - 783
EP  - 785
UR  - https://ijcai.org/proceedings/1987/160
ER  -