Direction Coding Method And Its Application To Scene Analysis
Proceedings of the Fourth International Joint Conference on Artificial Intelligence. Visual Information Processing. Pages 620-626.
Abstract
In order to cope with image signal variations in imaging devices, a direction coding method is proposed for stable scene analysis and object recognition. This method makes extensive use of macroscopic processing of direction-coded images to achieve noise-free analysis. Examples showing recognition of obliquely-imaged box-like objects whose surfaces are rather complicated are included. Additional efforts are made to recognize surface information of objects by spatially transforming the surface image as if it were viewed from a vertical direction. This method also involves positioninvariant and rotation-invariant image data transformation techniques, thus raising the possibility of more effective image analysis in actual application.
@inproceedings{ijcai1975p97,
title = {Direction Coding Method And Its Application To Scene Analysis},
author = {Ejirl, M. and Yode, H. and Motolke, J.},
booktitle = {Proceedings of the Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-75}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Patrick Winston and Carl Hewitt},
pages = {620--626},
year = {1975},
note = {Visual Information Processing},
url = {https://ijcai.org/proceedings/1975/97},
}
TY - CPAPER TI - Direction Coding Method And Its Application To Scene Analysis AU - Ejirl, M. AU - Yode, H. AU - Motolke, J. T2 - Proceedings of the Fourth International Joint Conference on Artificial Intelligence, IJCAI-75 PB - International Joint Conferences on Artificial Intelligence PY - 1975 SP - 620 EP - 626 UR - https://ijcai.org/proceedings/1975/97 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
