An Operator Which Locates Edges in Digitized Pictures
Journal of the ACM (JACM)
On the optimal detection of curves in noisy pictures
Communications of the ACM
The teachable language comprehender: a simulation program and theory of language
Communications of the ACM
Learning Structural Descriptions From Examples
Learning Structural Descriptions From Examples
Human Problem Solving
Problem-Solving Methods in Artificial Intelligence
Problem-Solving Methods in Artificial Intelligence
Hi-index | 0.00 |
This paper examines the applicability of current scene analysis techniques to real world problems. The majority of the current techniques have been developed for simple scenes with straight lines, simple shapes, good contrast, and little texture. This paper shows several examples illustrating that many of these techniques are directly applicable to real world problems, particularly the schemes for finding primitive scene information. It is also shown, however, that the achievement of significant real world analysis requires further development of the representations of complex shapes and texture, decision processes specific to spatial problems and realistic control techniques that utilize every piece of available information. Finally, the concept of a full system is advocated as a paradigm that has more promise than the past piecemeal approach.