Evidential Reasoning in Parallel Hierarchical Vision Programs
arXiv:1304.3098v13 citations
Originality Synthesis-oriented
AI Analysis
This addresses pattern recognition in vision systems, but appears incremental as it adapts an existing theory to a specific architecture.
The paper tackles the problem of visual pattern perception by adapting Dempster-Shafer theory for use in a massively parallel hierarchical system, showing that the techniques improve the system's performance in an extended example.
This paper presents an efficient adaptation and application of the Dempster-Shafer theory of evidence, one that can be used effectively in a massively parallel hierarchical system for visual pattern perception. It describes the techniques used, and shows in an extended example how they serve to improve the system's performance as it applies a multiple-level set of processes.