Feature Extraction Without Edge Detection
Abstract
Information representation is a critical issue in machine vision. The representation strategy in the primitive stages of a vision system has enormous implications for the performance in subsequent stages. Existing feature extraction paradigms, like edge detection, provide sparse and unreliable representations of the image information. In this thesis, we propose a novel feature extraction paradigm. The features consist of salient, simple parts of regions bounded by zero-crossings. The features are dense, stable, and robust. The primary advantage of the features is that they have abstract geometric attributes pertaining to their size and shape. To demonstrate the utility of the feature extraction paradigm, we apply it to passive navigation. We argue that the paradigm is applicable to other early vision problems. Feature extraction, Structure from motion, Edge detection, Passive navigation.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 1993
- Accession Number
- ADA279842
Entities
People
- Ronal D. Chaney
Organizations
- Massachusetts Institute of Technology