Return to search

Feature Extraction Without Edge Detection

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.

Identiferoai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/6794
Date01 September 1993
CreatorsChaney, Ronald D.
Source SetsM.I.T. Theses and Dissertation
Languageen_US
Detected LanguageEnglish
Format159 p., 1640697 bytes, 2318330 bytes, application/octet-stream, application/pdf
RelationAITR-1434

Page generated in 0.002 seconds