Accession Number : ADA295771

Title :   Fast Object Recognition in Noisy Images Using Simulated Annealing.

Descriptive Note : Memorandum rept.,

Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s) : Betke, Margrit ; Makris, Nicholas

PDF Url : ADA295771

Report Date : DEC 1994

Pagination or Media Count : 11

Abstract : A fast simulated annealing algorithm is developed for automatic object recognition. The normalized correlation coefficient is used as a measure of the match between a hypothesized object and an image. Templates are generated on-line during the search by transforming model images. Simulated annealing reduces the search time by orders of magnitude with respect to an exhaustive search. The algorithm is applied to the problem of how landmarks, for example, traffic signs, can be recognized by an autonomous vehicle or a navigating robot. The algorithm works well in noisy, real-world images of complicated scenes for model images with high information content.

Descriptors :   *ALGORITHMS, *ROBOTS, *TEMPLATES, *RECOGNITION, *AUTOMATIC, SIMULATION, ANNEALING, MODELS, TRAFFIC, SIGNS AND SYMPTOMS, TIME, CORRELATION, COEFFICIENTS, IMAGES, SEARCHING, SELF OPERATION, VEHICLES, ONLINE SYSTEMS.

Subject Categories : Electrical and Electronic Equipment
      Numerical Mathematics
      Human Factors Engineering & Man Machine System

Distribution Statement : APPROVED FOR PUBLIC RELEASE