Fast Object Recognition in Noisy Images Using Simulated Annealing

A fast simulatedannealingalgorithmis developed for automatic object recognition. The object recognition problem is addressed as the problem of best describing a match between a hypothesized object and an image. The normalized correlation coe cient is used as a measure of the match. 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, tra c signs, can be recognized by an autonomous vehicle or a navigating robot. Images are assumed to be taken while the robot or the vehicle is moving through its environment. It tries to match them with templates created online from models stored in a database. We illustrate the performance of our algorithm with real-world images of complicated scenes with tra c signs. False positive matches occur only for templates with very small information content. To...

• Type: Conference
• Year: 1995
• Where: ICCV
• Authors: Margrit Betke, Nicholas C. Makris
• Keywords: Computer Vision, False Positive Matches, ICCV 1995, Model Images, Object Recognition