Classification of trajectories—Extracting invariants with a neural network

✍ Scribed by Margit Kinder; Wilfried Brauer

• Publisher: Elsevier Science
• Year: 1993
• Tongue: English
• Weight: 626 KB
• Volume: 6
• Category: Article
• ISSN: 0893-6080
• DOI: 10.1016/s0893-6080(09)80010-5

✦ Synopsis

A neural classifier ofplanar trajectories is presented. There already exist a large variety oj classifiers that are specialized in particular invariants contained in a trajectory classification task such as position-invariance, rotation-invariance, and size-in variance. That is, there exist classifiers specialized in recognizing trajectories, e.g., independently oftheir position. The neural classifier presented in this paper is not restricted to certain invariants in a task: The neural network itself extracts the invariants contained in a classification task by assessing only the trajectories. The trajectories need to be given as a set ofpoints. No additional information must be available for training, which saves the designer from determining the needed invariants by himself. Besides its applicability to real-world problems, such a more general classifier is also cognitively plausible: In assessing trajectories for classification, human beings are able tofind class specific features no matter what kinds a/invariants they are confronted with. Invariants are easily handled by ignoring unspecific features.