샘플 클러스터링에 의한 규칙 학습 = Learning Rules Based on Sample Clustering

다국어 초록 (Multilingual Abstract)

Expertise of recognizing an object despite of every possible occlusions among objects is difficult to be provided directly to a system. In this paper, we propose a method for inferring inherent shape-characteristics of an object from training views provided. The method learns rules incrementally by alternating the rule induction process form limited number of training views and the rule verification process from the following training views. The learned rules are represented using logical expressions to enhance the readability. The proposed method is tested by simulating occlusions on 2-dimensional objects to examine the learning process and to show improvement of recognition rate. The results show that it can be applied to a practical system for 3-dimensional object recognition.