Year: 2007
Type: conference-paper
Abstract: Service robots need object recognition strategy that can work on various objects in complex backgrounds. Since no single method can work in every situation, we need to combine several methods so that the robots can use the appropriate one automatically. In this paper we propose a scheme to classify situations depending on the characteristics of object of interest and user demand. We classify the situations into four categories and employ different techniques for each one. We use SIFT, kernel PCA (KPCA) in conjunction with Support Vector Machine (SVM) using intensity and Gabor feature for four categories. We show that use of intensity feature or Gabor feature is important for the use of KPCA based techniques on different kinds of objects. Through our experiments, we show that by using our categorization scheme a service robot can select appropriate feature in kernel PCA based techniques and improve its recognition performance considerably. 1
Authors: Al Mansur, Yoshinori Kuno
Institution: Saitama University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W94904131