Human-robot interaction based on Haar-like features and eigenfaces

• DOI: 10.1109/robot.2004.1308099
• Publication Date: 2004-09-07T10:26:45Z
• Authors: J. Barreto; P. Menezes; J. Dias
• Keywords: Eigenface

This paper describes a machine learning approach for visual object detection and recognition which is capable of processing images rapidly achieving high rates. framework demonstrated on, in part motivated by, the task human-robot interaction. There are three main parts on this framework. The first person's face used as preprocessing system to second stage person interacting with robot, third one hand detection. technique based Haar-like features introduced by Viola et al. then improved Lienhart eigenimages PCA system. Used real-time interaction applications able detect recognise faces at 10.9 frames per PIV 2.2 GHz equipped USB camera.