Kohtaro Sabe

TL;DR: In this paper, a facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided.

TL;DR: In this paper, an obstacle recognition system is presented which can recognize an obstacle by accurately extracting a floor surface from the ground-contact plane of a robot by using a disparity image and homogeneous transform matrix.

TL;DR: In this article, a robot includes a face extraction unit for extracting a feature of a face contained in an image picked up by a CCD camera and a face recognition unit for recognizing a face according to the face extraction result obtained by the face extract unit.

TL;DR: In this paper, a robot that discriminates human faces is hierarchically arranged in a tree structure, where each node has a number of weak classifiers and each node learns face images associated with one label.

TL;DR: In this paper, a face image processing apparatus selects feature points and feature for identifying a person through statistical learning, which includes input means for inputting face image detected by arbitrary face detection means, face parts detection means for detecting the positions of face parts in several locations from the input face image, face pose estimation means for estimating face pose based on the detected positions of the face parts, feature point position correcting means for correcting the position of each feature point used for identifying the person based on a result of estimation of face pose by the face estimation means, and face identifying means for identifying