Learn More
This paper introduces a novel approach for face recognition using multiple face patterns obtained in various views for robot vision. A face pattern may change dramatically due to changes in the relation between the positions of a robot, a subject and light sources. As a robot is not generally able to ascertain such changes by itself, face recognition in(More)
This paper introduces the kernel constrained mutual sub-space method (KCMSM) and provides a new framework for 3D object recognition by applying it to multiple view images. KCMSM is a kernel method for classifying a set of patterns. An input pattern x is mapped into the high-dimensional feature space F via a nonlinear function φ, and the mapped pattern φ(x)(More)
In this paper, we propose a novel method named the Multiple Constrained Mutual Subspace Method which increases the accuracy of face recognition by introducing a framework provided by ensemble learning. In our method we represent the set of patterns as a low-dimensional subspace, and calculate the similarity between an input subspace and a reference(More)
SUMMARY In this paper, we propose a method for fast and accurate extraction of feature points such as pupils, nostrils, mouth edges, and the like from dynamic images with the purpose of face recognition. Accuracy of face extraction with these feature points used as criteria greatly affects the capabilities of face recognition methods based on pattern(More)
This paper proposes the kernel orthogonal mutual subspace method (KOMSM) for 3D object recognition. KOMSM is a kernel-based method for classifying sets of patterns such as video frames or multi-view images. It classifies objects based on the canonical angles between the nonlinear subspaces, which are generated from the image patterns of each object class by(More)
Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed , research in some branches of the field has been constrained due to the few number of stereo datasets with ground truth disparity maps available. Having available a large dataset of stereo images with(More)
This paper presents a novel algorithm for estimating stereo disparity which exploits the benefit of learning to the fullest. Given a cost volume of stereo matching, we solve the cost aggregation and disparity computation in one shot by using a classifier; we design a feature called matching cost pattern for the input which we extract from the cost volume(More)
In this paper, we propose a new image feature based on spatial co-occurrence among micropatterns, where each micropattern is represented by a Local Binary Pattern (LBP). In conventional LBP-based features such as LBP histograms, all the LBPs of micropatterns in the image are packed into a single histogram. Doing so discards important information concerning(More)