We propose a framework that performs action recognition and identity maintenance of multiple targets simultaneously. Instead of first establishing tracks using an appearance mode...
Image correction is discussed for realizing both effective object recognition and realistiic image-based rendering. Three image normalizations are compared in relation with the li...
In this paper, we propose a new constructive method, based on cooperative coevolution, for designing automatically the structure of a neural network for classification. Our appro...
Recent work suggests that the human ear varies significantly between different subjects and can be used for identification. In principle, therefore, using ears in addition to the f...
A measure of stability for a wide class of pattern recognition algorithms is introduced to cope with overfitting in classification problems. Based on this concept, constructive me...