∙∙Central symmetry. Power function does not only retain the negative part of the input but also is central symmetry. It enables the DCNN to distribute the centroids of the fingerprint classes uniformly in the whole space, which contributes to learning a discriminative representation. ...
To address these problems, in this study, we propose a novel domain adaptation method, referred to as discriminative invariant alignment (DIA), for image representation. DIA enriches the knowledge matrix by combining the class discriminative information of the source domain and local data structure ...
This paper presents a discriminative scale invariant feature transform (D-SIFT) based feature representation for person-independent facial expression recognition. Keypoint descriptors of the SIFT features are used to construct distinctive facial feature vectors. Kullback Leibler divergence is used for the ...
Aging variation poses a serious problem to automatic face recognition systems. Most of the face recognition studies that have addressed the aging problem are focused on age estimation or aging simulation. Designing an appropriate feature representation and an effective matching framework for age invariant...
Deep learningDiscriminative modelFeature encodingLinear regressionFacial aging variation is a major problem for face recognition systems due to large intra-personal variations caused by age progression. A major challenge is to develop an efficient, discriminative feature representation and matching framework,...
Learning 3D skeleton based representation for gesture recognition has increasingly attracted attention due to its invariance to camera viewpoint and video environment dynamics. Existing methods typically utilize absolute coordinates to extract human motion features. However, gestures are independent of the per...