Dual-Feature Bayesian MAP Classification: Exploiting Temporal Information for Video-Based Face Recognition
نویسندگان
چکیده
Machine recognition of faces in video is an emerging problem. Following recent advances, conventional exemplar-based schemes and image set approaches inadequately exploit temporal information in video sequences for the classification task. In this work, we propose a new dualfeature Bayesian maximum-a-posteriori (MAP) classification method for face recognition in video sequences. Both cluster and exemplar features are extracted and unified under a compact probabilistic framework. To realize a non-parametric solution, a joint probability function is modeled using relevant similarity measures for matching these features. Extensive experiments on two public face video datasets demonstrate the good performance of our proposed method.
منابع مشابه
Recognition of Visual Events using Spatio-Temporal Information of the Video Signal
Recognition of visual events as a video analysis task has become popular in machine learning community. While the traditional approaches for detection of video events have been used for a long time, the recently evolved deep learning based methods have revolutionized this area. They have enabled event recognition systems to achieve detection rates which were not reachable by traditional approac...
متن کاملFusing cluster-centric feature similarities for face recognition in video sequences
The emergence of video has presented new challenges to the problem of face recognition. Most of the existing methods are focused towards the use of either representative exemplars or image sets to summarize videos. There is little work as to how they can be combined effectively to harness their individual strengths. In this paper, we investigate a new dual-feature approach to face recognition i...
متن کاملHybridization of Facial Features and Use of Multi Modal Information for 3D Face Recognition
Despite of achieving good performance in controlled environment, the conventional 3D face recognition systems still encounter problems in handling the large variations in lighting conditions, facial expression and head pose The humans use the hybrid approach to recognize faces and therefore in this proposed method the human face recognition ability is incorporated by combining global and local ...
متن کاملSpatio-temporal Framework and Algorithms for Video-based Face Recognition
Face recognition is one of the most active research areas in computer vision and pattern recognition, having drawn tremendous attention in the last few decades. A variety of practical applications such as biometrics, visual surveillance, multimedia retrieval and consumer electronics has greatly benefited from it. However, under unconstrained environments and complex facial variations, conventio...
متن کاملHand Gesture Recognition from RGB-D Data using 2D and 3D Convolutional Neural Networks: a comparative study
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement dynamics, represented by temporal features, have to be extracted by analyzing the total fr...
متن کامل