2016 3rd International Conference on Information Science and Control Engineering (ICISCE 2016)

93 / 2016-04-12 10:39:08

Self-taught learning features for human action recognition

9811

Human action recognition has been a topic question in computer vision with its application in robotics, video surveillance, human-computer interaction, user interface design and multimedia video retrieval. But it is also a challenge work for the complex of feature extracting and limited labeled data. Previous feature extracting approaches are almost manual features, such as HOG, SIFT, HOF and so on. These manual features receive significant results in some specific applications. But algorithm generality is a problem. And they need mass of labeled data to training for recognition. So in this paper, we propose self-taught learning features and unsupervised learning pre-processing. In this method, we extract feature through unsupervised self-taught with large group of unlabeled data, then fine-turning with small number of labeled data. And the Soft max regression can classify and recognition human action. Experiments demonstrate that our method can receive outperform results.