期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2019
卷号：19
期号：11
页码：151-155
出版社：International Journal of Computer Science and Network Security
摘要：Recognizing human actions based on still-images is a challenging task involving predictions on human interaction with objects and body postures. In this paper, a novel method is proposed in which three networks are used to determine human pose, most relatable object in the scene and the overall scenario that includes actors and all objects around him. Before testing the proposed method the performance of the conventional transfer learning method is evaluated by four popular pre-trained convolutional neural networks for feature extraction and classification is performed by the Support vector machine, only principal components of extracted features are passed through SVM for predicting human action in the scene. To evaluate the proposed model Stanford40 dataset is used, the dataset contains images of 40 human actions and every image has a bounding box of the person performing the action. There is a total of 9532 images with 180-300 images per class, for the experiment only 10 classes of the dataset are used for proposed model evaluation. Experimental results show a proposed method in the paper achieves high robustness and accuracy.
关键词：convolutional neural networks; transfer learning; support vector machine.
