This paper presents a novel approach in a rarely studied area of computer vision: Human interaction recognition in still images. We explore whether the facial regions and their spatial configurations contribute to the recognition of interactions. In this respect, our method involves extraction of several visual features from the facial regions, as well as incorporation of scene characteristics and deep features to the recognition. Extracted multiple features are utilized within a discriminative learning framework for recognizing interactions between people. Our designed facial descriptors are based on the observation that relative positions, size and locations of the faces are likely to be important for characterizing human interactions. Since there is no available dataset in this relatively new domain, a comprehensive new dataset which includes several images of human interactions is collected. Our experimental results show that faces and scene characteristics contain important information to recognize interactions between people.

No abstract

No abstract

No abstract

With the recent development of the technology, it is seen that there is a significant increase in the studies on the analysis of human faces. Through the automatic analysing of the faces, it is possible to know the gender, emotional state, and even the identity of the people from an image. Of them, identity or face recognition has became the most important task which has been studied for a long time now as it is crucial to take measurement for public security, credit card verification, criminal identification, and the like. In this study, we have proposed an evolutionary-based framework that relies on genetic programming algorithm to evolve a binary-and multi-label image classifier program for gender classification, facial expression recognition, and face recognition tasks. The performance of the evolved programs has been compared with convolutional neural network, one of the most popular deep learning algorithms. The comparative results show that the proposed framework could better performance than the competitor algorithm. Therefore, it has been introduced to the research community as a new binary-and multi-label image classifier framework.