Estimating Attention of Faces Due to Its Growing Level of Emotions

Ravi Kant Kumar, Jogendra Garain, Dakshina Ranjan Kisku, Goutam Sanyal; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 1952-1960

In the task of attending faces in the disciplined assembly (Like in examination hall or Silent public places), our gaze automatically goes towards those persons who exhibits their expression other than the normal expression. It happens due to finding of dissimilar expression among the gathering of normal. In order to modeling this concept in the intelligent vision of computer system, hardly some effective researches have been succeeded. Therefore, in this proposal we have tried to come out with a solution for handling such challenging task of computer vision. Actually, this problem is related to cognitive aspect of visual attention. In the literature of visual saliency authors have dealt with expressionless objects but it has not been addressed with object like face which exploits expressions. Visual saliency is a term which differentiates "appealing" visual substance from others, based on their feature differences. In this paper, in the set of multiple faces, 'Salient face' has been explored based on 'emotion deviation' from the normal. In the first phase of the experiment, face detection task has been accomplished using Viola Jones face detector. The concept of deep convolution neural network (CNN) has been applied for training and classification of different facial expression of emotions. Moreover, saliency score of every face of the input image have been computed by measuring their 'emotion score' which depends upon the deviation from the 'normal expression' scores. This proposed approach exhibits fairly good result which may give a new dimension to the researchers towards the modeling of an intelligent vision system which can be useful in the task of visual security and surveillance.