Tensor Flow-Based Automatic Personality Recognition used in Asynchronous Video Interviews

Abstract: In this project, we propose a stress recognition algorithm using face images and face landmarks. In the case of stress recognition using a biological signal or thermal image, which is being studied a lot, a device for acquiring the corresponding information is required. In order to remedy this shortcoming, we proposed an algorithm that can recognize behavior of the person from images of video acquired with a general camera. We also designed a deep neural network that receives facial landmarks as input to take advantage of the fact that eye, mouth, and head movements are different from normal situations when a person is stressed and also we can identify the behavior of the particular candidate attending a online interview, there will conclude that whether the particular candidate is eligible or not. Experimental results show that the proposed algorithm recognizes behavior more effectively.

Keywords: Convolutional Neural Network (CNN), Personality Recognition, TensorFlow, OpenCV, HAAR Cascade