Author(s): NIE Jie, HUANG Lei, LI Zhen, ZHANG Jian, YAN Yan, WEI Zhi-qiang, Department of Computer Science and Technology, Tsinghua University, College of Information Science and Engineering, Ocean University of China
Pages: 129-136
Year: 2016 Issue:  11
Journal: Journal on Communications
Keyword:  portrait; visual feature; personality; privacy;
Abstract: Personalized recommendation in social media attempts to analyze the habits and personality based on the location information and pictures from the users’ comments on the public platform. This is very useful for personalized information recommendation. But from perspective of privacy protection, this will affect the privacy security. A novel human personality privacy analysis method based on portrait was proposed. By analyzing the personality model of the psychology, five visual features were proposed, including color features, texture features, shape features, Itten contrast features and expression features. Comprehensive experiments demonstrate the effectiveness of the proposed method. Further, the features analysis experiment show that the proposed features are very relevant to human personality privacy analyzing.