Predicting Occupation from Images by Combining Face and Body Context Information

• Main Authors: Chih-Hao Chiu, 邱志豪
• Other Authors: Wei-Ta Chu
• Format: Others
• Language: en_US
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/92504697562122918216

碩士 === 國立中正大學 === 資訊工程研究所 === 103 === Facial images embed age, gender, and other rich information that is implicitly related to occupation. In this work, we advocate that occupation prediction from a single facial image is a doable computer vision problem. We first extract visual features from multiple levels of patches and construct occupation descriptors by locality-constrained linear coding. To avoid the curse of dimensionality and overfitting, a boost strategy called multi-feature SVM is used to integrate features. Intra-class and inter-class visual variations are jointly considered in the boosting framework to further improve performance. We also employ the same framework to body context, and integrate heterogeneous information to predict occupation. In the evaluation, we verify effectiveness of predicting occupation from face, demonstrate promising performance obtained by combining face and body information, and investigate the influence of model parameters on prediction performance.