Local circular patterns for multi-modal facial gender and ethnicity classification

作者：

Highlights：

• We investigate multi-modal (2D + 3D) facial gender and ethnicity classification.

• We propose a novel local descriptor, LCP, to capture both 2D and 3D facial clues.

• LCP is more discriminative and more robust to noise than LBP-like features.

• Combing both modalities improves results in gender and ethnicity classification.

• We achieve competitive performance compared to state of the art in such tasks.

摘要

•We investigate multi-modal (2D + 3D) facial gender and ethnicity classification.•We propose a novel local descriptor, LCP, to capture both 2D and 3D facial clues.•LCP is more discriminative and more robust to noise than LBP-like features.•Combing both modalities improves results in gender and ethnicity classification.•We achieve competitive performance compared to state of the art in such tasks.

论文关键词：Soft biometrics,Multi-modal facial gender and ethnicity classification,Local descriptor,Decision level fusion

论文评审过程：Received 2 May 2013, Revised 10 May 2014, Accepted 26 June 2014, Available online 3 July 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2014.06.009