Iterative local re-ranking with attribute guided synthesis for face sketch recognition

作者：

Highlights：

• An attribute guided face sketch synthesis method is used to generate images with varying local characteristic, which could eliminate the face perception biases.

• To the best of our knowledge, it is the first exploration to introduce re-ranking technique for face sketch recognition.

• The proposed iterative local re-ranking method is designed to integrate the inherent local invariant information of face sketches.

• The proposed re-ranking method is effective on multiple face sketch databases and achieves superior performance compared with the state-of-the-art methods.

摘要

•An attribute guided face sketch synthesis method is used to generate images with varying local characteristic, which could eliminate the face perception biases.•To the best of our knowledge, it is the first exploration to introduce re-ranking technique for face sketch recognition.•The proposed iterative local re-ranking method is designed to integrate the inherent local invariant information of face sketches.•The proposed re-ranking method is effective on multiple face sketch databases and achieves superior performance compared with the state-of-the-art methods.

论文关键词：Face sketch recognition,Facial attribute,Re-ranking

论文评审过程：Received 2 August 2019, Revised 25 March 2020, Accepted 4 August 2020, Available online 5 August 2020, Version of Record 11 August 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107579