Evaluating effects of focal length and viewing angle in a comparison of recent face landmark and alignment methods

EURASIP Journal on Image and Video Processing

Jianzheng Liu¹  Khoa Luu²  Eric Patterson³  Xiang Li³  Jessica Baron³ 

[1] College of Computer Science & Information Engineering, Tianjin University of Science & Technology, 13th St, Binhai Xinqu, 300457, Tianjin, China;Department of Computer Science and Computer Engineering, University of Arkansas, JBHT #521, 72701, Fayetteville, AR, USA;School of Computing, Clemson University, 304 McAdams Hall, 29630, Clemson, SC, USA;

关键词: Facial alignment and landmarking;    Convolutional neural networks;    Focal length;    View angle;    Comparison;    Evaluation;    Review;   

DOI  :  10.1186/s13640-021-00549-3

来源: Springer

【 摘 要 】

Recent attention to facial alignment and landmark detection methods, particularly with application of deep convolutional neural networks, have yielded notable improvements. Neither these neural-network nor more traditional methods, though, have been tested directly regarding performance differences due to camera-lens focal length nor camera viewing angle of subjects systematically across the viewing hemisphere. This work uses photo-realistic, synthesized facial images with varying parameters and corresponding ground-truth landmarks to enable comparison of alignment and landmark detection techniques relative to general performance, performance across focal length, and performance across viewing angle. Recently published high-performing methods along with traditional techniques are compared in regards to these aspects.

【 授权许可】

CC BY