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

• Published in: EURASIP journal on image and video processing Vol. 2021; no. 1; pp. 1 - 18
• Main Authors: Li, Xiang, Liu, Jianzheng, Baron, Jessica, Luu, Khoa, Patterson, Eric
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 29.03.2021; Springer Nature B.V; SpringerOpen
• Subjects: Alignment; Artificial neural networks; Biometrics; Cameras; Comparison; Convolutional neural networks; Engineering; Evaluation; Facial alignment and landmarking; Focal length; Image Processing and Computer Vision; Pattern Recognition; Review; Signal,Image and Speech Processing; View angle; Viewing; Facial alignment and landmarking; Evaluation; Comparison; Focal length; View angle; Review; Convolutional neural networks
• ISSN: 1687-5281; 1687-5176; 1687-5281
• DOI: 10.1186/s13640-021-00549-3

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.