1. Enhanced face alignment using an unsupervised roll estimation initialization
- Author
-
Li, Cheng, Pourtaherian, Arash, Tjon A Ten, W.E., de With, Peter H.N., Zhou, Jianhong, Radeva, Petia, Nikolaev, Dmitry P., Verikas, Antanas, Video Coding & Architectures, and Center for Care & Cure Technology Eindhoven
- Subjects
Landmark ,business.industry ,Computer science ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Initialization ,Pattern recognition ,02 engineering and technology ,Blob detection ,Random forest ,Support vector machine ,03 medical and health sciences ,0302 clinical medicine ,Minimum bounding box ,Feature (computer vision) ,Face (geometry) ,landmark localization ,030221 ophthalmology & optometry ,0202 electrical engineering, electronic engineering, information engineering ,B-spline model ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,unsupervised roll-angle estimation - Abstract
We propose a novel and efficient initialization method for generalized facial landmark localization with an unsupervised roll-angle estimation based on B-spline models. We first show that the roll angle is crucial for an accurate landmark localization. Therefore, we develop an unsupervised roll-angle estimation by adopting a joint 1 st -order B-spline model, which is robust to intensity variations and generic for application to various face detectors. The method consists of three steps. First, the scaled-normalized Laplacian of Gaussian operator is applied to a bounding box generated by a face detector for extracting facial feature segments. Second, a joint 1 st -order B-spline model is fitted to the extracted facial feature segments, using an iterative optimization method. Finally, the roll angle is estimated through the aligned segments. We evaluate four state-of-the-art landmark localization schemes with the proposed roll-angle estimation initialization in the benchmark dataset. The proposed method boosts the performance of landmark localization in general, especially for cases with large head pose. Moreover, the proposed unsupervised roll-angle estimation method outperforms the standard supervised methods, such as random forest and support vector regression by 41.6% and 47.2%, respectively.
- Published
- 2019