Robust FEC-CNN: A High Accuracy Facial Landmark Detection System

Zhenliang He, Jie Zhang, Meina Kan, Shiguang Shan, Xilin Chen; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 98-104

Facial landmark detection is a typical and crucial task in computer vision widely used in face recognition, facial expression analysis, etc. In this work, we propose an effective facial landmark detection system, recorded as Robust FEC-CNN (RFC), which achieves impressive results on facial landmark detection in the wild. Considering the favorable ability of deep convolutional neural network, we resort to FEC-CNN as a basic method to characterize the complex nonlinearity from face appearance to shape. Moreover, face bounding box invariant technique is adopted to reduce the landmark localization sensitivity to the face detector while model ensemble strategy is adopted to further enhance the landmark localization performance. We participate the Menpo Facial Landmark Localisation in-the-Wild Challenge and our RFC significantly outperforms the baseline approach APS. Extensive experiments on Menpo Challenge dataset and IBUG dataset demonstrate the superior performance of the proposed RFC.