Effective face landmark localization via single deep network

2017/02/09 by Zongping Deng, Deng, Zongping, Ke Li +7
Computer Science · #Biometric Identification and Security #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face and Expression Recognition #Face recognition and analysis

paper · pdf · doi:10.48550/arxiv.1702.02719

openalex publication_date 2017/02/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we propose a novel face alignment method using single deep network (SDN) on existing limited training data. Rather than using a max-pooling layer followed one convolutional layer in typical convolutional neural networks (CNN), SDN adopts a stack of 3 layer groups instead. Each group layer contains two convolutional layers and a max-pooling layer, which can extract the features hierarchically. Moreover, an effective data augmentation strategy and corresponding training skills are also proposed to over-come the lack of training images on COFW and 300-W da-tasets. The experiment results show that our method outper-forms state-of-the-art methods in both detection accuracy and speed.

Related

• Deep Alignment Network: A convolutional neural network for robust face alignment
• Coarse-to-fine Face Alignment with Multi-Scale Local Patch Regression
• Dense Face Alignment
• Learning deep representation from coarse to fine for face alignment
• Facial Landmark Detection with Tweaked Convolutional Neural Networks