Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks
Top Cited Papers
- 26 August 2016
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 23 (10), 1499-1503
- https://doi.org/10.1109/lsp.2016.2603342
Abstract
Face detection and alignment in unconstrained environment are challenging due to various poses, illuminations, and occlusions. Recent studies show that deep learning approaches can achieve impressive performance on these two tasks. In this letter, we propose a deep cascaded multitask framework that exploits the inherent correlation between detection and alignment to boost up their performance. In particular, our framework leverages a cascaded architecture with three stages of carefully designed deep convolutional networks to predict face and landmark location in a coarse-to-fine manner. In addition, we propose a new online hard sample mining strategy that further improves the performance in practice. Our method achieves superior accuracy over the state-of-the-art techniques on the challenging face detection dataset and benchmark and WIDER FACE benchmarks for face detection, and annotated facial landmarks in the wild benchmark for face alignment, while keeps real-time performance.Keywords
Funding Information
- External Cooperation Program of BIC
- Chinese Academy of Sciences (172644KYSB20160033, 172644KYSB20150019)
- Shenzhen Research Program (KQCX2015033117354153, JSGG20150925164740726, CXZZ20150930104115529, CYJ20150925163005055, JCYJ201 60510154736343)
- Guangdong Research Program (2014B050505017, 2015B010129013)
- Natural Science Foundation of Guangdong Province (2014A030313688)
- Key Laboratory of Human Machine Intelligence-Synergy Systems
- Chinese Academy of Sciences
This publication has 20 references indexed in Scilit:
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- From Facial Parts Responses to Face Detection: A Deep Learning ApproachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- A deep pyramid Deformable Part Model for face detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- A convolutional neural network cascade for face detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face AlignmentLecture Notes in Computer Science, 2014
- Joint Cascade Face Detection and AlignmentLecture Notes in Computer Science, 2014
- Face Alignment by Explicit Shape RegressionInternational Journal of Computer Vision, 2013
- Pose-Free Facial Landmark Fitting via Optimized Part Mixtures and Cascaded Deformable Shape ModelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Robust Face Landmark Estimation under OcclusionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Active appearance modelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001