Regular Articles

Multiple deep convolutional neural networks averaging for face alignment

[+] Author Affiliations
Shaohua Zhang, Hua Yang, Zhouping Yin

Huazhong University of Science and Technology, State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Luoyu Road 1037, Wuhan 430074, China

J. Electron. Imaging. 24(3), 033013 (May 26, 2015). doi:10.1117/1.JEI.24.3.033013
History: Received January 9, 2015; Accepted April 30, 2015
Text Size: A A A

Abstract.  Face alignment is critical for face recognition, and the deep learning-based method shows promise for solving such issues, given that competitive results are achieved on benchmarks with additional benefits, such as dispensing with handcrafted features and initial shape. However, most existing deep learning-based approaches are complicated and quite time-consuming during training. We propose a compact face alignment method for fast training without decreasing its accuracy. Rectified linear unit is employed, which allows all networks approximately five times faster convergence than a tanh neuron. An eight learnable layer deep convolutional neural network (DCNN) based on local response normalization and a padding convolutional layer (PCL) is designed to provide reliable initial values during prediction. A model combination scheme is presented to further reduce errors, while showing that only two network architectures and hyperparameter selection procedures are required in our approach. A three-level cascaded system is ultimately built based on the DCNNs and model combination mode. Extensive experiments validate the effectiveness of our method and demonstrate comparable accuracy with state-of-the-art methods on BioID, labeled face parts in the wild, and Helen datasets.

Figures in this Article
© 2015 SPIE and IS&T

Citation

Shaohua Zhang ; Hua Yang and Zhouping Yin
"Multiple deep convolutional neural networks averaging for face alignment", J. Electron. Imaging. 24(3), 033013 (May 26, 2015). ; http://dx.doi.org/10.1117/1.JEI.24.3.033013


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

PubMed Articles
Advertisement


 

  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.