Research on Facial Feature Detection Based on Correlation Analysis

Abstract:

In order to enhance the extraction efficiency of facial feature, the paper explores a novel defect evaluation method that uses combined features and modified method classifiers to characterize and classify the defects of facial expression. It provides a good approach to implement facial expression recognition both in 2D and 3D images. Innovative methods which are aimed at reducing the computational complexity and improving the accuracy of expression recognition are proposed.The experiments result showed the proposed method achieved lower error rate than other method.

• Periodical: Advanced Materials Research (Volumes 1044-1045)
• Pages: 1489-1493
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1044-1045.1489
• Online since: October 2014
• Authors: Ming Zhou, Shu He, Yong Jun Cheng
• Keywords: Correlation Analysis, Face Detection, Feature Detection, Neural Network (NN)

References

[1] Wiskott L, Fellous J M, Kuiger N, et al. Face recognition by elastic bunch graph matching [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 775-779.

DOI: 10.1109/34.598235

[2] Liu DH, Lam KM, Shen LS. Optimal sampling of Gabor features for face recognition [J]. Pattern Recognition Letters, 2004, 25(2): 267-276.

DOI: 10.1016/j.patrec.2003.10.007

[3] Kim S, Chung ST, Jung S, et al. An improved illumination normalization based on anisotropic smoothing for face recognition[J]. International Journal of Computer Science and Engineering, 2008, 2(3): 89-95.

[4] Li M, Liu B. Research and Implementation of New Image Segmentation Method [J]. Journal of Convergence Information Technology, 2012, 7(8): 110-119.

[5] Bemardini F, Rushmeier H. The 3D model acquisition pipeline[C]/Computer Graphics Forum. Blackwell Publishers Ltd, 2002, 21(2): 149-172.

DOI: 10.1111/1467-8659.00574