Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (10): 2788-2793.DOI: 10.11772/j.issn.1001-9081.2018041068

Previous Articles     Next Articles

Unconstrained face verification based on 3D frontalization and similarity learning

XU Xin, LIANG Jiuzhen   

  1. College of Information Science & Engineering, Changzhou University, Changzhou Jiangsu 213164, China
  • Received:2018-03-20 Revised:2018-05-16 Online:2018-10-10 Published:2018-10-13
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61170121), the Social Development Project for Public Welfare Technology Research of Zhejiang Province (2017C33223).


徐昕, 梁久祯   

  1. 常州大学 信息科学与工程学院, 江苏 常州 213164
  • 通讯作者: 梁久祯
  • 作者简介:徐昕(1995-),女,江苏泰州人,硕士研究生,主要研究方向:人工智能、图像处理、人脸识别;梁久祯(1968-),男,山东泰安人,教授,博士,主要研究方向:人工智能。
  • 基金资助:

Abstract: Focusing on the problems of small samples, large face pose changes, occlusion and complex background, under unconstrained condition, a face verification method based on 3D frontalization and similarity learning was proposed. Firstly, the 3D frontalization progress was applied to generate the frontal face of the face image. Secondly, the complex background was removed by cropping the relevant face regions. Finally, a similarity learning method based on intra-personal subspace was applied to measure the similarity of the image pairs. Experiments were conducted on several databases that were built up by preprocessing the Labeled Faces in the Wild (LFW) database. the difference between these databases and original LFW is their images have been preprocessed. In the experiment with Local Ternary Pattern (LTP) descriptor as the feature extraction method and 625 training image pairs, the recognition rate of the proposed algorithm Similarity Learning over subspace (sub-SL) was 15.6% and 8.4% higher than that of Metric Learning over subspace (sub-ML) and Similarity Metric Learning over subspace (sub-SML) respectively. Experimental results show that the proposed algorithm can effectively improve the accuracy of face verification under unconstrained conditions.

Key words: unconstrained image, face verification, 3D face frontalization, similarity learning, metric learning

摘要: 针对无约束条件下的人脸图像样本少、面部姿态变化大、被遮挡以及背景复杂等问题,提出一种结合三维人脸矫正与相似性学习相结合的人脸验证算法(sub-SL)。首先,通过三维人脸矫正方法对人脸图像进行姿态矫正,将图像中的人脸矫正为标准正面脸;其次,裁剪该正面脸的脸部相关区域,去除复杂的图像背景;最后,利用基于个体子空间的相似性学习方法对图像对之间的相似度进行度量,完成人脸验证。实验采用了几个以LFW(Labeled Faces in the Wild)数据库为基础的经过预处理操作(例如人脸矫正、裁剪等)后建立起来的数据库。在基于局部三值模式(LTP)的特征提取方法并且训练图像对数为625的实验中,sub-SL算法的识别率比利用马氏距离进行度量学习的算法sub-ML以及结合了马氏距离与相似性学习的度量学习算法sub-SML分别高出了15.6%和8.4%。实验结果表明,sub-SL算法能够有效提高无约束条件下人脸识别的准确率。

关键词: 无约束图像, 人脸验证, 三维人脸矫正, 相似性学习, 度量学习

CLC Number: