计算机应用 ›› 2018, Vol. 38 ›› Issue (11): 3193-3198.DOI: 10.11772/j.issn.1001-9081.2018041274

• 第七届中国数据挖掘会议(CCDM 2018) • 上一篇    下一篇

基于极端学习机的人脸特征深度稀疏自编码方法

张欢欢, 洪敏, 袁玉波   

  1. 华东理工大学 信息科学与工程学院, 上海 200237
  • 收稿日期:2018-04-30 修回日期:2018-06-16 出版日期:2018-11-10 发布日期:2018-11-10
  • 通讯作者: 袁玉波
  • 作者简介:张欢欢(1968-),女,山东济南人,副教授,博士,主要研究方向:机器学习、数据挖掘、程序正确性验证、知识图谱;洪敏(1989-),女,山东菏泽人,硕士研究生,主要研究方向:数据挖掘、机器学习;袁玉波(1976-),男,云南宣威人,副教授,博士,主要研究方向:机器学习、数据科学、数据质量评估、数据挖掘。
  • 基金资助:
    国家自然科学基金资助项目(61001200);上海市科研计划项目(17DZ1101003)。

Deep sparse auto-encoder method using extreme learning machine for facial features

ZHANG Huanhuan, HONG Min, YUAN Yubo   

  1. College of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
  • Received:2018-04-30 Revised:2018-06-16 Online:2018-11-10 Published:2018-11-10
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61001200), the Scientific Research Project of Shanghai (17DZ1101003).

摘要: 针对输入人脸特征的不准确性导致识别系统识别率不高的问题,提出了一种有效的基于极端学习机(ELM)的人脸特征深度稀疏自编码(DSAE)方法。首先,利用截断式核范数构造损失函数,通过最小化损失函数提取人脸图像的稀疏特征;其次,利用极端学习机自编码器(ELM-AE)模型进行人脸特征的自编码,实现数据维度的降低以及噪声过滤;最后,通过经验风险极小化得到最优的深度结构。在ORL、IMM、Yale和UMIST人脸数据集上的实验结果表明,DSAE方法对高维人脸图像的识别率明显优于极端学习机、随机森林(RF)等算法,且具有良好的泛化性能。

关键词: 人脸图像, 极端学习机, 自编码器, 截断式核范数正则化, 稀疏特征

Abstract: Focused on the problem of low recognition in recognition systems caused by the inaccuracy of input features, an efficient Deep Sparse Auto-Encoder (DSAE) method using Extreme Learning Machine (ELM) for facial features was proposed. Firstly, truncated nuclear norm was used to construct loss function, and sparse features of face images were extracted by minimizing loss function. Secondly, self-encoding of facial features was used by Extreme Learning Machine Auto-Encoder (ELM-AE) model to achieve data dimension reduction and noise filtering. Thirdly, the optimal depth structure was obtained by minimizing the empirical risk. The experimental results on ORL, IMM, Yale and UMIST datasets show that the DSAE method not only has higher recognition rate than ELM, Random Forest (RF), etc. on high-dimensional face images, but also has good generalization performance.

Key words: face image, Extreme Learning Machine (ELM), auto-encoder, Truncated Nuclear Norm Regularization (TNNR), sparse feature

中图分类号: