CASIA OpenIR  > 毕业生  > 博士学位论文
非控场景下人脸分析关键问题研究
曹冬
学位类型工学博士
导师谭铁牛 ; 孙哲南 ; 赫然
2016-05-29
学位授予单位中国科学院研究生院
学位授予地点北京
关键词非控场景 视频 人脸识别 哈希 性别识别 多角度聚类
其他摘要

       人脸分析是一种具有广泛潜在应用的生物识别技术。在互联网金融、安防监控、考勤等众多身份认证领域得到了使用,受到研究者们广泛关注。目前,在可控环境下,人脸分析相关任务已经达到了比较满意的效果。然而在非控环境下,由于受到光照、姿态、表情、分辨率等非可控因素影响,人脸相关任务的性能依然很差,无法满足实际应用的要求。本论文主要针对非控场景下人脸分析的几个关键问题展开研究,并针对相关的问题提出了相应的解决办法。主要创新点如下:
       1.针对视频人脸识别问题, 提出了一种联合空间学习的算法,它同时从视频中发现最具有代表性的样本和具有判别能力的特征。我们将这个联合空间学习描述成一个同时针对列(样本)和行(特征)的矩阵最小化问题。然后我们提出了一种循环最优化算法来逐步地降低联合损失函数。同时我们使用随机化技术来获取数据中的非线性结构,通过这种方式准确率和性能都获得了提升。
       2.针对图像集人脸识别效率问题,提出了学习图像集的具有判别性和紧凑性的二值化表达。为了达到这个目的,本文将Hadamard二值码嵌入到哈希函数中。Hadamard 码不仅可以提供监督信息同时也可以促使目标函数生成满足某些信息论准则的高质量编码。同时使用低秩约束来达到压缩图像集的目的,实验结果证明这种方式可以有效地降低每个图像集的冗余性。最后我们引入一个基于核的方法来进一步的提升算法的性能。
      3.针对非控场景下的性别识别问题, 构造了一种多阶局部二值特征提取人脸中丰富信息,具体来说,通过三种不同统计方式来获取具有互补关系的特征,即 像素、区域均值、区域方差。这使得特征描述子的表达能力更加丰富。同时开发了一种局部增强学习算法来联合学习三个局部分类器,从而提升算法的分类性能。通过这两个阶段的融合,可以有效的
降低光照、表情、姿态等因素影响。
      4.针对非控场景下多角度聚类问题, 提出一种基于非负字典对学习方法进行鲁棒的多角度聚类。具体来说,我们联合学习一个语义投影和特征投影。这种组合使得我们的计算既可以很好地提取聚类中心又可以降低噪声的影响。然后我们引入一个一致性约束和局部结构保持约束使得不同角度的聚类结果保持一致。为了降低算法时间复杂度,我们提出使用交替线性最小化算法来逐步降低目标函数的损失。理论和实验分析证明这种算法可以快速地收敛到一个全局最优解。
      总的来说,本文针对非控场景下人脸分析的几个关键问题:身份识别、识别效率、性别识别、多角度聚类等问题进行了系统而深入的研究,提升了现有的人脸分析算法性能。

;

Face analysis is a popular biometric technique and has many potential applications. In the constrained situation, face analysis has achieved excellent performance. However, in the unconstrained situation, the performance is still far behind satisfactory due to various factors such as illumination, pose, expression and low-resolution. In this thesis, we study some unconstrained face analysis tasks and propose our improved algorithms. The main contributions include the following issues:
        1.To deal with the video based face recognition, we propose a joint space learning method to simultaneously identify the most representative samples and discriminative feature from face video. Joint space learning is formulated as a matrix minimization problem with respect to both the columns (samples) and rows (features). Then an alternate minimization algorithm is developed to monotonically decrease the joint loss function. In addition, randomized techniques are applied to capture the nonlinear structure in unconstrained data, so that both accuracy and efficiency can be improved.
        2.To improve the efficiency of video based face recognition,  we propose to learn discriminative and compact binary codes for image set. To do this, we propose to embed the Hadamard code into the hashing function. This process not only leverages discriminative information but favors an information-theoretic criterion to yield high-quality codes. The low rank constraint is introduced to reduce the redundance of the image set. Moreover, we use a anchor points based kernel method to further improve the performance of the algorithm.
       3.To deal with the unconstrained gender recognition,  we propose to learn multiple order local binary patterns as feature descriptor. Specifically, we extract features according to three different statistical methods, i.e., single pixel value, mean and variance.
 Then, we further develop a localized multi-boost learning algorithm to combine these features for classification. Experiments show that the proposed method can effectively reduce the influence of the unconstrained factors.
       4.To deal with the unconstrained multi-view clustering problem, we propose a new Dictionary learning framework, called Nonnegative Dictionary Pair Learning, for robust multi-view clustering. To do this, we propose to learn a semantic projection and a feature projection jointly. A consistency constraint and a local geometric preserving constraint are combined to push the clustering solution in each view towards a common consensus. Then an alternate minimization algorithm called proximal alternating linearized minimization algorithm (PALM) is developed to monotonically decrease the joint loss function.
        In summary, in this thesis, we systematically study some unconstrained face analysis problems like identification recognition, image set hashing, gender recognition and multi-view clustering. Our proposed works improve the performance of the related challenges.

学科领域模式识别与智能系统
文献类型学位论文
条目标识符http://ir.ia.ac.cn/handle/173211/11839
专题毕业生_博士学位论文
作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
曹冬. 非控场景下人脸分析关键问题研究[D]. 北京. 中国科学院研究生院,2016.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
非控场景下人脸分析关键问题研究.pdf(14863KB)学位论文 暂不开放CC BY-NC-SA请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[曹冬]的文章
百度学术
百度学术中相似的文章
[曹冬]的文章
必应学术
必应学术中相似的文章
[曹冬]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。