标题: 基于深度学习的适应性特征映射应用于个人化表情辨识
Deep Learning Based Adaptive Feature Mapping Approach to Personalized Facial Expression Recognition
作者: 林俊贤
吴炳飞
Lin, Chun-Hsien
Wu, Bing-Fei
电控工程研究所
关键字: 跨域适应;适应性学习;深度学习;表情辨识;回归;Cross domain adaption;Adaptive learning;Deep learning;Facial expression recognition;Regression
公开日期: 2016
摘要: 在人机介面上,自动化表情辨识系统是一个重要的功能,一旦机器可以读懂人的情绪的话,那么它就可以提供一些贴心的服务,而这是在这个智慧时代中相当重要的课题。近日,由于深度学习在巨量资料训练后的表现十分出色,因此很多方法都是基于深层神经网路所实现的。然而,如果深层模型没有训练过在一些特定场合的资料的话,那么它的辨识能力就会因此受到限制,但是资料的标记是相当费时费工的。因此本研究主要提出如何利用未标记的新资料,将一个训练过后的通用模型个人化的方法。
我们提出适应性特征映射的方式将新资料的特征分布转换到旧资料的特征分布上. 藉由将每一个新资料与其最相近的旧资料之前的误差最小化,那些在易混淆边界上的新资料特征,就会被牵引至靠近群落中心的位置,如此一来,它们预测错误的结果就有机会被修正。在此之前,我们希望可以训练出一个通用且较稳健的深层模型,因此我们搜集了23,591张表情影像来做为训练资料,而绝大部分是由YouTube的影片上撷取下来加以标记的。为了让模型得以有效学习,我们也做了空间校正与特征强化,其中包含了平移校正、旋转校正、Neighbor-center difference images (NCDIs)以及椭圆切割法。在五种资料库上的测试下,在大部分的状况下,适应性特征映射都有助于提升通用模型应用于特定环境下的表现,由此可见,这个方法对于实现个人化辨识的深层模型是有相当的潜力的。
Automatic facial expression recognition is useful in human-machine interface. Machines can give the close services when knowing the human's emotion, which is important in this intelligent generation. Many deep learning approaches are employed in current year due to its outstanding accuracy as it is trained by large amount of data. The performance is limited, however, in the specific condition or population if the model is not trained by the new data under such environment. In fact, labeling the data is a hard work and time consuming. Hence, this paper addresses the problem of how to personalize the generic model without label information from the testing data.
Adaptive feature mapping (AFM) is proposed to transform the feature distribution of new subjects into that of trained data. By means of minimizing the error between each testing sample and the most relevant trained sample, AFM can tow the testing samples near the confusing boundary to the centers of categories; therefore, their predicted labels can be corrected. To train a generic and robust deep model, 23,591 training images are extracted from YouTube mostly. Besides, to strengthen the learning efficiency, neighbor-center difference images (NCDIs) and ellipse cropping are utilized to enhance the features of the input image. After testing on five databases, AFM shows its ability to personalize the deep model and improves the performance in most of the cases. Therefore, AFM has the potential to realize the personal recognition base on deep learning.
URI: http://etd.lib.nctu.edu.tw/cdrfb3/record/nctu/#GT070460018
http://hdl.handle.net/11536/140238
显示于类别:Thesis