Recognizing faces using Adaptively Weighted Sub-Gabor Array from a single sample image per enrolled subject

In this paper, we propose a new approach for face representation and recognition based on Adaptively Weighted Sub-Gabor Array (AWSGA) when only one sample image per enrolled subject is available. Instead of using holistic representation of face images which is not effective under different facial expressions and partial occlusions, the proposed algorithm utilizes a local Gabor array to represent faces partitioned into sub-patterns. Especially, in order to perform matching in the sense of the richness of identity information rather than the size of a local area and to handle the partial occlusion problem, the proposed method employs an adaptively weighting scheme to weight the Sub-Gabor features extracted from local areas based on the importance of the information they contain and their similarities to the corresponding local areas in the general face image. An extensive experimental investigation is conducted using AR and Yale face databases covering face recognition under controlled/ideal condition, different illumination condition, different facial expression and partial occlusion. The system performance is compared with the performance of four benchmark approaches. The promising experimental results indicate that the proposed method can greatly improve the recognition rates under different conditions.     

Face recognition from a single image per person: A survey

One of the main challenges faced by the current face recognition techniques lies in the difficulties of collecting samples. Fewer samples per person mean less laborious effort for collecting them, lower cost for storing and processing them. Unfortunately, many reported face recognition techniques rely heavily on the size and representative of training set, and most of them will suffer serious performance drop or even fail to work if only one training sample per person is available to the systems. This situation is called “one sample per person” problem: given a stored database of faces, the goal is to identify a person from the database later in time in any different and unpredictable poses, lighting, etc. from just one image. Such a task is very challenging for most current algorithms due to the extremely limited representative of training sample. Numerous techniques have been developed to attack this problem, and the purpose of this paper is to categorize and evaluate these algorithms. The prominent algorithms are described and critically analyzed. Relevant issues such as data collection, the influence of the small sample size, and system evaluation are discussed, and several promising directions for future research are also proposed in this paper.     

Unified probabilistic models for face recognition from a single example image per person

This paper presents a new technique of unified probabilistic models for face recognition from only one single example image per person. The unified models, trained on an obtained training set with multiple samples per person, are used to recognize facial images from another disjoint database with a single sample per person. Variations between facial images are modeled as two unified probabilistic models: within-class variations and between-class variations. Gaussian Mixture Models are used to approximate the distributions of the two variations and exploit a classifier combination method to improve the performance. Extensive experimental results on the ORL face database and the authors‘ database (the ICT-JDL database) including totally 1,750 facial images of 350 individuals demonstrate that the proposed technique, compared with traditional eigenface method and some well-known traditional algorithms, is a significantly more effective and robust approach for face recognition.     

基于泛滑动窗与加权2DLDA的单样本人脸识别

对于单训练样本人脸识别,基于每人多个训练样本的传统人脸识别算法效果均不太理想。尤其是基于Fisher线性鉴别准则的一些方法,由于类内散布矩阵为零矩阵,根本无法进行识别。针对这一问题进行了分析研究,提出了一种新的样本扩充方法,即泛滑动窗法。采用“大窗口,小步长”的机制进行窗口图像采集和样本扩充,不仅增加了训练样本,而且充分保持和强化了原始样本模式固有的类内和类间信息。然后,使用加权二维线性鉴别分析方法（Weighted 2DLDA）对上面获得的窗口图像进行特征抽取。在ORL国际标准人脸库上进行的实验表明了所提算法的可行性和有效性。