Face Recognition Using Vector Quantization Histogram And Support Vector Machine Classifier
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE: TECHNIQUES AND APPLICATIONS, AITA 2016(2016)
摘要
In this paper, we propose a new face recognition method combining Vector Quantization (VQ) method and Support Vector Machine (SVM) classifier. VQ method is used as a feature extractor and SVM classifier for feature classification. By applying low pass filtering and VQ processing to a facial image, a histogram including effective facial feature is generated, which is called VQ histogram. After dividing VQ histograms into training set and testing set, classifiers are trained with training examples (training histograms) by using Gradient Descent Method (GDM). Testing examples (testing histograms) can be tested with optimal classifiers for face recognition. We use the publicly available ORL face database for the evaluation of recognition accuracy, which consist of 400 images of 40 individuals. Experimental results show that the variety of filter size affects the recognition accuracy. The recognition rate increases with an increase of the ratio of training examples and testing examples, and maximum recognition rate of 98.0 % is obtained.
更多查看译文
关键词
Face recognition,Vector Quantization (VQ) histogram,Support Vector Machine (SVM),Gradient Descent Method (GDM)
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要