摘要
由于Gabor函数的生物特征,所以Gabor小波经常被用来进行纹理特征提取应用于人脸识别。然而由于在提取Gabor小波特征时运算复杂度高和所需运行时间长,使其不具备应用到实时的条件下,从而限制了Gabor小波在工程上的应用。本文提出了一种简化Gabor小波人脸识别算法,降低了运算复杂度,提高了特征提取的实时性,而且能取得与连续Gabor小波人脸识别算法相同的效果,并且与经典的PCA、LDA、LBP等经典算法相比取得了更好的识别率。
Gabor wavelets have commonly used for extracting texture and face recognition for its biological characteristics. However, extracting the Gabor features is computationally intensive and long run time required, so the features may be impractical for real-time applications. In this paper, we propose a set of simplified version of Gabor wavelets（SGWs） for face recognition. The simplified Gabor wavelets algorithm reduces the computationally complexity and improves the efficiency of feature extraction. Face recognition algorithm based on simplified Gabor wavelets can achieve a similar performance level to that using Gabor wavelets. When compare to the PCA, LDA, LBP and other conventional methods, our proposed method can achieve a better performance in the terms of recognition accuracy and computational complexity.
出处
《电子器件》
CAS
北大核心
2012年第6期687-691,共5页
Chinese Journal of Electron Devices
基金
国家自然科学基金项目(61231002
61273266
51075068)
教育部博士点专项基金(20110092130004)
