考虑Gabor小波特征的LBFI识别仿真  

Simulation of Local Blur Face Image Recognition Considering Gabor Wavelet Features

作　　者：王娟娟[1] 宋三华[1] 杜云明[2] WANG Juan-juan;SONG San-hua;DU Yun-ming(School of Computer and Artificial Intelligence,Huanghuai University,Zhumadian Henan 463000,China;College of Information and Electronic Technology,Jiamusi University,Jiamusi Heilongjiang 154007,China)

机构地区：[1]黄淮学院计算机与人工智能学院,河南驻马店463000 [2]佳木斯大学信息电子技术学院,黑龙江佳木斯154007

出　　处：《计算机仿真》2023年第9期237-241,共5页Computer Simulation

基　　金：2022年河南省科技攻关项目(222102210279)。

摘　　要：识别局部模糊人脸图像时,若不能增强模糊部分的信息,会降低图像识别精度,为提升模糊人脸图像的识别效果,提出基于Gabor小波特征的局部模糊人脸图像识别方法。使用均值滤波方法对图像噪声实施剔除,并根据剔除结果利用直方图均衡化算法对局部模糊实施信息增强处理;以上述图像处理结果为基础,使用Gabor小波变换方法提取图像显著、不显著特征向量,根据决策融合方法对提取的特征实施融合处理;通过LDA分类器对融合特征实施分类处理,基于分类结果实现人脸图像的精准识别。实验结果表明,使用上述方法开展人脸识别时,识别率较高、识别效果好。In order to improve the recognition effect of fuzzy face images,this paper put forward a local blur face recognition method based on Gabor wavelet features.At first,the mean filtering method was adopted to eliminate the noise from images,and then the histogram equalization algorithm was used to enhance the local blur information according to the elimination results.Based on the above results,the Gabor wavelet transform was used to extract the salient and non-salient feature vectors of the image.Moreover,the extracted features were fused by the decision fusion method.Then,the fused features were classified by the LDA classifier.Based on the classification result,the accurate face recognition was achieved.Experimental results show that the proposed method has high recognition rate and good recognition effect.

关 键 词：小波变换 局部模糊人脸图像 识别方法 人脸特征提取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]