电子测量与仪器学报

刘玉珍,王鑫磊,林森.加权自适应MULBP与2DPCA结合的掌纹识别方法[J].电子测量与仪器学报,2021,35(1):142-150

加权自适应MULBP与2DPCA结合的掌纹识别方法

Palmprint recognition method by combining weighted adaptive MULBP and 2DPCA

DOI：

英文关键词:palmprint recognition MULBP Information entropy 2DPCA robustness

基金项目:辽宁省教育厅科学研究项目（LJ2019JL022,L2014132）、辽宁省自然科学基金面上项目（2015020100）、辽宁省自然科学基金指导计划（2019 ZD 0038）资助项目

作者	单位
刘玉珍	辽宁工程技术大学电子与信息工程学院葫芦岛125105
王鑫磊	辽宁工程技术大学电子与信息工程学院葫芦岛125105
林森	辽宁工程技术大学电子与信息工程学院葫芦岛125105

Author	Institution
Liu Yuzhen	Electronic and Information Engineering School, Liaoning Technical University, Huludao 125105,China
Wang Xinlei	Electronic and Information Engineering School, Liaoning Technical University, Huludao 125105,China
Lin Sen	Electronic and Information Engineering School, Liaoning Technical University, Huludao 125105,China

摘要点击次数: 624

全文下载次数: 3

中文摘要:

针对局部二值模式(local binary pattern, LBP)容易受到随机噪声和边缘点对图像的影响,以及局部二值模式描述图像纹理特征时阈值不能自动选取导致鲁棒性差的问题,提出一种基于加权自适应多重均匀局部二值模式(weighted adaptive multiple uniform local binary pattern, WA MULBP)与二维主成分分析(two dimensional principal component analysis, 2DPCA)相结合的掌纹识别方法。首先采用直方图均衡化(histogram equalization,HE)对掌纹感兴趣区域(region of interest, ROI)图像进行光照预处理,减少成像时的光照变化对最后掌纹识别成功率产生的影响;然后将预处理后的图像分成大小均匀的子块并利用自适应多重均匀局部二值模式(adaptive multiple uniform local binary pattern, A MULBP)算法获取各个子块的纹理特征直方图和权值;最后,将各个子块的纹理特征直方图和权值相乘串联得到最终的纹理特征直方图,经2DPCA维数约简后采用欧氏距离判别法进行掌纹识别。在香港理工大学PolyU图库、同济和IIT D非接触式图库、自建非接触图库以及它们的噪声图库上进行对比实验,可获得最低等误率分别为1879 0%、2019 2%、2184 9%、2663 2%、4380 3%、4730 1%、5005 0%和5223 7%,且识别时间都在1 s以内。相比其他算法,在保证实时性的情况下,有效提高了识别精度和鲁棒性。

英文摘要:

In order to solve the problem that the local binary pattern (LBP) is easily affected by random noise and edge points on the image, and the threshold cannot be automatically selected when the local binary mode describes the texture features of the image, resulting in poor robustness, a palmprint recognition method based on weighted adaptive multiple uniform local binary pattern (WA MULBP) and two dimensional principal component analysis (2DPCA) is proposed. Firstly, the histogram equalization (HE) is used to perform pretreatment of the palmprint region of interest (ROI) image to reduce the impact of the illumination change during imaging on the final palmprint recognition success rate. Secondly, the preprocessed image is divided into sizes Uniform sub blocks and use adaptive multiple uniform local binary pattern (A MULBP) algorithm to obtain texture feature histograms and weights of each sub block. Finally, the texture feature histogram of each sub block is multiplied and concatenated to obtain the final texture feature histogram, after the 2DPCA dimension reduction, the Euclidean distance discriminant method is used for palmprint recognition. Comparing experiments on Hong Kong Polytechnic University PolyU database, Tongji and IIT D non contact database, self built non contact database and their noise database. The lowest equivalent error rates are 1879 0%, 2019 2%, 2184 9%, 2663 2%, 4380 3%, 4730 1%, 5005 0% and 5223 7% and the recognition time is within 1 s. Compared with other algorithms, the recognition accuracy and robustness are effectively improved while ensuring real time performance.

查看全文查看/发表评论下载PDF阅读器