基于加权自适应多重均匀LBP和2DPCA的掌纹识别
首发时间:2020-06-29
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(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对掌纹感兴趣区域(area 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(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?在掌纹公开标准数据库和自建非接触图库以及它们的噪声图库上进行对比实验,可获最低等误率分别为1.8790%和4.3803%?2.0192%和4.7301%?2.1849%和5.0050%?2.6632%和5.2237%?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?
关键词: 掌纹识别;均匀局部二值模式;信息熵;二维主成分分析;鲁棒性
For information in English, please click here
Palmprint recognition based on weighted adaptive multiple uniform LBP and 2DPCA
Abstract:In order to solve the problem that the 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 mode (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. Comparative experiments were conducted on the open standard database of palmprints ,self-built non-contact database and its noise database. The lowest equal error rates are 1.8790% and 4.3803%, 2.0192% and 4.7301%, 2.1849% and 5.050%, 2.6632% and 5.2237%, respectively. Compared with other algorithms, the recognition accuracy and robustness are effectively improved while ensuring real-time performance.
Keywords: Palmprint recognition MULBP Information entropy 2DPCA Robustness
基金:
引用
No.****
动态公开评议
共计0人参与
勘误表
基于加权自适应多重均匀LBP和2DPCA的掌纹识别
评论
全部评论0/1000