基于改进LBP的手指静脉识别算法

Finger Vein Recognition Algorithm Based on Improved LBP

为进一步提高手指静脉识别算法识别率,在图像预处理阶段提出了将直方图均衡化算法与局部对比度增强算法相结合,在扩大静脉图像动态范围的同时增强图像的细节。在图像识别阶段,提出了一种基于局部二值模式(Local Binary Pattern,LBP)的改进算子用来描述图像局部纹理特征,并结合权重分配和分块LBP特征算法对图像进行特征提取。最后使用支持向量机(Support Vector Machine,SVM)算法对图像特征进行训练。实验结果表明,上述算法识别率高达99.33%,与传统的识别算法相比具有明显的准确率提高。

In order to further improve the recognition rate of finger vein recognition algorithm,this paper proposed a combination of histogram equalization algorithm and local contrast enhancement algorithm in image preprocessing stage to enhance the detail of the image while expanding the dynamic range of vein image. In the image recognition stage,an improved operator based on Local Binary Pattern( LBP) was proposed to describe the local texture feature of the image,and the feature extraction was carried out by combining the weight distribution and LBP feature algorithm. Finally,the support vector machine( SVM) algorithm was used to train the image features. The experimental results show that the recognition rate of this algorithm is as high as 99.33%,which is obviously improved compared with the traditional identification algorithm.