基于多角度旋转积分图的手背静脉身份识别

Dorsal Hand Vein Recognition Based on Multi-angle Rotation Integration

随着生物特征识别技术水平的飞速发展,手背静脉身份识别也广泛运用于各个领域;由于采集终端硬件设备和采集环境的差异,手背静脉识别效果并不理想;针对手背静脉图像在亮度,旋转,尺寸等方面造成的影响,提出了基于多角度旋转积分图的手背静脉身份识别方法;首先在尺度归一化后结合检测边缘性能的静脉图像梯度分割方法对图像进行二值分割,然后选取最佳角度间隔做旋转积分运算,最后通过二维离散余弦变换截取最佳特征矩阵用于分类识别,识别率超过99.9%;通过对比其它传统算法对手背静脉图像的识别效果来验证本文特征提取方法的可行性和优越性。

With the rapid development of the biometric technology,the identity recognition technology of dorsal hand vein has been more and more widely used in many fields.Because of the influence of the different hardware conditions and environment,the recognition rate is not ideal.Study on the problem of brightness,rotation,scales of the dorsal hand vein images,a method of dorsal hand vein identity recognition based on multi-angle rotation integration is proposed.At first,the dorsal hand vein images are binary-segmented by a gradient method of detecting edge performance after scale normalized,then select the best angular interval for the rotation integral operation,finally,the best feature matrix is intercepted after two-dimensional discrete cosine transform for classification and recognition,the recognition rate is more than 99.9%.The experiment verifies the feasibility and superiority of the method proposed in this paper by comparing the recognition effects of other traditional algorithm of dorsal hand vein images.