基于方向权值扩散的指纹方向场计算

Computation on fingerprint orientation field based on direction weight diffusion

为有效解决噪声区域指纹质量块重建方向场(orientation filed,OF)可靠性低的问题,提出一种基于方向权值扩散求方向场的方法.首先,利用平方梯度法对指纹方向场进行粗提取,利用基于权值的梯度一致性对指纹质量进行评估,把质量块分为四个等级;然后,利用邻域判别法对误判的指纹块进行修正,统计邻域块中已评估块的个数,把质量分数相同的指纹块分为三个优先级;最后,利用质量和优先级对指纹方向场进行扩散迭代,在迭代过程中根据待评估块邻域块的方向梯度一致性赋予不同的权值,待评估块迭代完全后得到最终的方向场.实验结果表明:该方法能够通过质量扩散来提高低质量区域的可靠性,从而提高低质量区域方向场的准确度.

To solve the problem of low reliability of orientation filed computation in the poor quality fingerprint block,a method for computing the orientation field based on the diffusion of the direction weights was proposed.Firstly,the square direction gradient method was applied to extract the rough direction of the fingerprint field,and then the quality of the fingerprint was evaluated by using the gradient consistency based on the weights.The quality block was divided into four levels.Subsequently the neighborhood discrimination method was performed to correct the misjudged fingerprint block.After correcting the misjudged quality block,the number of the evaluated blocks in the neighboring block was counted.Thereafter,the blocks with the same quality score were divided into three priority levels.Finally,the fingerprint orientation field was iteratively calculated according to the quality and priority.During the iteration process,different weight values were assigned according to the square gradient of the neighborhoods of the block to be evaluated.After the iteration of the evaluation block was completed,the final orientation field was obtained.Experimental results show that the proposed method can improve the reliability of the low-quality region through quality diffusion,thereby enhancing the accuracy of the regions with poor reliability.