基于Krawtchouk矩和支持向量机的印鉴真伪识别  

Seal identification based on krawtchouk moment and support vector machine

作　　者：朱胜银 赵红东 杨志明 王敬 李宇海 ZHU Shengyin;ZHAO Hongdong;YANG Zhiming;WANG Jing;LI Yuhai(School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, China;State Key Laboratory of pulsed power laser technology, Tianjin 300308, China)

机构地区：[1]河北工业大学电子信息工程学院,天津300401 [2]脉冲功率激光技术国家重点实验室,天津300308

出　　处：《光学技术》2018年第3期354-358,共5页Optical Technique

基　　金：脉冲功率激光技术国家重点实验室开放基金项目(614210701041705)

摘　　要：提出了一种将Krawtchouk矩特征不变量与高斯核支持向量机相结合的印鉴识别方法。实验中将得出的印鉴图像Krawtchouk矩特征向量作为高斯核支持向量机的输入参量,利用遗传算法优化支持向量机的惩罚因子和核参数,使识别性能得到有效提高;实验显示Krawtchouk矩下的印鉴类间散度与类内散度比值是Zernike矩的2.93倍,与遗传算法优化后的高斯核支持向量机相结合下的识别率明显提高。结果表明：与Zernike矩不变量相比,Krawtchouk矩不变量能更加准确地描述印鉴图像特征,识别性能更好。A seal recognition method based on Krawtchouk moment feature invariants and Gauss kernel support vector machine is proposed. In the experiment,the Krawtchouk moments feature vector of the seal image is used as the input parameters of the Gauss kernel support vector machine,and genetic algorithm is used to optimize the kernel parameter and penalty factor of support vector machine,so that the recognition performance can be improved effectively. The experimental results show that the ratio between the class scatter and within class scatter of Krawtchouk moments is 2.93 times of that of Zernike moments,and the recognition rate is significantly improved with the combination of Gauss kernel support vector machine optimized by genetic algorithm.The Krawtchouk moment invariants can more accurately describe the characteristics of the seal image,and the recognition performance is better compared with the method based on Zernike moment invariants.

关 键 词：印鉴图像识别 特征提取 KRAWTCHOUK矩 支持向量机 遗传算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]