非接触指纹识别具有接受程度高、防伪性高、卫生性高等优点,是目前生物特征识别领域的研究热点,但是非接触指纹图像的背景区域比接触式的相对复杂,指纹图像会出现旋转和平移现象,且脊、谷线的对比度较低,这些因素严重影响了非接触指纹的识别性能.采用接触式指纹图像处理方法很难达到良好的处理效果.本文根据非接触指纹图像的特点提出了相应的非接触指纹图像的预处理方法.首先采用图像YCbCr模型中的Cb分量和Otsu法相结合的方法进行手指区域的提取.其次采用高频强调滤波和迭代自适应直方图均衡化相结合的图像增强算法进行图像增强处理,再用简化的Gabor函数模板进行二次增强,然后提出了一种手指指纹ROI区域提取的方法.最后本文采用基于AR-LBP算法进行特征提取,利用最近邻分类器进行特征匹配.实验结果表明,本文提出的非接触指纹算法能够达到很好的图像识别效果.%Touchless fingerprint recognition with high acceptance,high security,hygiene advantages,is currently a hot research field of biometrics,The background areas of touchless fingerprints are more complex than those of the contact,Fingerprint image will appear rotation and translation phenomenon,What's more,the contrast of the ridge and valley lines is much lower,These factors seriously affected the performance of the touchless fingerprint recognition.So the general methods for contact fingerprint images are difficult to achieve good effect.Firstly,In this paper,a method is put out to preprocess the images reasonably aiming at these features.Secondly,the Otsu based on the Cb component of the YCbCr model is adopted to extract the finger area.When the fingerprint images are enhanced,combining the high frequency emphasis filtering and iterafive adaptive histogram equalization technique is adopted firstly and then the simplified Gabor function template is used to enhance them again.thirdly,this paper proposed a new method of extracting the ROI fingerprint area.lastly,AR-LBP algorithm is adopted for feature extraction and the nearest neighbor classifier is used for feature matching.Experimental results show that the proposed method in this paper can achieve good image identify results.
展开▼
