欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为了解决单样本掌纹识别的困难，研究了基于最近相关性分类器（NCC）的单样本掌纹识别方法。首先对掌纹图像进行分块，划分为若干个子图像；然后运用统计特征、傅里叶变换、离散余弦变换（DCT）和Oabor变换4种方法对子图像进行特征提取，将所有子图像的特征向量组合在一起形成该图像的特征向量；最后应用NCC进行分类识别。运用PolyU掌纹图像库，对本文算法进行测试。实验结果表明：与最近邻分类器（NNC）和支持向量机（SVM）相比，在不同大小的子图像上，运用不同的特征提取算法，NCC均提高了识别率；分类时间在0．3-0．7s之间，满足实时系统的需求。
英文摘要：
In order to solve the problem of palmprint recognition of a single sample, a new palmprint rec- ognition method for a single sample based on the nearest correlation classifier（NCC） is developed. First, a palmprint image is partitioned into several smaller sub-images. Then the sub-image feature vectors are extracted by four feature extraction methods. They are statisties feature,Fourier transform,discrete cosine transform （DCT） and Gabor transform. The feature vectors of all the sub-images are combined to- gether to form the feature vectors of the palmprint image. Finally, the pattern classification can be implemented by the NCC. The effectiveness of the developed approach is tested on the PolyU palmprint database. The experimental results show that compared with the nearest neighbor classifier （NNC） and the support vector machine （SVM）,the recognition rates of the new classifier are significantly improved using different feature extraction algorithms in different size sub-images. The classification time is between 0. 3 s and 0. 7 s. Therefore the algorithm meets the real-time requirements.
同期刊论文项目
同项目期刊论文
期刊信息
位置：