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：
针对单独提取传统的局部二元模式（local binary pattern,LBP）指静脉特征识别率不高的问题,提出一种结合分块LBP和分块主成分分析（principal component analysis,PCA）的特征提取方法。首先对手指静脉感兴趣区域（region of interested,ROI）进行分块,提取分块LBP特征;然后,采用分块PCA对所提取特征进行降维除冗,得到一组新的降维后特征;最后计算欧氏距离并采用最近邻分类器进行分类。实验结果表明,论文提出方法识别率可达99.33%,等误率（equal error rate,EER）低至0.21%。与传统的3种算法进行比较,该方法的识别率有很大提高,且具有较好的稳定性和鲁棒性。
英文摘要：
Aiming at the problem of the traditional local binary pattern （LBP） of finger vein image may have low recognition rate, a method combined block LBP and block principal component analysis （PCA）is proposed in this paper. First, the region of interested （ROI） of finger vein image is dividedinto several blocks and the block LBP featureisextracted. Second, the dimension of extracted featureis reduced by using the block PCA. At last, Euclidean distance is calculatedandthe nearest neighbor classifier is takenfor verification. The results of the experiment show that the method can increase the recognition rate to 99.33% and decrease the equal error rate （EER） to 0. 21% . Compared with threetraditional algorithms, the method can greatly increase the recognition rate and has excellent stability and robust.
同期刊论文项目
同项目期刊论文
Multiobjective optimization of HEV fuel economy and emissions using the self-adaptive differential e
Rough neural network modeling based on fuzzy rough model and its application to texture classificati
A Selection Model for Optimal Fuzzy Clustering Algorithm and Number of Clusters Based on Competitive
A multiscale bi-Gaussian filter for adjacent curvilinear structures detection with application to va
Multi-Objective self-adaptive differential evolution with elitist archive and crowding entropy-based
On Global Robust Stability of a Class of Delayed Neural Networks with Discontinuous Activation Funct
Neural networks-based adaptive robust control of crawler-type mobile manipulators using sliding mode
Long-term Prediction of Time Series with Iterative Extended Kalman Filter Trained Single Multiplicat
Intelligent injection liquid particle inspection machine based on two-dimensional Tsallis Entropy wi
Predicting reliability and failures of engine systems by single multiplicative neuron model with ite
期刊信息
位置：