基于Dempster-Shafer证据理论的虹膜图像分类方法

为了提高虹膜图像的分类率，提出了一种基于证据理论的虹膜图像分类方法．该方法利用虹膜图像的纹理变化信息来提取虹膜灰度信号的比率特征，并结合证据理论实现了虹膜图像的决策分类，降低了不确定性因素对图像分类的影响，提高了分类率．在相同的实验条件下，对不同数量的虹膜图像进行了实验验证，结果表明，该方法在保持了分类稳定性的同时，其分类率比直方图交叉分类方法和直方图比率特征分类方法分别提高了6．96％和4．44％．

Iris Image Classification Approach Based on Dempster-Shafer Theory of Evidence

In order to improve the iris image classification rate, an image classification method is developed based on Dempster-Shafer evidence theory. Firstly, the ratio features of iris gray signals are extracted by using the texture changing information of iris images. Secondly, the decision classification is realized by employing Dempster-Shafer evidence theory to reduce the influence of uncertain factors on image classification and improve the classification rate. Under the same conditions, experiment validation has been carried out for various numbers of iris images, the results show that comparing with the histogram intersection and histogram ratio feature classification, the classification rate of the proposed algorithm is increased 6.96% and 4.44% respectively, while keeping the stability of classification.