【摘要】 为了提高银行卡号识别准确率,提出了一种HOG特征模板匹配算法。经过对银行卡进行预处理,提取二值化数字图像,利用HOG算法提取出数字图像的特征向量,设计一种基于图像质心划分ceil的方法,通过计算特征向量与模板向量的欧氏距离,识别银行卡号。测试结果表明,该算法识别准确率达到98%以上。更多还原

【Abstract】 In order to improve the accuracy of bank card number recognition, a HOG feature template matching algorithm is proposed. After preprocessing the bank card, extracting the binary digital image and the feature vector of the digital image by HOG algorithm, this paper designs a method based on image centroid partition ceil, and identifies the bank card number by calculating the Euclidean distance between the feature vector and the template vector. The test results show that the accuracy of the algorithm is over 98%.更多还原