CAJ | 학술논문

为了有效提取印章图像的特征，提出了一种基于 NSCT Ⅱ GLCM 的印章图像特征提取方法。首先对图像进行 NSCT 分解，得到多幅子图像；然后通过 GLCM 提取图像的特征信息，并用特征参数描述该矩阵，用该特征参数构成的特征向量代表图像的特征信息；最后利用欧式距离对图像进行分类。针对印章图像进行了大量的实验，并与 GLCM 法和LBP-GLCM 融合法进行了比较。结果表明，该方法识别率更高。
위료유효제취인장도상적특정，제출료일충기우 NSCT Ⅱ GLCM 적인장도상특정제취방법。수선대도상진행 NSCT 분해，득도다폭자도상；연후통과 GLCM 제취도상적특정신식，병용특정삼수묘술해구진，용해특정삼수구성적특정향량대표도상적특정신식；최후이용구식거리대도상진행분류。침대인장도상진행료대량적실험，병여 GLCM 법화LBP-GLCM 융합법진행료비교。결과표명，해방법식별솔경고。
In order to effectively extract the seal image characteristics , feature extraction method of seal image based on GLCM in NSCT domain is proposed in this paper . Firstly , seal image is decomposed by NSCT to obtain multiple subband images , and the characteristic information is extracted according to GLCM , the characteristic parameters are used to describe the matrix . Use the fea-ture vector made of the characteristic parameters to represent the feature information of images . Finally , different types of seal im-ages are distinguished by Euclidean distance in the feature space . Experimental results on the seal image show that compared with the GLCM and LBP-GLCM fusion method , the method proposed in this paper has a higher recognition rate .