基于纹理图像的农产品无损标识与真伪识别技术研究  

Research on Nondestructive Identification Technology and Authenticity Identification Technology of Agricultural Products Based on Texture Image

作　　者：向绪友[1] 周超[1] 贺艺[1] 刘学文 李亮[1] XIANG Xu-you;ZHOU Chao;HE Yi;LIU Xue-wen;LI Liang(Hunan Agricultural Information and Engineering Research Institute,Hunan Intelligent Agricultural Engineering Technology Research Center,Changsha 410125,PRC)

机构地区：[1]湖南省农业信息与工程研究所,湖南省智慧农业工程技术研究中心,湖南长沙410125

出　　处：《湖南农业科学》2020年第8期93-96,共4页Hunan Agricultural Sciences

基　　金：湖南省农业科技创新资金项目(2017X07,2019XX02)。

摘　　要：研究了一种基于产品表面纹理图像特征的产品真伪识别方法。使用具有定位、定向、定界和标定作用的标签联合产品本身天然纹理实现无损标识,一方面将官方纹理图像和用户纹理图像的特征值统一到同一计算空间,同时降低纹理图像拍摄条件,使应用场景更加丰富;另一方面利用分区将图像的纹理特征表达从一维扩展到多维,通过突出局部特征提高真伪识别准确率。A product authenticity recognition method based on product surface texture image features is studied.The label with the functions of location,orientation,delimitation and calibration is used to realize the nondestructive identification by combining the natural texture of the product,on the one hand,it unifies the eigenvalue calculation of official texture image and user texture image into the same computing space,at the same time,it reduces the shooting conditions of texture image and makes the application scene richer;the texture feature expression of texture image is extended from one dimension to multi dimension by using partition,and the recognition accuracy is improved by highlighting local features.

关 键 词：纹理图像 纹理防伪 纹理分类 局部特征描述 信息技术 农产品 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]