基于灰度共生矩阵和分形的哈密瓜表皮网状纹理分析  

Netlike texture analysis of hami melon using parameters based on GLCM and fractal

作　　者：王魏[1] 冯全[1] 杨梅[1] 

机构地区：[1]甘肃农业大学工学院,兰州730070

出　　处：《中国农业大学学报》2012年第3期138-142,共5页Journal of China Agricultural University

基　　金：国家自然科学基金项目(61062012)

摘　　要：根据表皮纹理对哈密瓜进行自动分级。选取基于灰度共生矩阵的4种纹理参数和分形盒维数对哈密瓜表皮纹理进行统计分析,研究哈密瓜以及作为对比组的西瓜和甜瓜关于这5种纹理参数的分布规律。试验结果表明:基于灰度共生矩阵的4种纹理参数能将大部分纹理清晰与纹理模糊、霉变的哈密瓜表皮区分开,分形盒维数则可区分大部分纹理模糊表皮与霉变表皮;这5种纹理参数的组合可区分哈密瓜与西瓜、甜瓜的纹理。For the purpose of automatic grading of Hami melon according to the skin texture,statistical analysis of four texture parameters based on gray-level co-occurrence matrix（GLCM） and fractal box-counting dimension of Hami melon was tested on Hami melon.And texture features of Hami melon,water melon and ordinary melon were studied as well.Results show that the GLCM-based parameters do well in distinguishing clearly texture from blurry and decayed texture of hemi melon,and fractal-based parameter does well in distinguishing blurry from decayed texture of hemi melon.The combination of these parameters also does well in distinguishing texture of hami melon from water melon and ordinary melon.

关 键 词：哈密瓜 网状纹理 自动分级 灰度共生矩阵 分形 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]