基于直方图调整的传统民族图案特征分析  

Traditional Chinese patterns analysis based on histogram adjustment

作　　者：李笑牛[1] 郭海[1] 孟佳娜[1] 

机构地区：[1]大连民族学院计算机科学与工程学院,辽宁大连116605

出　　处：《大连民族学院学报》2013年第5期539-542,共4页Journal of Dalian Nationalities University

基　　金：中央高校基本科研业务费专项资金资助项目(DC12010212)

摘　　要：利用计算机图形图像技术对中国传统民族艺术图案的特征进行了数值分析。利用直方图均衡化和灰度值五值化方法将原始灰度图像进行灰度分布调整,形成具有更加清晰灰度差异的新灰度图像;利用图像分析与处理中的几何不变矩方法,计算新灰度图像的12个几何不变矩,作为其特征向量;利用聚类分析中的k-均值聚类方法对其进行分类。通过具体算例,可以看出该方法原理简单、实现容易,得到了较好的分析结果,为传统民族艺术图案的计算机分析与处理提供了参考。In this paper, the numerical analysis is studied with the help of computer technology to the numerical features of traditional Chinese art patterns. Firstly, the original gray image will be gray -scale adjusted by using the gray value transformation and a new image with adjusted gray levels will be formed. Secondly, by using the geometry invariant moments method in image analysis and processing, 12 new geometry gray image invariant moments as its feature vectors will be calculated. Finally, the classification is corned on using k - means clustering method in clustering analysis. Through specific examples, we can see that the method is simple in princi- ple, easy realization, and it will provide a reference method for computer analysis and process- of traditional Chinese art patterns.

关 键 词：直方图均衡化 矩不变量 传统民族图案 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]