基于ART2网络的彩色像素分析及其应用  

Color Pixel Categorization Based on ART2 Network

作　　者：陈众[1] 蔡自兴[1] 叶青[2] 

机构地区：[1]中南大学信息科学与工程学院,长沙410083 [2]长沙理工大学电气与信息工程学院,长沙410076

出　　处：《中国图象图形学报》2008年第4期634-641,共8页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60234030)

摘　　要：像素分析是图像处理相关领域的其他分析(例如形状、纹理等)的基础,正确而有效地识别图像或视频流中像素的色彩及亮度是顺利进行后续工作的保证。在对RGB颜色空间做合理映射变换的基础上,提出了将ART2网络运用于彩色像素的归类,并通过图像处理的过程和结果演示了警戒值调节和"幼态延续"学习的作用。对处理结果的理论分析表明,这种方法符合人类观察图像的心理和生理过程,对阴影等干扰信息具有较强的适应性。Pixel analysis is the primary step for region,shape and texture analysis and even for semantic analysis. The correctness of the color and luminance analysis of certain pixel in an image or a series of video streams is a guarantee to the acceptable result of other image processing. Based on a reasonable mapping operation to vectors in RGB color space,this paper applies the ART2 to the layered detecting approach to categorize color pixels. The processing steps and final results not only demonstrate the functions of ＂neoteny learning＂ and adjusting of vigilance value,but also illustrate that the method is coherent with the human psychological and physiological process of observing an image and also has strong adaptability for shadow noise suppression.

关 键 词：像素分析 阴影 ART2 图像处理 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP753[自动化与计算机技术—控制科学与工程]