自然条件下葡萄叶片图像颜色一致性恢复效果的对比研究  

Color consistency recovery effect of grape leaf images taken under natural condition

作　　者：赵玉琴[1] 冯全[1] 李妙祺[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》2016年第6期92-99,共8页Journal of China Agricultural University

基　　金：国家自然科学基金资助项目(61461005)

摘　　要：针对不同的光照以及不同天气条件引起叶片图像颜色不一致的问题,采用10种典型的颜色恒常性算法对葡萄叶片图像中颜色的恢复效果进行对比试验,用色差ΔEa*b*和估计光源角度误差2种方法对不同算法的颜色恢复效果进行评价。试验结果表明:各种算法对图像中叶片颜色恢复均有一定的效果,其中2nd-order Grey-Edge和Edge-based Gamut Mapping 2种算法对不同光照和天气条件下以及多个品种的葡萄叶片图像处理后,其色差误差和估计光源角度误差均达到最小;从视觉角度上看,这2种算法处理后的图像也最接近基准图像。试验还表明:这2种颜色恒常性算法对于解决农业领域中许多由于成像条件的差异所引起的图像颜色偏差问题有明显的效果,而且能很好地实现葡萄叶片图像中颜色的恢复。The color of the images for the same leaf look inconsistent when they are taken under various illuminations or weather conditions.Ten typical color constancy algorithms are used to process grape leaf images and their effects on color restoration were assessed in both color differenceΔEa＊b＊ and the angle error of the estimation source methods.The results showed that：Both methods worked to some extent,which 2nd-order Grey-Edge and Edge-based Gamut Mapping achieved the best results regardless of various illuminations,weather conditions or grape cultivars;And,from the visual aspect,the leaf color of images processed by both algorithms was closest to the reference image.The data indicate that：The 2color consistency algorithms are of great help to solve the problems of color variety in the images incurred by different imaging conditions and to realize the color recovery of grape leaf images.

关 键 词：葡萄 叶片颜色 图像处理 颜色恒常性算法 一致性恢复 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]