基于图像分析的偏色检测及颜色校正方法  

Color Cast Detection and Color Correction Methods Based on Image Analysis

作　　者：徐晓昭[1] 蔡轶珩[1] 刘长江[1] 贾克斌[1] 沈兰荪[1] 

机构地区：[1]北京工业大学信号与信息处理研究室,北京100022

出　　处：《测控技术》2008年第5期10-12,21,共4页Measurement & Control Technology

基　　金：国家自然科学基金重点项目(60431020);北京市自然科学基金项目(3052005);教育部博士点基金项目(20040005015);北京工业大学第六届研究生科技基金资助课题(ykj-2007-1906;ykj-2007-1908)

摘　　要：采用一种基于等效圆的偏色检测方法,克服了传统方法在图像偏色检测中的局限性。为了对检测后的偏色图像进行校正,采用一种结合灰度世界和完美反射的颜色校正方法,弥补了传统方法的不足,从而得到更为"真实"的校正图像。实验结果表明,基于图像分析的偏色检测及颜色校正方法,提高了偏色检测的可靠性,取得了较好的颜色校正效果。该方法仅利用图像本身的特征进行分析,具有普遍的适用性。A color cast detection method based on equivalent circle is applied, which overcomes the limit of traditional methods of detecting image color cast, In order to correct color cast of detected image, the color correction method of combing gray world and prefect reflector is applied, which offsets the defect of traditional methods and gets more ＂real＂ corrected image. Experiment results show that color cast detection and color correction methods based on image analysis enhance the reliability of color cast detection, and achieve good color correction effects. The proposed methods only use feature of image to analyze, and have universal applicability.

关 键 词：图像分析 偏色检测 颜色校正 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]