基于白平衡算法的图像色度学分割  

Image Colorimetry Segmentation Based on White Balance Algorithm

作　　者：刘玉成[1] 张颖超[2] 

机构地区：[1]南京财经大学经管中心,南京210046 [2]南京信息工程大学信息与控制学院,南京210046

出　　处：《计算机工程》2012年第20期195-196,199,共3页Computer Engineering

基　　金：江苏省六大人才高峰基金资助项目(06-A-027);江苏省高校自然科学基金资助项目(06KJD520122)

摘　　要：受外界光照环境的影响,采集得到的图像存在色彩偏移的问题。为此,利用白平衡算法对其进行校正。按图像特性调整红、绿、蓝三色的强度,以修正外部光线所造成的误差。采用色度学的图像处理方法,使检测结果更稳健。对二值图像做边界跟踪处理,并使用直方图进行分割。实验结果表明,该方法的分割准确率较高。According to the influence by outside light environment,the color images collected often have color offset problems,so this paper uses a white balance correction algorithm.It adjusts the image strength of red,green and blue on the basis of the present image characteristic,to correct the error caused by external light.Thus it can solve the problems caused by light color offset to some extent,and make the examination result steadier by using the image of colorimetric method of image processing.It uses the binary image boundary tracking processing,and the histogram segmentation.Experimental result shows that this method has higher segmentation accuracy.

关 键 词：白平衡 色度学 边界跟踪 神经网络 RGB向量空间 直方图分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]