摘要
光学膀胱内窥镜是膀胱癌检测中极为重要的诊疗仪器,对膀胱癌的诊断起着关键作用。但膀胱内窥镜图像成像时会由于光照不均匀或者液体残留等原因出现光线过暗或过度曝光等现象。通过基于视网膜皮层算法(Retinex)中的单尺度视网膜皮层算法(singele scale retinex,SSR),多尺度加权平均的Retinex算法(multi scale retinex,MSR)和彩色恢复多尺度视网膜皮层算法(multi-scale retinex with color restoration,MSRCR)对暗区图像进行处理。试验发现Retinex算法可以使暗区图像得到改进,其中由高斯函数和高斯环绕函数组成的MSRCR算法处理效果最好。
Optical bladder endoscopy is a very important diagnostic and therapeutic instrument for bladder cancer detection,it plays a key role in the diagnosis of bladder cancer.However,the light is too dark or overexposed due to uneven illumination or liquid residue.The dark area image is processed by single scale Retinex(SSR),multi scale Retinex(MSR)and multi scale Retinex with color restoration(MSRCR)based on Retinex algorithm.Experiments show that Retinex algorithm can improve the dark area image,and msrcr algorithm composed of Gaussian function and Gaussian surround function has the best processing effect.
作者
卫凯龙
张武凤
姜峰
董和磊
Wei Kailong;Zhang Wufeng;Jiang Feng;Dong Helei(East China Institute of Photo-electron IC,Suzhou 215010,China;School of Instrument and Electronics,North University of China,Taiyuan 030051,China)
出处
《国外电子测量技术》
北大核心
2021年第9期13-17,共5页
Foreign Electronic Measurement Technology
基金
中国博士后科学基金(2017M611201,2019T120198)项目资助。
