焦炭光学组织的超反射率图像分析系统  

Hyper-Reflectance Image Analysis System of Coke Optical Texture

作　　者：夏杰[1,2] 谢威[1,2] 陈雁秋[1,2] 

机构地区：[1]复旦大学计算机科学技术学院,上海201203 [2]复旦大学上海市智能信息处理重点实验室,上海201203

出　　处：《计算机系统应用》2016年第12期35-41,共7页Computer Systems & Applications

基　　金：国家自然科学基金(61175036)

摘　　要：分析焦炭的光学组织是一种重要的评估焦炭质量的方式,目前这种评估方式还停留在人工阶段.为了改变现状,本文设计和实现了一套自动分析系统,可以自动采集焦炭切片的显微图像并自动分割和识别其中的焦炭光学组织.系统由图像采集系统和图像分析系统两个子系统构成.在图像采集系统中,我们使用多角度极化技术拍摄得到焦炭切片在不同极化角度下的反射率图像,本文称这种特殊图像为超反射率图像.在图像分析系统中,我们提出了一种针对焦炭的超反射率图像的新型分析算法,可以准确高效地分割和识别图像中的各种焦炭光学组织.Analyzing optical texture of metallurgical cokes is an important way to measure the quality of coke. Currently, these measurements have been still in the manual stage. In this paper, we present a system to improve the status quo, which can automatically capture the microscopic images of coke sections and then segment and recognize different coke optical textures in the images. The system consists of two subsystems, which are image acquisition system and image analysis system. We take advantage of multi-directional polarizing technique to capture the reflectance images of coke sections at different polarizing angles, and this special type of image is termed as hyper-reflectance image in this paper. In the image analysis system, we propose a novel analysis algorithm to analyze the hyper-reflectance image of coke, which shows excellent performance in the segmenting and recognizing of coke optical texture.

关 键 词：焦炭光学组织 显微图像 多角度极化 图像分割 形态剖面 随机森林 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]