基于模糊综合评判的在线图像分割

Online image segmentation on fuzzy comprehensive evaluation

为使矿岩块度在线检测能精确和快速地进行,提出了一种自适应阈值分割算法:首先选取全局自动阈值分割算法粗分割图像,然后针对粗分割效果较差的目标区域,重复利用阈值分割算法直到无区域可分离。在重复分割前,利用模糊综合评判方法对每一个目标物体的参数(尺寸,形状及梯度等)进行综合评价,若该目标为非正常块度,对其进行重复分割。通过对一次矿山爆破的300多幅矿岩块度图像进行测试表明:在线图像分割算法与新近的聚类分析及图论最小割算法相比,不仅简单而且具有较好的分割效果,在保证在线处理速度的要求下,分割准确率达95%以上,可有效地扩展应用在其它颗粒在线检测系统中。

In this paper,a monitoring system grabed the fragment images at the end of the conveyor belt and did the image processing in time,and the key task and the problem for the system was to deal with the touching fragments quickly and accurately.To resolve the problem,an adaptive image segmentation algorithm was proposed based on the analyses of fragment size,shape and gradient etc.Firstly a fragment image was roughly segmented by a recursive thresholding algorithm,and then the treatment was repeated for the regions of touching fragments.The judgment for touching fragments applied fuzzy comprehensive evaluation for rock fragment size,shape and gradient etc.In one Mine,300 fragment images were took to do testing,the experimental results indicated that as compared to clustering analysis and graph based algorithms,the new algorithm can successfully make fragment image segmentation online,the accuracy was about 95%.The new algorithm can also be expanded into other complicated particle online monitoring systems.