文章基本信息

标题：A Novel Image Segmentation Algorithm Based on Graph Cut Optimization Problem
本地全文：下载
作者：Zhang Guang-hua ; Xiong Zhong-yang ; Li Kuan 等
期刊名称：TELKOMNIKA (Telecommunication Computing Electronics and Control)
印刷版ISSN：2302-9293
出版年度：2015
卷号：13
期号：4
页码：1337-1342
DOI：10.12928/telkomnika.v13i4.1178
语种：English
出版社：Universitas Ahmad Dahlan
摘要：Image segmentation, a fundamental task in computer vision, has been widely used in recent years in many fields. Dealing with the graph cut optimization problem obtains the image segmentation results. In this study, a novel algorithm with weighted graphs was constructed to solve the image segmentation problem through minimization of an energy function. A binary vector of the segmentation label was defined to describe both the foreground and the background of an image. To demonstrate the effectiveness of our proposed method, four various types of images were used to construct a series of experiments. Experimental results indicate that compared with other methods, the proposed algorithm can effectively promote the quality of image segmentation under three performance evaluation metrics, namely, misclassification error rate, rate of the number of background pixels, and the ratio of the number of wrongly classified foreground pixels.
其他摘要：Image segmentation, a fundamental task in computer vision, has been widely used in recent years in many fields. Dealing with the graph cut optimization problem obtains the image segmentation results. In this study, a novel algorithm with weighted graphs was constructed to solve the image segmentation problem through minimization of an energy function. A binary vector of the segmentation label was defined to describe both the foreground and the background of an image. To demonstrate the effectiveness of our proposed method, four various types of images were used to construct a series of experiments. Experimental results indicate that compared with other methods, the proposed algorithm can effectively promote the quality of image segmentation under three performance evaluation metrics, namely, misclassification error rate, rate of the number of background pixels, and the ratio of the number of wrongly classified foreground pixels.