Interactive image segmentation by maximal similarity based region merging
Interactive image segmentation by maximal similarity based region merging
复制标题
基于最大相似度的区域合并的交互式图像分割
DOI：
10.1016/j.patcog.2009.03.004
复制
发表时间：
2010-02-01
影响因子：
8
通讯作者：
Wu, Chengke
中科院分区：
文献类型：
--
作者：
Ning, Jifeng;Zhang, Lei;Wu, Chengke
高效的图像分割是计算机视觉和目标识别中的一项重要任务。由于全自动图像分割对于自然图像来说通常是非常困难的，因此具有一些简单用户输入的交互式方案是很好的解决方案。提出了一种新的基于区域合并的交互式图像分割方法。用户只需要用笔画粗略地表示出物体和背景的位置和区域，这些笔画被称为标记。提出了一种新的基于最大相似度的区域合并机制，利用标记指导合并过程。如果Q在所有Q的相邻区域中与Q具有最高相似性，则将区域R与其相邻区域Q合并。该方法自动合并的区域，最初分割的均值漂移分割，然后有效地提取对象的轮廓标记的所有非标记区域作为背景或对象。该方法不需要预先设定相似度阈值，且对图像内容具有自适应性。实验结果表明，该方法能够从复杂背景中可靠地提取目标轮廓。(C)2009爱思唯尔有限公司保留所有权利。
Efficient and effective image segmentation is an important task in computer vision and object recognition. Since fully automatic image segmentation is usually very hard for natural images, interactive schemes with a few simple user inputs are good solutions. This paper presents a new region merging based interactive image segmentation method. The users only need to roughly indicate the location and region of the object and background by using strokes, which are called markers. A novel maximal-similarity based region merging mechanism is proposed to guide the merging process with the help of markers. A region R is merged with its adjacent region Q if Q has the highest similarity with Q among all Q's adjacent regions. The proposed method automatically merges the regions that are initially segmented by mean shift segmentation, and then effectively extracts the object contour by labeling all the non-marker regions as either background or object. The region merging process is adaptive to the image content and it does not need to set the similarity threshold in advance. Extensive experiments are performed and the results show that the proposed scheme can reliably extract the object contour from the complex background. (C) 2009 Elsevier Ltd. All rights reserved.