引用本文

产思贤, 周小龙, 张卓, 陈胜勇. 一种基于超像素的肿瘤自动攻击交互式分割算法. 自动化学报, 2017, 43(10): 1829-1840. doi: 10.16383/j.aas.2017.e160186

Chan Sixian, Zhou Xiaolong, Zhang Zhuo, Chen Shengyong. Interactive Multi-label Image Segmentation With Multi-layer Tumors Automat. ACTA AUTOMATICA SINICA, 2017, 43(10): 1829-1840. doi: 10.16383/j.aas.2017.e160186

http://www.aas.net.cn/cn/article/doi/10.16383/j.aas.2017.e160186

关键词

Growcut算法，交互式分割，超像素，肿瘤自动攻击 

摘要

交互式分割对于选取图像中感兴趣的对象很有意义.在图像处理领域中有着很重要的地位，具有广泛的应用，至今仍然是一个研究的热点问题.然而，逐像素执行交互式分割通常是耗时的.本文提出了一种新的分割方法.在Growcut算法框架下，提出基于超像素的肿瘤自动攻击（TA）分割.其中，超像素可以提供强大的边界信息来引导分割，且可以由过分割算法很容易来获取.TA与细胞自动攻击算法（CA）有着相似的原理，给定少量的用户标记目标的超像素，可以由TA完成目标分割任务，处理速度比Growcut算法快.此外，为获得最佳效果，应用了水平集和多层TA方法来进行边界的调整.在VOC挑战分割数据集上进行的实验表明，所提出的分割算法性能表现优异，高效和精准，且能处理多目标分割任务.

文章导读

Image segmentation task is to divide an image into regions of interest that are suitable for machine or human operations [1], [2] like image retrieval and recognition. Recently, the accuracies of completely automatic segmentation techniques [3], [4] have been enhanced substantially. Nevertheless, the achievements of current state-of-the-art algorithms still cannot satisfy the accuracy requirement of professional image editors for choosing target boundaries. Many interactive algorithms have been proposed to improve the accuracy recently. These algorithms are based on the graph-based theory, including interactive grabcut [5], graph-cut [6]-[8], random walks [9], regioncut [10] and growcut [11].

Graph-cut [6] is an assembled optimization strategy to address the issue of the object segmentation in an image. An image is treated as a graph and each pixel is a graph node. The globally optimal pixel labelling for two-label case (i.e., object and background) can be efficiently computed by using max-flow/min-cut algorithms. Grabcut [5] is an improvement of graph-cut by merging an iterative segmentation mechanism. The first proximity of the ultimate foreground/background labelling can be found when the user draws a rectangular box surrounding the target of interest. Random walker (RW) [9] acquires a few pixels as user-determined seed labels, but it gives an analytical decision of the probability which a random walker starts at each unlabelled pixel will attain one of the pre-labelled pixels firstly. Object segmentation is gained by distributing each pixel to the label for which the greatest probability is computed. Some special images with poor structure, color, and appearance features also can employ the RW for editing. But it is not easy to control and accomplish this kind of energy minimizing approach. Regioncut [10] associates the traits of the robustness of region information and the precision of gradient oriented segmentation approaches. Furthermore, the distributed seeds are initialized by region probabilities. This method can reach the state of convergence without user initialized seeds. Under the framework of the cellular automata (CA) [12], an interactive segmentation method, named growcut [11], is proposed. There are two major properties of this algorithm. One is the possibility to deal with the multi-label segmentations. The other is that this approach can be extended to handle the high-dimensional images.

In computer vision, interactive object segmentation plays a significant role in photo analysis and image editing. Under interactions in terms of scribbles [1], [2] or bounding boxes [13] around the object of interest for seeds, users can directly utilize the segmentation algorithm towards a desired output. Recently, researchers have presented many powerful approaches for interactive image segmentation. In this paper, we focus on the literature of interactive segmentation performed with super-pixel.

In regioncut [10], a Gaussian mixture model (GMM) and a precision of gradient oriented segmentation method are learned by combining the robustness of region information. The GMM is applied in pre-initializing the region probabilities. In this way, it is similar to distributed seeds. The final segmentation output is still gained from building a pixel-based graph. Additionally, the ineffectiveness of only using final segmentation mask is shown in the results. In [14], the method fuses the framework mentioned in [15] to obtain super-pixels on each frame independently. After that, the optical forward and backward information are utilized to build a spatio-temporal super-pixel graph. The graphs based on occlusion boundaries are focused on and the major contribution is to use the information of an occlusion boundary detector to modify them. Subsequently, the spatio-temporal super-pixel graph is partitioned into object and background by graph-cut. In [16], super-pixels serve as interactive buttons which can be tapped by the user quickly to add or remove an initial low quality segmentation mask, with the purpose of correcting the segmentation errors and generating promising results. Reference [17] develops an innovative segmentation framework based on bipartite graph partitioning, in which the multi-layer super-pixels can be fused in a principled manner. Computationally, it is tailored to unbalance bipartite graph structure and lead to a highly efficient, linear-time spectral algorithm. As far as our information goes, nevertheless, almost all the existing interactive approaches initialize the object and background via pixels.

图 1  The final results of our proposed interactive segmentation system. (a), (b) and (c) are single object segmentations and (d) is the multi-object segmentation.

图 2  The process of our interactive segmentation algorithm.

图 3  The framework of proposed algorithm.

In this paper, we have investigated a new approach for solving the issue of interactive object segmentation in the image. The presented TA was similar to CA. However, the TA could operate super-pixel directly. Based upon TA, a novel growcut strategy was motivated to handle super-pixels via interactions with neighbors. Experiments illustrated that our approach achieved superior performance and exceeded other state-of-the-arts. It demonstrated by experiments that the context-based multi-layer TA could effectively enhance any given state-of-the-art methods to obtain more accurate results.

In the future, we will continue to improve the performance of proposed approach by extracting more effective features and integrating more algorithms. Implementing a high performance version by the graphics processing unit to fully explore the parallel nature of the algorithm is also a promising direction.

作者简介

Xiaolong Zhou

received the Ph.D.degree in mechanical engineering from the Department of Mechanical and Biomedical Engineering, City University of Hong Kong, Hong Kong, in 2013.He joined Zhejiang University of Technology, Zhejiang, China in February 2014 where he currently serves as an Associate Professor at the College of computer Science and Technology.From April 2015 to May 2016, he worked as a Senior Research Fellow at the School of computing, University of Portsmouth, Portsmouth, UK.He serves as an IEEE member and an ACM member.He received the T.J.Tarn Best Paper Award on ROBIO2012 and ICRA2016 CEB award for Best Reviewers.His research interests include visual tracking, gaze estimation, 3D reconstruction and their applications in various fields.He has authored over 50 peer-reviewed international journals and conference papers.He has served as a Program committee Member on ROBIO2015, ICIRA2015, SMC2015, HSI2016, ICIA2016, and ROBIO2016.E-mail:zxl@zjut.edu.cn

Zhuo Zhang 

received the B.E.degree in computer science and technology from Zhejiang University of Technology in 2015.He is currently pursuing his M.E.degree in computer science and technology at Zhejiang University of Technology.His research interests include machine learning and visual object detection.E-mail:imzhuo@foxmail.com

Shengyong Chen 

received the Ph.D.degree in computer vision from City University of Hong Kong, Hong Kong, in 2003.He is currently a Professor of Tianjin University of Technology and Zhejiang University of Technology, China.He received a fellowship from the Alexander von Humboldt Foundation of Germany and worked at University of Hamburg in 2006-2007.His research interests include computer vision, robotics, and image analysis.Dr.Chen is a Fellow of IET and senior member of IEEE and CCF.He has published over 100 scientific papers in international journals.He received the National Outstanding Youth Foundation Award of China in 2013.E-mail:sy@ieee.org

Sixian Chan 

received the bachelor degree from Anhui University of Architecture in 2012.He is a Ph.D.candidate at the computer Science and Technology Department of Zhejiang University of Technology.His research interests include image processing, machine learning, and video tracking.Corresponding author of this paper.E-mail:sxchan@163.com