Multi-scale region composition of hierarchical image segmentation
- PDF / 4,168,079 Bytes
- 23 Pages / 439.642 x 666.49 pts Page_size
- 96 Downloads / 207 Views
Multi-scale region composition of hierarchical image segmentation Bo Peng1,2 · Zaid Al-Huda1,2 · Zhuyang Xie1,2 · Xi Wu3 Received: 4 January 2020 / Revised: 30 June 2020 / Accepted: 13 July 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Hierarchical image segmentation is a prominent trend in the literature as a way to improve the segmentation quality. Generally, meaningful objects in an image are described by segments from different scales. Thus, one may spend extra effort on searching for the best representation of objects in the hierarchical segmentation result. In this paper, a novel algorithm is proposed to optimally select the segmentation scale, which leads to a composite segmentation as the output. To this end, the quality of regions from different scales of the hierarchical segmentation is evaluated. Then, a graphical model is constructed as a set of nodes. The weights among nodes are computed according to the segmentation quality of regions in multiple levels. In order to optimize the labeling of each node in the graph, the composition process is performed twice with two sampling intervals. Comprehensive experiments are conducted on different datasets for popular hierarchical image segmentation algorithms. The results show that the output of the proposed algorithm can improve the quality of hierarchical segmentation in a single scale at a low cost of computation. Keywords Hierarchical image segmentation · Segmentation evaluation · Graphical model · Scale selection
1 Introduction Image segmentation refers to the partitioning of an image into multiple regions, allowing meaningful objects to be extracted for high-level computer visual tasks. It could be a This work was supported by the National Natural Science Foundation of China under Grant 61772435, Sichuan Highway Science and Technology Project under Grant 2019-01. Bo Peng
[email protected] 1
School of Information Science and Technology, Southwest Jiaotong University, Chengdu, 611756, China
2
National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Chengdu, China
3
School of Computer Science, Chengdu University of Information Technology, Chengdu, 610225, China
Multimedia Tools and Applications
challenge task due to image noise [10–12] or ill-posed nature [54]. In general cases, the definition of “meaningful objects” is vague. Therefore, there is no single solution on how to properly segment an image. Many recent studies [3, 21, 26, 31, 35, 42, 56, 58] have shown that outputs in the form of a hierarchical segmentation outperform the one-solution algorithms [9, 15, 48], since the partition of objects can be obtained in multiple scales. Furthermore, the widespread use of the Berkeley Segmentation Database (BSDS) [3] in the field provides good evidence that image segmentation might be close to a well-defined problem in the presence of multiple human ground truths in different scales. The goal of hierarchical segmentation is to generate a dendrogram, where each node denotes
Data Loading...
