Please use this identifier to cite or link to this item:
Title: Semantic image segmentation and evaluation
Authors: Li, Hui
Keywords: DRNTU::Engineering::Computer science and engineering
Issue Date: 2015
Source: Li, H. (2015). Semantic image segmentation and evaluation. Master's thesis, Nanyang Technological University, Singapore.
Abstract: Though quite a few image segmentation benchmark datasets have been constructed, there is no suitable benchmark for semantic image segmentation. In this thesis, we first construct a benchmark for such a purpose, where the groundtruths are generated by leveraging the existing fine granular groundtruths in the Berkeley Segmentation Dataset (BSD) as well as using an interactive segmentation tool for new images. We also propose a percept-tree-based region merging strategy for dynamically adapting the groundtruth for evaluating test segmentation. Moreover, we propose a new evaluation metric that is easy to understand and compute, and does not require boundary matching. Experimental results show that, compared with the BSD, the generated groundtruth dataset is more suitable for evaluating semantic image segmentation, and the conducted user study demonstrates that the proposed evaluation metric matches user ranking very well. In the second part of this thesis, we focus on segmentation application by utilizing prior information (i.e., depth in this thesis) to improve segmentation quality. To the best of our knowledge, little work has been attempted so far to achieve automatic image segmentation on RGB-D image. Users are usually asked to input scribbles to indicate the foreground and background or the framework needs to be trained on a database to obtain the bounding box for a specified target. All these methods require external information. We propose to utilize Kinect shadow information into state-of-the-art algorithms for automatic foreground segmentation and multiple object segmentation. Experimental results demonstrate that the proposed shadow-assisted segmentation methods can achieve fully automatic cutout with superior segmentation performance.
DOI: 10.32657/10356/62262
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Theses

Files in This Item:
File Description SizeFormat 
Li Hui.pdf2.63 MBAdobe PDFThumbnail

Page view(s) 50

Updated on Jul 5, 2022

Download(s) 10

Updated on Jul 5, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.