dc.contributor.authorLi, Hui
dc.date.accessioned2015-03-12T08:27:56Z
dc.date.accessioned2017-07-23T08:30:22Z
dc.date.available2015-03-12T08:27:56Z
dc.date.available2017-07-23T08:30:22Z
dc.date.copyright2015en_US
dc.date.issued2015
dc.identifier.citationLi, H. (2015). Semantic image segmentation and evaluation. Master's thesis, Nanyang Technological University, Singapore.
dc.identifier.urihttp://hdl.handle.net/10356/62262
dc.description.abstractThough 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.en_US
dc.format.extent65 p.en_US
dc.language.isoenen_US
dc.subjectDRNTU::Engineering::Computer science and engineeringen_US
dc.titleSemantic image segmentation and evaluationen_US
dc.typeThesis
dc.contributor.schoolSchool of Computer Engineering
dc.contributor.supervisorZheng Jianmin
dc.contributor.supervisorCai Jianfeien_US
dc.description.degreeMASTER OF ENGINEERING (SCE)en_US
dc.identifier.doihttps://doi.org/10.32657/10356/62262


Files in this item

FilesSizeFormatView
Li Hui.pdf2.690Mbapplication/pdfView/Open

This item appears in the following Collection(s)

Show simple item record