Please use this identifier to cite or link to this item:
Title: A learning-based approach to reduce JPEG artifacts in image matting
Authors: Choi, I.
Kim, S.
Brown, M.S. 
Tai, Y.-W.
Keywords: Jpeg Deblocking
Issue Date: 2013
Citation: Choi, I., Kim, S., Brown, M.S., Tai, Y.-W. (2013). A learning-based approach to reduce JPEG artifacts in image matting. Proceedings of the IEEE International Conference on Computer Vision : 2880-2887. ScholarBank@NUS Repository.
Abstract: Single image matting techniques assume high-quality input images. The vast majority of images on the web and in personal photo collections are encoded using JPEG compression. JPEG images exhibit quantization artifacts that adversely affect the performance of matting algorithms. To address this situation, we propose a learning-based post-processing method to improve the alpha mattes extracted from JPEG images. Our approach learns a set of sparse dictionaries from training examples that are used to transfer details from high-quality alpha mattes to alpha mattes corrupted by JPEG compression. Three different dictionaries are defined to accommodate different object structure (long hair, short hair, and sharp boundaries). A back-projection criteria combined within an MRF framework is used to automatically select the best dictionary to apply on the object's local boundary. We demonstrate that our method can produces superior results over existing state-of-the-art matting algorithms on a variety of inputs and compression levels. © 2013 IEEE.
Source Title: Proceedings of the IEEE International Conference on Computer Vision
ISBN: 9781479928392
DOI: 10.1109/ICCV.2013.358
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Mar 16, 2019


checked on Feb 27, 2019

Page view(s)

checked on Feb 9, 2019

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.