Light Filed Image Quality Assessment by Local and Global Features of Epipolar Plane Image
Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45) › 32_Refereed conference paper (with ISBN/ISSN) › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
| Original language | English |
|---|---|
| Title of host publication | 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM) |
| Publisher | IEEE |
| ISBN (Electronic) | 9781538653210 |
| Publication status | Published - Sep 2018 |
Publication series
| Name | IEEE International Conference on Multimedia Big Data (BigMM) |
|---|---|
| Publisher | IEEE |
Conference
| Title | 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM) |
|---|---|
| Place | China |
| City | Xi'an |
| Period | 13 - 16 September 2018 |
Link(s)
Abstract
Light field, as a popular representation of three-dimensional scenes, attracted much attention in the research community recently. For light field images, various processing operations might degrade the image quality. In this work, we propose a visual quality assessment method for light field images (LFIs) based on local and global features of epipolar plane images (EPIs). It is known that EPI reflects the relationship among LFIs in both 2D spatial domain (x, y) and angular domain (s, t). We use gradient magnitude similarity to compute the local visual quality variations of LFIs. Additionally, the global structure features are extracted to predict the global variations for LFIs. The final quality score of LFIs is calculated by combining the local and global variations. Experimental results show that the proposed method can obtain consistent results of visual quality assessment for LFIs with human ratings.
Research Area(s)
- epipolar plane images (EPIs), Light field image (LFI), visual quality assessment
Citation Format(s)
Light Filed Image Quality Assessment by Local and Global Features of Epipolar Plane Image. / Fang, Yuming; Wei, Kangkang; Hou, Junhui et al.
2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM). IEEE, 2018. 8499086 (IEEE International Conference on Multimedia Big Data (BigMM)).Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45) › 32_Refereed conference paper (with ISBN/ISSN) › peer-review
