Image de-fencing framework with hybrid inpainting algorithm. Issue 7 (October 2016)
- Record Type:
- Journal Article
- Title:
- Image de-fencing framework with hybrid inpainting algorithm. Issue 7 (October 2016)
- Main Title:
- Image de-fencing framework with hybrid inpainting algorithm
- Authors:
- Farid, Muhammad
Mahmood, Arif
Grangetto, Marco - Abstract:
- Abstract Detection and removal of fences from digital images become essential when an important part of the scene turns to be occluded by such unwanted structures. Image de-fencing is challenging because manually marking fence boundaries is tedious and time-consuming. In this paper, a novel image de-fencing algorithm that effectively detects and removes fences with minimal user input is presented. The user is only requested to mark few fence pixels; then, color models are estimated and used to train Bayes classifier to segment the fence and the background. Finally, the fence mask is refined exploiting connected component analysis and morphological operators. To restore the occluded region, a hybrid inpainting algorithm is proposed that integrates exemplar-based technique with a pyramid-based interpolation approach. In contrast to previous solutions which work only for regular pattern fences, the proposed technique is able to remove both regular and irregular fences. A large number of experiments are carried out on a wide variety of images containing different types of fences demonstrating the effectiveness of the proposed approach. The proposed approach is also compared with state-of-the-art image de-fencing and inpainting techniques and showed convincing results.
- Is Part Of:
- Signal, image and video processing. Volume 10:Issue 7(2016)
- Journal:
- Signal, image and video processing
- Issue:
- Volume 10:Issue 7(2016)
- Issue Display:
- Volume 10, Issue 7 (2016)
- Year:
- 2016
- Volume:
- 10
- Issue:
- 7
- Issue Sort Value:
- 2016-0010-0007-0000
- Page Start:
- 1193
- Page End:
- 1201
- Publication Date:
- 2016-10
- Subjects:
- Image de-fencing -- Object removal -- Fence removal -- Image completion -- Hybrid inpainting
Signal processing -- Digital techniques -- Periodicals
Image processing -- Digital techniques -- Periodicals
Digital video -- Periodicals
621.3822 - Journal URLs:
- http://www.springerlink.com/content/120512/ ↗
http://www.springerlink.com/openurl.asp?genre=journal&issn=1863-1703 ↗
http://www.springer.com/gb/ ↗ - DOI:
- 10.1007/s11760-016-0876-7 ↗
- Languages:
- English
- ISSNs:
- 1863-1703
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 8275.985203
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 9992.xml