Edge-aware image filtering using a structure-guided CNN
- Authors
- Kim S.; Song C.; Jang J.; Paik, Joonki
- Issue Date
- 28-Feb-2020
- Publisher
- Institution of Engineering and Technology
- Keywords
- image segmentation; image restoration; computer vision; filtering theory; neural nets; edge detection; feature extraction; image enhancement; image denoising; restoration problems; edge-preserving smoothing; image denoising; edge-aware image filtering; structure-guided; fundamental preprocessing step; accurate computer vision applications; robust computer vision applications; image segmentation; convolutional neural network-based methods; significant edge information; feature extraction layers; deep CNN model; network model; convolution artefact removal; structure extraction network; end-to-end trainable architecture; significant edges; state-of-the-art denoising filters; image enhancement
- Citation
- IET Image Processing, v.14, no.3, pp 472 - 479
- Pages
- 8
- Journal Title
- IET Image Processing
- Volume
- 14
- Number
- 3
- Start Page
- 472
- End Page
- 479
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/38540
- DOI
- 10.1049/iet-ipr.2018.6691
- ISSN
- 1751-9659
1751-9667
- Abstract
- Image filtering is a fundamental preprocessing step for accurate, robust computer vision applications such as image segmentation, object classification, and reconstruction. However, many convolutional neural network (CNN)-based methods tend to lose significant edge information in the output layer, and generate undesired artefacts in the feature extraction layers. This study presents a deep CNN model for edge-aware image filtering. The proposed network model consists of three sub-networks: (i) feature extraction, (ii) convolution artefact removal, and (iii) structure extraction networks. The proposed network model has an end-to-end trainable architecture that does not need any post-processing steps. Especially, the structure extraction network can successfully preserve significant edges. The proposed filter outperforms state-of-the-art denoising filters in terms of both objective and subjective measures, and can be used for various image enhancement and restoration problems such as edge-preserving smoothing, image denoising, deblurring, and deblocking. © The Institution of Engineering and Technology 2019
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School of Advanced Imaging Sciences, Multimedia and Film > Department of Imaging Science and Arts > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/38540)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.