We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Defocus and Motion Blur Detection with Deep Contextual Features.
- Authors
Kim, Beomseok; Son, Hyeongseok; Park, Seong‐Jin; Cho, Sunghyun; Lee, Seungyong
- Abstract
We propose a novel approach for detecting two kinds of partial blur, defocus and motion blur, by training a deep convolutional neural network. Existing blur detection methods concentrate on designing low‐level features, but those features have difficulty in detecting blur in homogeneous regions without enough textures or edges. To handle such regions, we propose a deep encoder‐decoder network with long residual skip‐connections and multi‐scale reconstruction loss functions to exploit high‐level contextual features as well as low‐level structural features. Another difficulty in partial blur detection is that there are no available datasets with images having both defocus and motion blur together, as most existing approaches concentrate only on either defocus or motion blur. To resolve this issue, we construct a synthetic dataset that consists of complex scenes with both types of blur. Experimental results show that our approach effectively detects and classifies blur, outperforming other state‐of‐the‐art methods. Our method can be used for various applications, such as photo editing, blur magnification, and deblurring.
- Subjects
ARTIFICIAL neural networks; IMAGE processing; MOTION analysis; MAGNIFICATION (Optics); TEXTURE (Art)
- Publication
Computer Graphics Forum, 2018, Vol 37, Issue 7, p277
- ISSN
0167-7055
- Publication type
Article
- DOI
10.1111/cgf.13567