Defocus and Motion Blur Detection with Deep Contextual Features. (24th October 2018)

• Record Type: Journal Article
• Authors: Kim, Beomseok; Son, Hyeongseok; Park, Seong‐Jin; Cho, Sunghyun; Lee, Seungyong
• Is Part Of: Computer graphics forum. Volume 37:Number 7(2018)
• Page Start: 277
• Page End: 288
• Publication Date: 2018-10-24
• Subjects: CCS Concepts -- Computing methodologies → Image processing; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.13567
• Languages: English
• ISSNs: 0167-7055

Abstract

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.