Abstract
Blur region detection from a single image with spatially-varying blur is a challenging task. Although many methods are proposed in the past decades, most of them are based on hand-crafted features. These features are not robust to image context, image size, blur type and other factors, which cannot obtain sound performance. In addition, the craft of these features requires a lot of domain knowledge. To address these problems, in this paper, a blur region detection method based on semantic segmentation is proposed to extract blur regions, which well integrates global image-level context and cross-layer context information making the auto-learned features more robust. Specifically, we design a blur detection net (BDNet) for blur detection by combining ResNets and FCNs. A binary mask can be produced in an end-to-end way. By our method, the mean region intersection over union (Mean IoU) increased by nearly 20% compared with most other blur detection methods. We make the code publicly available at https://github.com/SEU-DongHan/BDNet.
Highlights
Blur can be regarded as one type of photo degradation caused by many factors in the process of photo acquisition or post-processing
To overcome the aforementioned two issues, we propose a novel deep neural network called blur detection net (BDNet) by fusing the ResNets and FCNs
We review related work on blur detection, deep neural networks and semantic segmentation based on convolutional neural network
Summary
Blur can be regarded as one type of photo degradation caused by many factors in the process of photo acquisition or post-processing. Blur leads to the loss of details and prevents people from obtaining the information of the real scene captured by the image quickly and accurately. There are two common types of blur phenomenon, named motion blur and defocus (out of focus). The former is mainly caused by camera relative motion during exposure and the latter is caused by lens aberrations [1]. With the rapid development of computer vision techniques, image content understanding has become a hot research field, and it becomes essential to uncover the information immersed in the blurred image. Efficient and effective extraction of blur regions can naturally benefit many applications, including scene classification, object detection, image quality assessment, image restoration [2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
