Most of the images captured using optical imaging systems usually contain defocus blur. This blur is caused by a wide aperture that prevents light rays from converging properly when the scene point is not at the camera’s focus distance. Another type of common blur in images is motion blur, which is caused by the relative motion between the camera and scene objects. Blur in images causes the deterioration of the image quality and it is considered an undesirable effect because it leads to the loss of the necessary details required for the scene interpretation. Therefore, automatic detection of blurred and sharp pixels in an image and their classification into respective regions are essential for different image processing and computer vision applications, including but not limited to object detection, scene classification, image segmentation, background blur magnification, depth of field extension and depth estimation.

Blur detection and segmentation for a single image without any prior information is a challenging task. The performance of the blur detection method is affected by a number of challenges. Firstly, traditional low-level features are unable to distinguish blurred regions from the focused regions. Blurred regions do not contain structural information from in-focus smooth regions. Moreover, the edge information between the well-focused region and blurred regions has not been preserved properly. Furthermore, limited datasets are available for deep learning with images having both defocus and motion blur altogether.

The aim of this Special Issue is to solicit original research articles and review articles exploring recent trends in understanding the blur in images. We hope that this Special Issue also gathers research focusing on novel methods, applications in blur detection, and classification. Submissions discussing novel contributions on machine learning, deep learning, and optimization-based methods to detect and classify blurred and nonblurred image pixels are particularly encouraged.

Potential topics include but are not limited to the following:

• Mathematical models for blur detection and classification
• Supervised and unsupervised machine learning-based techniques for blur detection and classification
• Deep learning-based models and methods for blur detection and classification
• Statistical priors-based methods and models for blur detection and classification
• Optimisation based models and techniques for blur detection and classification
• Blur detection and classification for scene classification
• Blur-based image and scene segmentation
• Estimation and segmentation of partial blur in natural images
• Blur-based object detection and recognition
• Three-dimensional (3D) shape from defocus blur
• Blur-based depth estimation and depth enhancement