Analysis of Blur Measure Operators for Single Image Blur Segmentation

Abstract

Blur detection and segmentation for a single image without any prior information is a challenging task. Numerous techniques for blur detection and segmentation have been proposed in the literature to ultimately restore the sharp images. These techniques use different blur measures in different settings, and in all of them, blur measure plays a central role among all other steps. Blur measure operators have not been analyzed comparatively for both of the spatially-variant defocus and motion blur cases. In this paper, we provide the performance analysis of the state-of-the-art blur measure operators under a unified framework for blur segmentation. A large number of blur measure operators are considered for applying on a diverse set of real blurry images affected by different types and levels of blur and noise. The initial blur maps then are segmented into blurred and non-blurred regions. In order to test the performance of blur measure operators in segmentation process in equal terms, it is crucial to consider the same intermediate steps involved in the blur segmentation process for all of the blur measure operators. The performance of the operators is evaluated by using various qualitative measures. Results reveal that the blur measure operators perform well under certain condition and factors. However, it has been observed that some operators perform adequately overall well or worse against almost all imperfections that prevail over the real-world images.

Automatic detection of simulated motion blur in mammograms

“…Blur measure (BM) operators are mathematical features that quantify blur in a pixel neighborhood. In this study, we examined 28 BM operators from an extensive review of the state‐of‐the‐art and analyzed their performance when distinguishing various levels of blur in mammograms. BM operators are divided into broad families based on their working principle, including Gradient‐based, Laplacian‐based, Statistics‐based, Wavelet‐based, Discrete‐cosine‐transform‐based (DCT), and miscellaneous operators (Table ).…”

“…BM operators are divided into broad families based on their working principle, including Gradient‐based, Laplacian‐based, Statistics‐based, Wavelet‐based, Discrete‐cosine‐transform‐based (DCT), and miscellaneous operators (Table ). Feature‐specific parameters used for computing the BM operators were the same ones proposed by Pertuz et al and Ali et al (See Appendix S2).…”

“…Lower blur measurements imply a greater amount of detected blur as defined in the equations of the BM operators. 19,20 The differences arise from the different sizes of the blur PSF masks used in the two databases due to the intrinsic differences in pixel resolution. DDSM has a higher resolution of 43.5 microns per pixel compared to the 70-micron pixel resolution in INbreast, and since simulated tissue motion is in millimeters, the blur PSF masks for DDSM must have more pixels than the masks for INbreast for a given amount of tissue motion.…”

Untitled

“…Since input is discrete, algorithm suffers from quantization error which was removed with the use of continuous values. Ali and Mahmood [3] has proposed IQR based blur classification in which they have used initial blur, normalization and IQR for blur segmentation as well as classification. There is another way of distinguish blur image from unblur image.…”

Image Dehazing Based on (CMTnet) Cascaded Multi-scale Convolutional Neural Networks and Efficient Light Estimation Algorithm

“…Calculate blurriness map by using equation 3 For measuring blur amount on an image, various techniques have been proposed in the literature. Usman et al [37] discussed and evaluated more than thirty blur measure operators. They showed that "Gradient Energy" is one of the best operators in terms of measure and precision; thus, we choose it to estimate the initial blur map.…”