Detection and segmentation of defocus blur is a challenging task in digital imaging applications as the blurry images comprise of blur and sharp regions that wrap significant information and require effective methods for information extraction.Existing defocus blur detection and segmentation methods have several limitations i.e.,discriminating sharp smo-oth and blurred smooth regions,low recognition rate in noisy images,and high computational cost without having any prior knowledge of images i.e.,blur degree and camera configura-tion.Hence,there exists a dire need to develop an effective method for defocus blur detection,and segmentation robust to the above-mentioned limitations.This paper presents a novel features descriptor local directional mean patterns(LDMP)for defocus blur detection and employ KNN matting over the detected LDMP-Trimap for the robust segmentation of sharp and blur regions.We argue/hypothesize that most of the image fields located in blurry regions have significantly less specific local patterns than those in the sharp regions,therefore,pro-posed LDMP features descriptor should reliably detect the defo-cus blurred regions.The fusion of LDMP features with KNN matting provides superior performance in terms of obtaining high-quality segmented regions in the image.Additionally,the proposed LDMP features descriptor is robust to noise and successfully detects defocus blur in high-dense noisy images.Experimental results on Shi and Zhao datasets demonstrate the effectiveness of the proposed method in terms of defocus blur detection.Evaluation and comparative analysis signify that our method achieves superior segmentation performance and low computational cost of 15 seconds.

Awais KHAN;Aun IRTAZA;Ali JAVED;Tahira NAZIR;Hafiz MALIK;Khalid Mahmood MALIK;Muhammad Ammar KHAN

Department of Computer Science,University of Engineering and Technology,Taxila 47050,Pakistan;Department of Electrical and Computer Engineering,University of Michigan,Dearborn,MI 48128,USA;Department of Software Engineering,University of Engineering and Technology,Taxila 47050,Pakistan;Department of Computer Science and Engineering,Oakland University,MI 48309,USA

计算机科学前沿

[1]Awais KHAN;Aun IRTAZA;Ali JAVED;Tahira NAZIR;Hafiz MALIK;Khalid Mahmood MALIK;Muhammad Ammar KHAN-.Defocus blur detection using novel local directional mean patterns(LDMP)and segmentation via KNN matting)[J].计算机科学前沿,2022(02):104-116

LDMP,smo,oth,Trimap,defo

Defocus,detection,using,novel,local,directional,mean,patterns,segmentation,via,KNN,matting,Detection,defocus,challenging,task,digital,imaging,applications,blurry,images,comprise,sharp,regions,that,wrap,information,require,methods,extraction,Existing,have,several,limitations,discriminating,blurred,smooth,low,recognition,noisy,high,computational,cost,without,having,any,prior,knowledge,degree,camera,configura,Hence,exists,need,develop,robust,above,mentioned,This,paper,presents,features,descriptor,employ,over,detected,We,argue,hypothesize,most,fields,located,significantly,less,specific,than,those,therefore,should,reliably,fusion,provides,superior,performance,terms,obtaining,quality,segmented,Additionally,proposed,noise,successfully,detects,dense,Experimental,results,Shi,Zhao,datasets,demonstrate,effectiveness,Evaluation,comparative,analysis,signify,our,achieves,seconds

0.437733