Matches in SemOpenAlex for { <https://semopenalex.org/work/W2743704482> ?p ?o ?g. }
- W2743704482 endingPage "157" @default.
- W2743704482 startingPage "144" @default.
- W2743704482 abstract "Abstract Image segmentation is an important step for large-scale image analysis and object recognition. Variational-based segmentation methods are widely studied due to their good performance, but they still suffer from incapability to deal with images bearing weak contrast, overlapped noise and cluttered texture. To tackle this problem, we propose a new statistical information analysis based multi-scale and global optimization method for image segmentation. This multi-scale processing which is consistent with human’s cognition mechanism enables us identify target at coarse scale. The high-level prior is obtained by the multiple Gaussian kernel gray equalization and used as shape constraint in following fine-scale. An efficient energy functional is proposed with convexity and improved TV regularization in order to segment inhomogeneous target from noisy background. A convex relaxation function is explicitly represented by cubic B-Spline basis for fast convergence and intrinsic smooth segmentation. Finally, the energy functional is minimized by standard methods of Split Bregman, Gradient Descent Flow and the corresponding Euler–Lagrange Equation. Experimental results on synthetic and real world images validate the robustness and high accuracy boundaries detection for low contrast, noisy and texture images." @default.
- W2743704482 created "2017-08-17" @default.
- W2743704482 creator A5033906524 @default.
- W2743704482 creator A5046520540 @default.
- W2743704482 creator A5048649183 @default.
- W2743704482 creator A5053453125 @default.
- W2743704482 creator A5074421743 @default.
- W2743704482 creator A5084269743 @default.
- W2743704482 date "2018-01-01" @default.
- W2743704482 modified "2023-10-12" @default.
- W2743704482 title "B-Spline based globally optimal segmentation combining low-level and high-level information" @default.
- W2743704482 cites W1951160674 @default.
- W2743704482 cites W1966935423 @default.
- W2743704482 cites W1968889171 @default.
- W2743704482 cites W1971923777 @default.
- W2743704482 cites W1979393293 @default.
- W2743704482 cites W1982935657 @default.
- W2743704482 cites W1987286789 @default.
- W2743704482 cites W1988907315 @default.
- W2743704482 cites W1991113069 @default.
- W2743704482 cites W1998999283 @default.
- W2743704482 cites W2008009722 @default.
- W2743704482 cites W2010001400 @default.
- W2743704482 cites W2012276822 @default.
- W2743704482 cites W2018319950 @default.
- W2743704482 cites W2038495454 @default.
- W2743704482 cites W2040124524 @default.
- W2743704482 cites W2049783800 @default.
- W2743704482 cites W2051477566 @default.
- W2743704482 cites W2080668963 @default.
- W2743704482 cites W2088293348 @default.
- W2743704482 cites W2092915696 @default.
- W2743704482 cites W2095049733 @default.
- W2743704482 cites W2104095591 @default.
- W2743704482 cites W2114487471 @default.
- W2743704482 cites W2116040950 @default.
- W2743704482 cites W2139478903 @default.
- W2743704482 cites W2142058898 @default.
- W2743704482 cites W2144133758 @default.
- W2743704482 cites W2145803225 @default.
- W2743704482 cites W2149184914 @default.
- W2743704482 cites W2155343350 @default.
- W2743704482 cites W2159152281 @default.
- W2743704482 cites W2165734775 @default.
- W2743704482 cites W2568681932 @default.
- W2743704482 cites W1969993007 @default.
- W2743704482 doi "https://doi.org/10.1016/j.patcog.2017.08.011" @default.
- W2743704482 hasPublicationYear "2018" @default.
- W2743704482 type Work @default.
- W2743704482 sameAs 2743704482 @default.
- W2743704482 citedByCount "12" @default.
- W2743704482 countsByYear W27437044822017 @default.
- W2743704482 countsByYear W27437044822018 @default.
- W2743704482 countsByYear W27437044822019 @default.
- W2743704482 countsByYear W27437044822020 @default.
- W2743704482 countsByYear W27437044822021 @default.
- W2743704482 countsByYear W27437044822022 @default.
- W2743704482 crossrefType "journal-article" @default.
- W2743704482 hasAuthorship W2743704482A5033906524 @default.
- W2743704482 hasAuthorship W2743704482A5046520540 @default.
- W2743704482 hasAuthorship W2743704482A5048649183 @default.
- W2743704482 hasAuthorship W2743704482A5053453125 @default.
- W2743704482 hasAuthorship W2743704482A5074421743 @default.
- W2743704482 hasAuthorship W2743704482A5084269743 @default.
- W2743704482 hasConcept C10390562 @default.
- W2743704482 hasConcept C127413603 @default.
- W2743704482 hasConcept C153180895 @default.
- W2743704482 hasConcept C154945302 @default.
- W2743704482 hasConcept C33923547 @default.
- W2743704482 hasConcept C41008148 @default.
- W2743704482 hasConcept C66938386 @default.
- W2743704482 hasConcept C89600930 @default.
- W2743704482 hasConceptScore W2743704482C10390562 @default.
- W2743704482 hasConceptScore W2743704482C127413603 @default.
- W2743704482 hasConceptScore W2743704482C153180895 @default.
- W2743704482 hasConceptScore W2743704482C154945302 @default.
- W2743704482 hasConceptScore W2743704482C33923547 @default.
- W2743704482 hasConceptScore W2743704482C41008148 @default.
- W2743704482 hasConceptScore W2743704482C66938386 @default.
- W2743704482 hasConceptScore W2743704482C89600930 @default.
- W2743704482 hasFunder F4320321001 @default.
- W2743704482 hasFunder F4320321135 @default.
- W2743704482 hasLocation W27437044821 @default.
- W2743704482 hasOpenAccess W2743704482 @default.
- W2743704482 hasPrimaryLocation W27437044821 @default.
- W2743704482 hasRelatedWork W2005476934 @default.
- W2743704482 hasRelatedWork W2361006516 @default.
- W2743704482 hasRelatedWork W2510758617 @default.
- W2743704482 hasRelatedWork W2753174232 @default.
- W2743704482 hasRelatedWork W2754350655 @default.
- W2743704482 hasRelatedWork W2807253728 @default.
- W2743704482 hasRelatedWork W2897195263 @default.
- W2743704482 hasRelatedWork W3095523211 @default.
- W2743704482 hasRelatedWork W4206076898 @default.
- W2743704482 hasRelatedWork W4226401448 @default.
- W2743704482 hasVolume "73" @default.
- W2743704482 isParatext "false" @default.
- W2743704482 isRetracted "false" @default.