Matches in SemOpenAlex for { <https://semopenalex.org/work/W2783140350> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2783140350 abstract "Blur type identification is significant for blind image recovery in image processing area. In this paper, an accurate classification system exploiting Convolution Neural Network (CNN) is designed to identify four blur types of images: defocus blur, Gaussian blur, haze blur and motion blur. A supervised learning model of Simplified-Fast-Alexnet (SFA), which is an abbreviated and modified version of Alexnet, is created to map the input images into a higher dimensional feature space, in which the blurs can be classified accurately. With proportional compressing the output number of each convolution layer in Alexnet by the ratio of 0.5 and removing the first two Full Connected layers (FCs) in Alexnet, the SFA successfully simplifies the Alexnet and overcomes the fatal disadvantage of parameter redundancy. Moreover, the batch normalization layers are added into the designated classifier to replace the dropout method, thus it can accelerate the convergence rate of deep network during the training stage by reducing internal covariate shift as well as alleviate the overfitting problem. Experiments demonstrate the remarkable performance of the suggested approach in comparison with the original Alexnet and the state-of-the-art on the frequently-used Berkeley dataset and Pascal VOC 2007 dataset." @default.
- W2783140350 created "2018-01-26" @default.
- W2783140350 creator A5000432967 @default.
- W2783140350 creator A5009851374 @default.
- W2783140350 creator A5056918757 @default.
- W2783140350 creator A5081990773 @default.
- W2783140350 date "2017-10-01" @default.
- W2783140350 modified "2023-10-14" @default.
- W2783140350 title "Blur image classification based on deep learning" @default.
- W2783140350 cites W1668010126 @default.
- W2783140350 cites W2027231794 @default.
- W2783140350 cites W2029783634 @default.
- W2783140350 cites W2104564430 @default.
- W2783140350 cites W2127235472 @default.
- W2783140350 cites W2128428741 @default.
- W2783140350 cites W2151931211 @default.
- W2783140350 cites W2255344654 @default.
- W2783140350 cites W2294215176 @default.
- W2783140350 cites W2553441888 @default.
- W2783140350 doi "https://doi.org/10.1109/ist.2017.8261503" @default.
- W2783140350 hasPublicationYear "2017" @default.
- W2783140350 type Work @default.
- W2783140350 sameAs 2783140350 @default.
- W2783140350 citedByCount "16" @default.
- W2783140350 countsByYear W27831403502019 @default.
- W2783140350 countsByYear W27831403502020 @default.
- W2783140350 countsByYear W27831403502021 @default.
- W2783140350 countsByYear W27831403502022 @default.
- W2783140350 crossrefType "proceedings-article" @default.
- W2783140350 hasAuthorship W2783140350A5000432967 @default.
- W2783140350 hasAuthorship W2783140350A5009851374 @default.
- W2783140350 hasAuthorship W2783140350A5056918757 @default.
- W2783140350 hasAuthorship W2783140350A5081990773 @default.
- W2783140350 hasConcept C104317376 @default.
- W2783140350 hasConcept C106430172 @default.
- W2783140350 hasConcept C115961682 @default.
- W2783140350 hasConcept C153180895 @default.
- W2783140350 hasConcept C154945302 @default.
- W2783140350 hasConcept C22019652 @default.
- W2783140350 hasConcept C2777708103 @default.
- W2783140350 hasConcept C31972630 @default.
- W2783140350 hasConcept C41008148 @default.
- W2783140350 hasConcept C50644808 @default.
- W2783140350 hasConcept C81363708 @default.
- W2783140350 hasConcept C9417928 @default.
- W2783140350 hasConceptScore W2783140350C104317376 @default.
- W2783140350 hasConceptScore W2783140350C106430172 @default.
- W2783140350 hasConceptScore W2783140350C115961682 @default.
- W2783140350 hasConceptScore W2783140350C153180895 @default.
- W2783140350 hasConceptScore W2783140350C154945302 @default.
- W2783140350 hasConceptScore W2783140350C22019652 @default.
- W2783140350 hasConceptScore W2783140350C2777708103 @default.
- W2783140350 hasConceptScore W2783140350C31972630 @default.
- W2783140350 hasConceptScore W2783140350C41008148 @default.
- W2783140350 hasConceptScore W2783140350C50644808 @default.
- W2783140350 hasConceptScore W2783140350C81363708 @default.
- W2783140350 hasConceptScore W2783140350C9417928 @default.
- W2783140350 hasLocation W27831403501 @default.
- W2783140350 hasOpenAccess W2783140350 @default.
- W2783140350 hasPrimaryLocation W27831403501 @default.
- W2783140350 hasRelatedWork W1769766618 @default.
- W2783140350 hasRelatedWork W2006617887 @default.
- W2783140350 hasRelatedWork W2042244451 @default.
- W2783140350 hasRelatedWork W2094238738 @default.
- W2783140350 hasRelatedWork W2132591835 @default.
- W2783140350 hasRelatedWork W2152301642 @default.
- W2783140350 hasRelatedWork W2354226224 @default.
- W2783140350 hasRelatedWork W2767651786 @default.
- W2783140350 hasRelatedWork W2992709101 @default.
- W2783140350 hasRelatedWork W3195523115 @default.
- W2783140350 isParatext "false" @default.
- W2783140350 isRetracted "false" @default.
- W2783140350 magId "2783140350" @default.
- W2783140350 workType "article" @default.