Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386850096> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4386850096 endingPage "472" @default.
- W4386850096 startingPage "459" @default.
- W4386850096 abstract "Deep Convolutional Neural Networks (CNNs) have achieved high accuracy in image classification tasks, however, most existing models are trained on high-quality images that are not subject to image degradation. In practice, images are often affected by various types of degradation which can significantly impact the performance of CNNs. In this work, we investigate the influence of image degradation on three typical image classification CNNs and propose a Degradation Type Adaptive Image Classification Model (DTA-ICM) to improve the existing CNNs’ classification accuracy on degraded images. The proposed DTA-ICM comprises two key components: a Degradation Type Predictor (DTP) and a Degradation Type Specified Image Classifier (DTS-IC) set, which is trained on existing CNNs for specified types of degradation. The DTP predicts the degradation type of a test image, and the corresponding DTS-IC is then selected to classify the image. We evaluate the performance of both the proposed DTP and the DTA-ICM on the Caltech 101 database. The experimental results demonstrate that the proposed DTP achieves an average accuracy of 99.70%. Moreover, the proposed DTA-ICM, based on AlexNet, VGG19, and ResNet152, exhibits an average accuracy improvement of 20.63%, 18.22%, and 12.9%, respectively, compared with the original CNNs in classifying degraded images. It suggests that the proposed DTA-ICM can effectively improve the classification performance of existing CNNs on degraded images, which has important practical implications." @default.
- W4386850096 created "2023-09-20" @default.
- W4386850096 creator A5004371292 @default.
- W4386850096 creator A5024023248 @default.
- W4386850096 creator A5032024117 @default.
- W4386850096 creator A5034382078 @default.
- W4386850096 creator A5046597133 @default.
- W4386850096 creator A5066570148 @default.
- W4386850096 date "2024-01-01" @default.
- W4386850096 modified "2023-09-27" @default.
- W4386850096 title "A Degradation Type Adaptive and Deep CNN-Based Image Classification Model for Degraded Images" @default.
- W4386850096 doi "https://doi.org/10.32604/cmes.2023.029084" @default.
- W4386850096 hasPublicationYear "2024" @default.
- W4386850096 type Work @default.
- W4386850096 citedByCount "0" @default.
- W4386850096 crossrefType "journal-article" @default.
- W4386850096 hasAuthorship W4386850096A5004371292 @default.
- W4386850096 hasAuthorship W4386850096A5024023248 @default.
- W4386850096 hasAuthorship W4386850096A5032024117 @default.
- W4386850096 hasAuthorship W4386850096A5034382078 @default.
- W4386850096 hasAuthorship W4386850096A5046597133 @default.
- W4386850096 hasAuthorship W4386850096A5066570148 @default.
- W4386850096 hasBestOaLocation W43868500961 @default.
- W4386850096 hasConcept C115961682 @default.
- W4386850096 hasConcept C153180895 @default.
- W4386850096 hasConcept C154945302 @default.
- W4386850096 hasConcept C2779679103 @default.
- W4386850096 hasConcept C41008148 @default.
- W4386850096 hasConcept C50644808 @default.
- W4386850096 hasConcept C75294576 @default.
- W4386850096 hasConcept C76155785 @default.
- W4386850096 hasConcept C81363708 @default.
- W4386850096 hasConcept C95623464 @default.
- W4386850096 hasConceptScore W4386850096C115961682 @default.
- W4386850096 hasConceptScore W4386850096C153180895 @default.
- W4386850096 hasConceptScore W4386850096C154945302 @default.
- W4386850096 hasConceptScore W4386850096C2779679103 @default.
- W4386850096 hasConceptScore W4386850096C41008148 @default.
- W4386850096 hasConceptScore W4386850096C50644808 @default.
- W4386850096 hasConceptScore W4386850096C75294576 @default.
- W4386850096 hasConceptScore W4386850096C76155785 @default.
- W4386850096 hasConceptScore W4386850096C81363708 @default.
- W4386850096 hasConceptScore W4386850096C95623464 @default.
- W4386850096 hasIssue "1" @default.
- W4386850096 hasLocation W43868500961 @default.
- W4386850096 hasOpenAccess W4386850096 @default.
- W4386850096 hasPrimaryLocation W43868500961 @default.
- W4386850096 hasRelatedWork W2563096758 @default.
- W4386850096 hasRelatedWork W2742991909 @default.
- W4386850096 hasRelatedWork W2767651786 @default.
- W4386850096 hasRelatedWork W2912288872 @default.
- W4386850096 hasRelatedWork W2936488316 @default.
- W4386850096 hasRelatedWork W2972035100 @default.
- W4386850096 hasRelatedWork W4225852842 @default.
- W4386850096 hasRelatedWork W4306753247 @default.
- W4386850096 hasRelatedWork W4386053843 @default.
- W4386850096 hasRelatedWork W3158004940 @default.
- W4386850096 hasVolume "138" @default.
- W4386850096 isParatext "false" @default.
- W4386850096 isRetracted "false" @default.
- W4386850096 workType "article" @default.