FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289861079> ?p ?o ?g. }

• W4289861079 endingPage "1611" @default.
• W4289861079 startingPage "1611" @default.
• W4289861079 abstract "In the arena of image forensics, detecting manipulations in an image is extremely significant because of the use of images in different fields. Various detection techniques have been suggested in the literature that are based on digging out the features from images to unveil the traces left by manipulation operations. In this paper, a deep learning-based approach is proposed in which a residual network is used to learn deep, complex features from preprocessed images for classification into authentic and forged images. There is statistical symmetry in similar types of images and asymmetry in different types of images. The proposed scheme can highlight the statistical asymmetry between authentic and forged images. In the proposed scheme, firstly, an RGB image is analyzed for different JPEG compression levels. The obtained difference between the error levels is used to extract enhanced LBP code. Then, the scale- and direction-invariant LBP (SD-LBP) code is transformed into SD-LBP feature maps to feed to a deep residual network. Next, the concept of explainable artificial intelligence (XAI) is used to help provide explanations and interpret the output, thereby raising the credibility of the proposed approach. The unique feature selection approach employed is the kernel SHAP method, which is focused on the Shapley values. This technique is used to pinpoint the specific characteristics that are responsible for the aberrant behavior of the forged images dataset. Later, the deep learning-based model is trained and validated using these feature sets. A pre-activation version of ResNet-50 architecture is used that achieved an accuracy of 99.31%, 99.52%, 98.05%, and 99.10% on CASIA v1, CASIA v2, IMD 2020, and DVMM datasets, respectively. The capability of the pretrained residual network and rich textural features, which are scale- and direction-invariant, helps to expand the detection accuracy of the proposed approach. The results confirmed that the method either produced competitive results or outperformed existing methods." @default.
• W4289861079 created "2022-08-05" @default.
• W4289861079 creator A5005595837 @default.
• W4289861079 creator A5035473732 @default.
• W4289861079 creator A5057787794 @default.
• W4289861079 creator A5089058934 @default.
• W4289861079 date "2022-08-05" @default.
• W4289861079 modified "2023-09-30" @default.
• W4289861079 title "Using XAI for Deep Learning-Based Image Manipulation Detection with Shapley Additive Explanation" @default.
• W4289861079 cites W1971111339 @default.
• W4289861079 cites W2129964868 @default.
• W4289861079 cites W2169439181 @default.
• W4289861079 cites W2194775991 @default.
• W4289861079 cites W2345213863 @default.
• W4289861079 cites W2345283083 @default.
• W4289861079 cites W2600000323 @default.
• W4289861079 cites W2612190542 @default.
• W4289861079 cites W2770456481 @default.
• W4289861079 cites W2792595326 @default.
• W4289861079 cites W2887063112 @default.
• W4289861079 cites W2891503716 @default.
• W4289861079 cites W2902301960 @default.
• W4289861079 cites W2905347572 @default.
• W4289861079 cites W2962772482 @default.
• W4289861079 cites W3000649475 @default.
• W4289861079 cites W3015070991 @default.
• W4289861079 cites W3021904838 @default.
• W4289861079 cites W3026256782 @default.
• W4289861079 cites W3027377338 @default.
• W4289861079 cites W3103753223 @default.
• W4289861079 cites W3182830746 @default.
• W4289861079 cites W4220844375 @default.
• W4289861079 cites W4224959664 @default.
• W4289861079 cites W4225137962 @default.
• W4289861079 doi "https://doi.org/10.3390/sym14081611" @default.
• W4289861079 hasPublicationYear "2022" @default.
• W4289861079 type Work @default.
• W4289861079 citedByCount "4" @default.
• W4289861079 countsByYear W42898610792022 @default.
• W4289861079 countsByYear W42898610792023 @default.
• W4289861079 crossrefType "journal-article" @default.
• W4289861079 hasAuthorship W4289861079A5005595837 @default.
• W4289861079 hasAuthorship W4289861079A5035473732 @default.
• W4289861079 hasAuthorship W4289861079A5057787794 @default.
• W4289861079 hasAuthorship W4289861079A5089058934 @default.
• W4289861079 hasBestOaLocation W42898610791 @default.
• W4289861079 hasConcept C108583219 @default.
• W4289861079 hasConcept C11413529 @default.
• W4289861079 hasConcept C115961682 @default.
• W4289861079 hasConcept C138885662 @default.
• W4289861079 hasConcept C153180895 @default.
• W4289861079 hasConcept C154945302 @default.
• W4289861079 hasConcept C155512373 @default.
• W4289861079 hasConcept C177264268 @default.
• W4289861079 hasConcept C199360897 @default.
• W4289861079 hasConcept C2776401178 @default.
• W4289861079 hasConcept C2776760102 @default.
• W4289861079 hasConcept C31972630 @default.
• W4289861079 hasConcept C41008148 @default.
• W4289861079 hasConcept C41895202 @default.
• W4289861079 hasConcept C61265191 @default.
• W4289861079 hasConceptScore W4289861079C108583219 @default.
• W4289861079 hasConceptScore W4289861079C11413529 @default.
• W4289861079 hasConceptScore W4289861079C115961682 @default.
• W4289861079 hasConceptScore W4289861079C138885662 @default.
• W4289861079 hasConceptScore W4289861079C153180895 @default.
• W4289861079 hasConceptScore W4289861079C154945302 @default.
• W4289861079 hasConceptScore W4289861079C155512373 @default.
• W4289861079 hasConceptScore W4289861079C177264268 @default.
• W4289861079 hasConceptScore W4289861079C199360897 @default.
• W4289861079 hasConceptScore W4289861079C2776401178 @default.
• W4289861079 hasConceptScore W4289861079C2776760102 @default.
• W4289861079 hasConceptScore W4289861079C31972630 @default.
• W4289861079 hasConceptScore W4289861079C41008148 @default.
• W4289861079 hasConceptScore W4289861079C41895202 @default.
• W4289861079 hasConceptScore W4289861079C61265191 @default.
• W4289861079 hasFunder F4320322120 @default.
• W4289861079 hasIssue "8" @default.
• W4289861079 hasLocation W42898610791 @default.
• W4289861079 hasOpenAccess W4289861079 @default.
• W4289861079 hasPrimaryLocation W42898610791 @default.
• W4289861079 hasRelatedWork W2076289882 @default.
• W4289861079 hasRelatedWork W2083751184 @default.
• W4289861079 hasRelatedWork W2168562287 @default.
• W4289861079 hasRelatedWork W2341400081 @default.
• W4289861079 hasRelatedWork W2345915074 @default.
• W4289861079 hasRelatedWork W2369998053 @default.
• W4289861079 hasRelatedWork W2786306966 @default.
• W4289861079 hasRelatedWork W4210680147 @default.
• W4289861079 hasRelatedWork W4244083225 @default.
• W4289861079 hasRelatedWork W4281928084 @default.
• W4289861079 hasVolume "14" @default.
• W4289861079 isParatext "false" @default.
• W4289861079 isRetracted "false" @default.
• W4289861079 workType "article" @default.