Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387650744> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4387650744 abstract "Generative AI has gained enormous interest nowadays due to new applications like chatGPT, DALL E, Stable Difussion and Deep Fake. Particularly DALL E, Stable Difussion and others (Adobe Firefly, ImagineArt...) are able to create images from a text prompt and are also able to recreate real photographs. Due to this fact, intense research has arisen to create new image forensics applications able to distinguish between real captured images and videos and artificial ones. Detecting forgeries made with Deep Fake is one of the most researched issues. This paper is about another kind of forgery detection. The purpose of this research aims to detect photo realistic AI created images versus real photos coming from a physical camera. For this purpose, techniques that perform a pixel level feature extraction are used. First one is Photo Response Non-Uniformity (PRNU). PRNU is a special noise due to imperfections on the camera sensor that is used for source camera identification. The underlying idea is that AI images will have a different PRNU pattern. Second one is Error level analysis (ELA). This is other type of feature extraction traditionally used for detecting image editions. In fact, ELA is being used nowadays by photographers to detect manually AI created images. Both kinds of features are used to train Convolutional Neural Networks to differentiate between AI images and real photographs. Good results are obtained achieving accuracy rates over 95%. Both extraction methods are carefully assessed by computing precision/recall and F1-score measurements." @default.
- W4387650744 created "2023-10-16" @default.
- W4387650744 creator A5009315212 @default.
- W4387650744 creator A5015382009 @default.
- W4387650744 creator A5093065831 @default.
- W4387650744 date "2023-10-09" @default.
- W4387650744 modified "2023-10-16" @default.
- W4387650744 title "Detection of AI Created Images Using Pixel-wise Feature Extraction and Convolutional Neural Networks" @default.
- W4387650744 doi "https://doi.org/10.20944/preprints202310.0547.v1" @default.
- W4387650744 hasPublicationYear "2023" @default.
- W4387650744 type Work @default.
- W4387650744 citedByCount "0" @default.
- W4387650744 crossrefType "posted-content" @default.
- W4387650744 hasAuthorship W4387650744A5009315212 @default.
- W4387650744 hasAuthorship W4387650744A5015382009 @default.
- W4387650744 hasAuthorship W4387650744A5093065831 @default.
- W4387650744 hasBestOaLocation W43876507441 @default.
- W4387650744 hasConcept C108583219 @default.
- W4387650744 hasConcept C116834253 @default.
- W4387650744 hasConcept C138885662 @default.
- W4387650744 hasConcept C153180895 @default.
- W4387650744 hasConcept C154945302 @default.
- W4387650744 hasConcept C160633673 @default.
- W4387650744 hasConcept C2776401178 @default.
- W4387650744 hasConcept C31972630 @default.
- W4387650744 hasConcept C41008148 @default.
- W4387650744 hasConcept C41895202 @default.
- W4387650744 hasConcept C52622490 @default.
- W4387650744 hasConcept C59822182 @default.
- W4387650744 hasConcept C81363708 @default.
- W4387650744 hasConcept C86803240 @default.
- W4387650744 hasConceptScore W4387650744C108583219 @default.
- W4387650744 hasConceptScore W4387650744C116834253 @default.
- W4387650744 hasConceptScore W4387650744C138885662 @default.
- W4387650744 hasConceptScore W4387650744C153180895 @default.
- W4387650744 hasConceptScore W4387650744C154945302 @default.
- W4387650744 hasConceptScore W4387650744C160633673 @default.
- W4387650744 hasConceptScore W4387650744C2776401178 @default.
- W4387650744 hasConceptScore W4387650744C31972630 @default.
- W4387650744 hasConceptScore W4387650744C41008148 @default.
- W4387650744 hasConceptScore W4387650744C41895202 @default.
- W4387650744 hasConceptScore W4387650744C52622490 @default.
- W4387650744 hasConceptScore W4387650744C59822182 @default.
- W4387650744 hasConceptScore W4387650744C81363708 @default.
- W4387650744 hasConceptScore W4387650744C86803240 @default.
- W4387650744 hasLocation W43876507441 @default.
- W4387650744 hasOpenAccess W4387650744 @default.
- W4387650744 hasPrimaryLocation W43876507441 @default.
- W4387650744 hasRelatedWork W2085033728 @default.
- W4387650744 hasRelatedWork W3029198973 @default.
- W4387650744 hasRelatedWork W3133861977 @default.
- W4387650744 hasRelatedWork W3167935049 @default.
- W4387650744 hasRelatedWork W3193565141 @default.
- W4387650744 hasRelatedWork W4226493464 @default.
- W4387650744 hasRelatedWork W4285411112 @default.
- W4387650744 hasRelatedWork W4293226380 @default.
- W4387650744 hasRelatedWork W4312417841 @default.
- W4387650744 hasRelatedWork W4375867731 @default.
- W4387650744 isParatext "false" @default.
- W4387650744 isRetracted "false" @default.
- W4387650744 workType "article" @default.