Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312754519> ?p ?o ?g. }
- W4312754519 endingPage "128553" @default.
- W4312754519 startingPage "128543" @default.
- W4312754519 abstract "The number of images produced each day increased significantly. The ability to detect and correct an image’s orientation can provide several advantages in computer vision. This paper presents a new framework based on a transfer learning technique for automatically detecting image orientation. To implement the power of deep neural networks, we applied a convolutional neural network model pre-trained on the ImageNet database for feature extraction. Then, we built a multi-class logistic regression classifier to detect the four image orientation probabilities corresponding to the following orientations (0 for no orientation, 90, 180, and 270). We tested our model on the SUN-397 dataset, one of the most extensive data sets currently used for image-orientation detection tasks. We conducted a cross-dataset evaluation for in-depth testing and analysis. We also examined our model using different old and recent state-of-the-art convolutional neural network (CNN) baselines. We demonstrate that our model yields promising results based on transfer learning for feature extraction combined with a one-vs-rest logistic regression classifier. Our proposed model surpassed the state-of-the-art results in terms of accuracy and performance." @default.
- W4312754519 created "2023-01-05" @default.
- W4312754519 creator A5002247412 @default.
- W4312754519 creator A5031103866 @default.
- W4312754519 date "2022-01-01" @default.
- W4312754519 modified "2023-09-30" @default.
- W4312754519 title "Transfer Learning for Automatic Image Orientation Detection Using Deep Learning and Logistic Regression" @default.
- W4312754519 cites W1556531089 @default.
- W4312754519 cites W1944847058 @default.
- W4312754519 cites W2017814585 @default.
- W4312754519 cites W2023047877 @default.
- W4312754519 cites W2031489346 @default.
- W4312754519 cites W2039788538 @default.
- W4312754519 cites W2059103669 @default.
- W4312754519 cites W2080529918 @default.
- W4312754519 cites W2082261253 @default.
- W4312754519 cites W2105975320 @default.
- W4312754519 cites W2107634464 @default.
- W4312754519 cites W2111046785 @default.
- W4312754519 cites W2114125949 @default.
- W4312754519 cites W2114759000 @default.
- W4312754519 cites W2152161678 @default.
- W4312754519 cites W2157888595 @default.
- W4312754519 cites W2161969291 @default.
- W4312754519 cites W2165698076 @default.
- W4312754519 cites W2194775991 @default.
- W4312754519 cites W2280985394 @default.
- W4312754519 cites W2293149400 @default.
- W4312754519 cites W2323724370 @default.
- W4312754519 cites W2531409750 @default.
- W4312754519 cites W2751770049 @default.
- W4312754519 cites W2963446712 @default.
- W4312754519 cites W3034429256 @default.
- W4312754519 cites W3040752473 @default.
- W4312754519 cites W3135939397 @default.
- W4312754519 cites W3138516171 @default.
- W4312754519 cites W3174907491 @default.
- W4312754519 cites W3176117373 @default.
- W4312754519 cites W4200122203 @default.
- W4312754519 cites W4213149721 @default.
- W4312754519 cites W4280514473 @default.
- W4312754519 cites W4284893453 @default.
- W4312754519 cites W4288064682 @default.
- W4312754519 cites W4312443924 @default.
- W4312754519 doi "https://doi.org/10.1109/access.2022.3225455" @default.
- W4312754519 hasPublicationYear "2022" @default.
- W4312754519 type Work @default.
- W4312754519 citedByCount "2" @default.
- W4312754519 countsByYear W43127545192023 @default.
- W4312754519 crossrefType "journal-article" @default.
- W4312754519 hasAuthorship W4312754519A5002247412 @default.
- W4312754519 hasAuthorship W4312754519A5031103866 @default.
- W4312754519 hasBestOaLocation W43127545191 @default.
- W4312754519 hasConcept C105795698 @default.
- W4312754519 hasConcept C108583219 @default.
- W4312754519 hasConcept C115961682 @default.
- W4312754519 hasConcept C119857082 @default.
- W4312754519 hasConcept C150899416 @default.
- W4312754519 hasConcept C151956035 @default.
- W4312754519 hasConcept C153180895 @default.
- W4312754519 hasConcept C154945302 @default.
- W4312754519 hasConcept C16345878 @default.
- W4312754519 hasConcept C2524010 @default.
- W4312754519 hasConcept C31972630 @default.
- W4312754519 hasConcept C33923547 @default.
- W4312754519 hasConcept C41008148 @default.
- W4312754519 hasConcept C50644808 @default.
- W4312754519 hasConcept C52622490 @default.
- W4312754519 hasConcept C75294576 @default.
- W4312754519 hasConcept C81363708 @default.
- W4312754519 hasConcept C83546350 @default.
- W4312754519 hasConcept C95623464 @default.
- W4312754519 hasConceptScore W4312754519C105795698 @default.
- W4312754519 hasConceptScore W4312754519C108583219 @default.
- W4312754519 hasConceptScore W4312754519C115961682 @default.
- W4312754519 hasConceptScore W4312754519C119857082 @default.
- W4312754519 hasConceptScore W4312754519C150899416 @default.
- W4312754519 hasConceptScore W4312754519C151956035 @default.
- W4312754519 hasConceptScore W4312754519C153180895 @default.
- W4312754519 hasConceptScore W4312754519C154945302 @default.
- W4312754519 hasConceptScore W4312754519C16345878 @default.
- W4312754519 hasConceptScore W4312754519C2524010 @default.
- W4312754519 hasConceptScore W4312754519C31972630 @default.
- W4312754519 hasConceptScore W4312754519C33923547 @default.
- W4312754519 hasConceptScore W4312754519C41008148 @default.
- W4312754519 hasConceptScore W4312754519C50644808 @default.
- W4312754519 hasConceptScore W4312754519C52622490 @default.
- W4312754519 hasConceptScore W4312754519C75294576 @default.
- W4312754519 hasConceptScore W4312754519C81363708 @default.
- W4312754519 hasConceptScore W4312754519C83546350 @default.
- W4312754519 hasConceptScore W4312754519C95623464 @default.
- W4312754519 hasFunder F4320323771 @default.
- W4312754519 hasLocation W43127545191 @default.
- W4312754519 hasOpenAccess W4312754519 @default.
- W4312754519 hasPrimaryLocation W43127545191 @default.
- W4312754519 hasRelatedWork W2279398222 @default.
- W4312754519 hasRelatedWork W2996856019 @default.
- W4312754519 hasRelatedWork W3012393889 @default.