Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200749121> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W3200749121 abstract "This thesis presents a patch-based image classification system in combination with anensemble technique named stacking. In the standard model an image is reshaped into a collectionof patches, from these patches feature vectors are extracted using the Histogram of OrientedGradients (HOG). Then a simple 3-layered multilayer perceptron (MLP) is used for classification.Classification is done by applying the sum voting technique, here the output probabilities of eachpatch in an image are summed up. The image is then assigned to the class with the highest sumof probabilities. During the training of this MLP dropout is applied to prevent the networkfrom overfitting. In the ensemble model an extra MLP is stacked after the usual MLP. Here themaximum, average or minimum output probabilities from all patches in an image are computedand serve as input values for the stacked MLP. Additionally, we varied with a pooling methodthat splits an image into quadrants. The patches of each quadrant are then used to train differentMLPs, the output probabilities of these MLPs serve as input values for the stacked MLP. Tomeasure the accuracy of these models the two widely known image recognition benchmarksMNIST (handwritten digits) and CIFAR-10 (objects) are used for experimentation. The standardmodel shows good performances on the MNIST dataset (99.45% correctly classified images). Theaddition of stacking and/or pooling results in a decrease in accuracy of 0.20-1.63%. On CIFAR-10the standard model also outperformed all other models (68.30%) with a decrease of 1.17-12.97%when stacking and/or pooling is used." @default.
- W3200749121 created "2021-09-27" @default.
- W3200749121 creator A5078949345 @default.
- W3200749121 date "2016-01-01" @default.
- W3200749121 modified "2023-09-23" @default.
- W3200749121 title "The effect of a stacked MLP trained on output probabilities in a patch-based image classification system" @default.
- W3200749121 hasPublicationYear "2016" @default.
- W3200749121 type Work @default.
- W3200749121 sameAs 3200749121 @default.
- W3200749121 citedByCount "0" @default.
- W3200749121 crossrefType "dissertation" @default.
- W3200749121 hasAuthorship W3200749121A5078949345 @default.
- W3200749121 hasConcept C115961682 @default.
- W3200749121 hasConcept C138885662 @default.
- W3200749121 hasConcept C153180895 @default.
- W3200749121 hasConcept C154945302 @default.
- W3200749121 hasConcept C179717631 @default.
- W3200749121 hasConcept C190502265 @default.
- W3200749121 hasConcept C22019652 @default.
- W3200749121 hasConcept C2776401178 @default.
- W3200749121 hasConcept C41008148 @default.
- W3200749121 hasConcept C41895202 @default.
- W3200749121 hasConcept C50644808 @default.
- W3200749121 hasConcept C53533937 @default.
- W3200749121 hasConcept C60908668 @default.
- W3200749121 hasConcept C70437156 @default.
- W3200749121 hasConcept C75294576 @default.
- W3200749121 hasConceptScore W3200749121C115961682 @default.
- W3200749121 hasConceptScore W3200749121C138885662 @default.
- W3200749121 hasConceptScore W3200749121C153180895 @default.
- W3200749121 hasConceptScore W3200749121C154945302 @default.
- W3200749121 hasConceptScore W3200749121C179717631 @default.
- W3200749121 hasConceptScore W3200749121C190502265 @default.
- W3200749121 hasConceptScore W3200749121C22019652 @default.
- W3200749121 hasConceptScore W3200749121C2776401178 @default.
- W3200749121 hasConceptScore W3200749121C41008148 @default.
- W3200749121 hasConceptScore W3200749121C41895202 @default.
- W3200749121 hasConceptScore W3200749121C50644808 @default.
- W3200749121 hasConceptScore W3200749121C53533937 @default.
- W3200749121 hasConceptScore W3200749121C60908668 @default.
- W3200749121 hasConceptScore W3200749121C70437156 @default.
- W3200749121 hasConceptScore W3200749121C75294576 @default.
- W3200749121 hasLocation W32007491211 @default.
- W3200749121 hasOpenAccess W3200749121 @default.
- W3200749121 hasPrimaryLocation W32007491211 @default.
- W3200749121 hasRelatedWork W1560239279 @default.
- W3200749121 hasRelatedWork W1673167037 @default.
- W3200749121 hasRelatedWork W1980740525 @default.
- W3200749121 hasRelatedWork W198996981 @default.
- W3200749121 hasRelatedWork W2024900987 @default.
- W3200749121 hasRelatedWork W2058078594 @default.
- W3200749121 hasRelatedWork W2081936877 @default.
- W3200749121 hasRelatedWork W2119671554 @default.
- W3200749121 hasRelatedWork W2119761601 @default.
- W3200749121 hasRelatedWork W2143460072 @default.
- W3200749121 hasRelatedWork W2156676092 @default.
- W3200749121 hasRelatedWork W2554574477 @default.
- W3200749121 hasRelatedWork W2920922306 @default.
- W3200749121 hasRelatedWork W2948920206 @default.
- W3200749121 hasRelatedWork W3036126916 @default.
- W3200749121 hasRelatedWork W3148304539 @default.
- W3200749121 hasRelatedWork W39061599 @default.
- W3200749121 hasRelatedWork W2752473221 @default.
- W3200749121 hasRelatedWork W2867489393 @default.
- W3200749121 hasRelatedWork W2929599689 @default.
- W3200749121 isParatext "false" @default.
- W3200749121 isRetracted "false" @default.
- W3200749121 magId "3200749121" @default.
- W3200749121 workType "dissertation" @default.