Matches in SemOpenAlex for { <https://semopenalex.org/work/W2339572040> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2339572040 abstract "Object recognition is a process of identifying a specific object in an image or video sequence. This task is still a challenge for computer vision systems. Many different approaches of object recognition including the traditional classifier or deep neural network were proposed. The objective of this thesis is to implement a deep convolution neural network for object classification. Different architecture and different parameters have been tested in order to improve the classification accuracy. This thesis propose a very simple deep learning network for object classification which comprises only the basic data processing. In the proposed architecture, deep convolution neural network has a total of five hidden layers. After every convolution, there is a subsampling layer which consists of a 2×2 kernel to do average pooling. This can help to reduce the training time and compute complexity of the network. For comparison and better understanding, this work also showed how to fine tune the hyper-parameters of the network in order to obtain a higher degree of classification accuracy. This work achieved a good performance on Cifar-10 dataset where the accuracy is 76.19%. In challenging image databases such as Pascal and ImageNet, this network might not be sufficient to handle the variability. However, deep convolution neural network can be a valuable baseline for studying advanced deep learning architectures for large-scale image classification tasks. This network can be further improved by adding some validation data and dropout to prevent overfitting" @default.
- W2339572040 created "2016-06-24" @default.
- W2339572040 creator A5080492117 @default.
- W2339572040 date "2015-06-01" @default.
- W2339572040 modified "2023-09-27" @default.
- W2339572040 title "Object classification using deep learning" @default.
- W2339572040 hasPublicationYear "2015" @default.
- W2339572040 type Work @default.
- W2339572040 sameAs 2339572040 @default.
- W2339572040 citedByCount "0" @default.
- W2339572040 crossrefType "dissertation" @default.
- W2339572040 hasAuthorship W2339572040A5080492117 @default.
- W2339572040 hasConcept C108583219 @default.
- W2339572040 hasConcept C115961682 @default.
- W2339572040 hasConcept C119857082 @default.
- W2339572040 hasConcept C153180895 @default.
- W2339572040 hasConcept C154945302 @default.
- W2339572040 hasConcept C193415008 @default.
- W2339572040 hasConcept C199360897 @default.
- W2339572040 hasConcept C22019652 @default.
- W2339572040 hasConcept C2776145597 @default.
- W2339572040 hasConcept C2781238097 @default.
- W2339572040 hasConcept C38652104 @default.
- W2339572040 hasConcept C41008148 @default.
- W2339572040 hasConcept C50644808 @default.
- W2339572040 hasConcept C64876066 @default.
- W2339572040 hasConcept C70437156 @default.
- W2339572040 hasConcept C75294576 @default.
- W2339572040 hasConcept C75608658 @default.
- W2339572040 hasConcept C81363708 @default.
- W2339572040 hasConcept C95623464 @default.
- W2339572040 hasConceptScore W2339572040C108583219 @default.
- W2339572040 hasConceptScore W2339572040C115961682 @default.
- W2339572040 hasConceptScore W2339572040C119857082 @default.
- W2339572040 hasConceptScore W2339572040C153180895 @default.
- W2339572040 hasConceptScore W2339572040C154945302 @default.
- W2339572040 hasConceptScore W2339572040C193415008 @default.
- W2339572040 hasConceptScore W2339572040C199360897 @default.
- W2339572040 hasConceptScore W2339572040C22019652 @default.
- W2339572040 hasConceptScore W2339572040C2776145597 @default.
- W2339572040 hasConceptScore W2339572040C2781238097 @default.
- W2339572040 hasConceptScore W2339572040C38652104 @default.
- W2339572040 hasConceptScore W2339572040C41008148 @default.
- W2339572040 hasConceptScore W2339572040C50644808 @default.
- W2339572040 hasConceptScore W2339572040C64876066 @default.
- W2339572040 hasConceptScore W2339572040C70437156 @default.
- W2339572040 hasConceptScore W2339572040C75294576 @default.
- W2339572040 hasConceptScore W2339572040C75608658 @default.
- W2339572040 hasConceptScore W2339572040C81363708 @default.
- W2339572040 hasConceptScore W2339572040C95623464 @default.
- W2339572040 hasLocation W23395720401 @default.
- W2339572040 hasOpenAccess W2339572040 @default.
- W2339572040 hasPrimaryLocation W23395720401 @default.
- W2339572040 hasRelatedWork W1842053956 @default.
- W2339572040 hasRelatedWork W2106665752 @default.
- W2339572040 hasRelatedWork W2234895705 @default.
- W2339572040 hasRelatedWork W2293823684 @default.
- W2339572040 hasRelatedWork W2473449033 @default.
- W2339572040 hasRelatedWork W2901832315 @default.
- W2339572040 hasRelatedWork W2907410141 @default.
- W2339572040 hasRelatedWork W2948808425 @default.
- W2339572040 hasRelatedWork W2963022579 @default.
- W2339572040 hasRelatedWork W2968538124 @default.
- W2339572040 hasRelatedWork W2974265398 @default.
- W2339572040 hasRelatedWork W3005208096 @default.
- W2339572040 hasRelatedWork W3049242142 @default.
- W2339572040 hasRelatedWork W3081370386 @default.
- W2339572040 hasRelatedWork W3091985378 @default.
- W2339572040 hasRelatedWork W3105979354 @default.
- W2339572040 hasRelatedWork W3109689451 @default.
- W2339572040 hasRelatedWork W3148401955 @default.
- W2339572040 hasRelatedWork W2147297298 @default.
- W2339572040 hasRelatedWork W2607240167 @default.
- W2339572040 isParatext "false" @default.
- W2339572040 isRetracted "false" @default.
- W2339572040 magId "2339572040" @default.
- W2339572040 workType "dissertation" @default.