Matches in SemOpenAlex for { <https://semopenalex.org/work/W1505315132> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W1505315132 abstract "As one of the most popular deep learning models, convolution neural network (CNN) has achieved huge success in image information extraction. Traditionally CNN is trained by supervised learning method with labeled data and used as a classifier by adding a classification layer in the end. Its capability of extracting image features is largely limited due to the difficulty of setting up a large training dataset. In this paper, we propose a new unsupervised learning CNN model, which uses a so-called convolutional sparse auto-encoder (CSAE) algorithm pre-train the CNN. Instead of using labeled natural images for CNN training, the CSAE algorithm can be used to train the CNN with unlabeled artificial images, which enables easy expansion of training data and unsupervised learning. The CSAE algorithm is especially designed for extracting complex features from specific objects such as Chinese characters. After the features of articficial images are extracted by the CSAE algorithm, the learned parameters are used to initialize the first CNN convolutional layer, and then the CNN model is fine-trained by scene image patches with a linear classifier. The new CNN model is applied to Chinese scene text detection and is evaluated with a multilingual image dataset, which labels Chinese, English and numerals texts separately. More than 10% detection precision gain is observed over two CNN models." @default.
- W1505315132 created "2016-06-24" @default.
- W1505315132 creator A5006414413 @default.
- W1505315132 creator A5011789645 @default.
- W1505315132 creator A5019708391 @default.
- W1505315132 creator A5044769501 @default.
- W1505315132 creator A5074339191 @default.
- W1505315132 creator A5088322622 @default.
- W1505315132 date "2015-07-01" @default.
- W1505315132 modified "2023-09-25" @default.
- W1505315132 title "A new unsupervised convolutional neural network model for Chinese scene text detection" @default.
- W1505315132 cites W2014286161 @default.
- W1505315132 cites W2048878808 @default.
- W1505315132 cites W2069816967 @default.
- W1505315132 cites W2096820674 @default.
- W1505315132 cites W2100556411 @default.
- W1505315132 cites W2101926813 @default.
- W1505315132 cites W2117259536 @default.
- W1505315132 cites W2120831521 @default.
- W1505315132 cites W2131163834 @default.
- W1505315132 cites W2131447359 @default.
- W1505315132 cites W2140132917 @default.
- W1505315132 cites W2142082467 @default.
- W1505315132 cites W2142159465 @default.
- W1505315132 cites W2162741153 @default.
- W1505315132 cites W2165569569 @default.
- W1505315132 doi "https://doi.org/10.1109/chinasip.2015.7230438" @default.
- W1505315132 hasPublicationYear "2015" @default.
- W1505315132 type Work @default.
- W1505315132 sameAs 1505315132 @default.
- W1505315132 citedByCount "12" @default.
- W1505315132 countsByYear W15053151322016 @default.
- W1505315132 countsByYear W15053151322017 @default.
- W1505315132 countsByYear W15053151322018 @default.
- W1505315132 countsByYear W15053151322020 @default.
- W1505315132 countsByYear W15053151322021 @default.
- W1505315132 countsByYear W15053151322022 @default.
- W1505315132 crossrefType "proceedings-article" @default.
- W1505315132 hasAuthorship W1505315132A5006414413 @default.
- W1505315132 hasAuthorship W1505315132A5011789645 @default.
- W1505315132 hasAuthorship W1505315132A5019708391 @default.
- W1505315132 hasAuthorship W1505315132A5044769501 @default.
- W1505315132 hasAuthorship W1505315132A5074339191 @default.
- W1505315132 hasAuthorship W1505315132A5088322622 @default.
- W1505315132 hasConcept C153180895 @default.
- W1505315132 hasConcept C154945302 @default.
- W1505315132 hasConcept C204321447 @default.
- W1505315132 hasConcept C41008148 @default.
- W1505315132 hasConcept C81363708 @default.
- W1505315132 hasConceptScore W1505315132C153180895 @default.
- W1505315132 hasConceptScore W1505315132C154945302 @default.
- W1505315132 hasConceptScore W1505315132C204321447 @default.
- W1505315132 hasConceptScore W1505315132C41008148 @default.
- W1505315132 hasConceptScore W1505315132C81363708 @default.
- W1505315132 hasLocation W15053151321 @default.
- W1505315132 hasOpenAccess W1505315132 @default.
- W1505315132 hasPrimaryLocation W15053151321 @default.
- W1505315132 hasRelatedWork W2175746458 @default.
- W1505315132 hasRelatedWork W2732542196 @default.
- W1505315132 hasRelatedWork W2738221750 @default.
- W1505315132 hasRelatedWork W2758063741 @default.
- W1505315132 hasRelatedWork W2760085659 @default.
- W1505315132 hasRelatedWork W2912288872 @default.
- W1505315132 hasRelatedWork W3012978760 @default.
- W1505315132 hasRelatedWork W3081496756 @default.
- W1505315132 hasRelatedWork W3093612317 @default.
- W1505315132 hasRelatedWork W4304820710 @default.
- W1505315132 isParatext "false" @default.
- W1505315132 isRetracted "false" @default.
- W1505315132 magId "1505315132" @default.
- W1505315132 workType "article" @default.