Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376141036> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4376141036 abstract "Abstract Scene text detection is challenging due to variations in text appearance, backgrounds, and orientations. It is necessary to improve robustness, accuracy, and efficiency for applications like OCR, image understanding, and autonomous vehicles. The combination of Generative Adversarial Network (GAN) and Network Variational Autoencoder (VAE) has the potential to create a more robust and powerful text detection network. The proposed network comprises three modules: the VAE module, the GAN module, and the text detection module. The VAE module generates diverse and variable text regions, while the GAN module refines and enhances these regions to make them more realistic and accurate. The text detection module is responsible for detecting text regions in the input image and assigning a confidence score to each region. During training, the entire network is trained end-to-end to minimize a joint loss function, which includes the VAE loss, the GAN loss, and the text detection loss. The VAE loss ensures that the generated text regions are diverse and variable, while the GAN loss ensures that the generated text regions are realistic and accurate. The text detection loss guarantees that the network can detect text regions in the input image with high accuracy. The proposed method employs an encoder-decoder structure in the VAE module and a generator-discriminator structure in the GAN module. The generated text regions are refined and enhanced by the GAN module to produce more accurate results. The text detection module then identifies the text regions with high confidence scores. The proposed network is tested on several datasets, including Total-Text, CTW1500, ICDAR 2015, ICDAR 2017, ReCTS, TD500, COCO-Text, SynthText, Street View Text, and KIAST Scene Text and achieved promising results." @default.
- W4376141036 created "2023-05-12" @default.
- W4376141036 creator A5070978005 @default.
- W4376141036 date "2023-05-10" @default.
- W4376141036 modified "2023-09-30" @default.
- W4376141036 title "End-to-End Training of VAE-GAN Network for Text Detection" @default.
- W4376141036 cites W2144554289 @default.
- W4376141036 cites W2786298913 @default.
- W4376141036 cites W2786962101 @default.
- W4376141036 cites W2965463054 @default.
- W4376141036 cites W3048939905 @default.
- W4376141036 cites W3113266311 @default.
- W4376141036 cites W3113538230 @default.
- W4376141036 cites W3155438076 @default.
- W4376141036 cites W3211262047 @default.
- W4376141036 cites W3213968854 @default.
- W4376141036 cites W4210344316 @default.
- W4376141036 cites W4294541956 @default.
- W4376141036 cites W4296580889 @default.
- W4376141036 cites W4360978772 @default.
- W4376141036 cites W654550266 @default.
- W4376141036 doi "https://doi.org/10.21203/rs.3.rs-2902207/v1" @default.
- W4376141036 hasPublicationYear "2023" @default.
- W4376141036 type Work @default.
- W4376141036 citedByCount "0" @default.
- W4376141036 crossrefType "posted-content" @default.
- W4376141036 hasAuthorship W4376141036A5070978005 @default.
- W4376141036 hasBestOaLocation W43761410361 @default.
- W4376141036 hasConcept C101738243 @default.
- W4376141036 hasConcept C104317684 @default.
- W4376141036 hasConcept C111919701 @default.
- W4376141036 hasConcept C118505674 @default.
- W4376141036 hasConcept C14036430 @default.
- W4376141036 hasConcept C153180895 @default.
- W4376141036 hasConcept C154945302 @default.
- W4376141036 hasConcept C185592680 @default.
- W4376141036 hasConcept C2779803651 @default.
- W4376141036 hasConcept C41008148 @default.
- W4376141036 hasConcept C50644808 @default.
- W4376141036 hasConcept C55493867 @default.
- W4376141036 hasConcept C63479239 @default.
- W4376141036 hasConcept C76155785 @default.
- W4376141036 hasConcept C78458016 @default.
- W4376141036 hasConcept C86803240 @default.
- W4376141036 hasConcept C94915269 @default.
- W4376141036 hasConceptScore W4376141036C101738243 @default.
- W4376141036 hasConceptScore W4376141036C104317684 @default.
- W4376141036 hasConceptScore W4376141036C111919701 @default.
- W4376141036 hasConceptScore W4376141036C118505674 @default.
- W4376141036 hasConceptScore W4376141036C14036430 @default.
- W4376141036 hasConceptScore W4376141036C153180895 @default.
- W4376141036 hasConceptScore W4376141036C154945302 @default.
- W4376141036 hasConceptScore W4376141036C185592680 @default.
- W4376141036 hasConceptScore W4376141036C2779803651 @default.
- W4376141036 hasConceptScore W4376141036C41008148 @default.
- W4376141036 hasConceptScore W4376141036C50644808 @default.
- W4376141036 hasConceptScore W4376141036C55493867 @default.
- W4376141036 hasConceptScore W4376141036C63479239 @default.
- W4376141036 hasConceptScore W4376141036C76155785 @default.
- W4376141036 hasConceptScore W4376141036C78458016 @default.
- W4376141036 hasConceptScore W4376141036C86803240 @default.
- W4376141036 hasConceptScore W4376141036C94915269 @default.
- W4376141036 hasLocation W43761410361 @default.
- W4376141036 hasOpenAccess W4376141036 @default.
- W4376141036 hasPrimaryLocation W43761410361 @default.
- W4376141036 hasRelatedWork W2572600474 @default.
- W4376141036 hasRelatedWork W2592385986 @default.
- W4376141036 hasRelatedWork W2776466379 @default.
- W4376141036 hasRelatedWork W2785535669 @default.
- W4376141036 hasRelatedWork W2897995864 @default.
- W4376141036 hasRelatedWork W2998168123 @default.
- W4376141036 hasRelatedWork W3080875971 @default.
- W4376141036 hasRelatedWork W3090006671 @default.
- W4376141036 hasRelatedWork W4220775285 @default.
- W4376141036 hasRelatedWork W4287995534 @default.
- W4376141036 isParatext "false" @default.
- W4376141036 isRetracted "false" @default.
- W4376141036 workType "article" @default.