Natural Scene Text Recognition Based on Encoder-Decoder Framework

Aiming at the situation that complex natural scene text is difficult to recognize a scene text recognition method based on an encoder-decoder framework is proposed. The method converts the natural text recognition into a sequence mark by combining the connection time classification (CTC) and attenti...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE access Ročník 7; s. 62616 - 62623
Hlavní autoři: Zuo, Ling-Qun, Sun, Hong-Mei, Mao, Qi-Chao, Qi, Rong, Jia, Rui-Sheng
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Artificial neural networks
Bi-LSTM
Character recognition
CNN
Coders
Convolutional neural networks
Decoding
encoder-decoder framework
Encoders-Decoders
Feature extraction
Image segmentation
Natural scene text recognition
Optical character recognition software
Recognition
Text recognition
Training
ISSN:2169-3536, 2169-3536
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Aiming at the situation that complex natural scene text is difficult to recognize a scene text recognition method based on an encoder-decoder framework is proposed. The method converts the natural text recognition into a sequence mark by combining the connection time classification (CTC) and attention mechanism under the encoder-decoder framework, in order to overcome the problem of character segmentation, using the correlation between image and text sequence. First of all, a convolutional neural network (CNN) is used to generate an ordered feature sequence from the entire word image. Then, the generated feature sequence is feature-coded using the bidirectional long short-term memory (Bi-LSTM) network. Finally, an integrated module of the CTC and attention mechanism is designed to decode and output the text sequence. The experiments show that compared with the comparison method, the recognition accuracy of the method is improved obviously.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2019.2916616