Synthesizing data for text recognition with style transfer
Sign Up to like & getrecommendations! Published in 2018 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-018-6656-3
Abstract: Most of the existing datasets for scene text recognition merely consist of a few thousand training samples with a very limited vocabulary, which cannot meet the requirement of the state-of-the-art deep learning based text recognition… read more here.
Keywords: text recognition; synthesizing data; style transfer; transfer ... See more keywords
Sliding window based off-line handwritten text recognition using edit distance
Sign Up to like & getrecommendations! Published in 2021 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-021-10988-9
Abstract: A significant issue in the domain of optical character recognition is handwritten text recognition. Here, two novel feature extraction techniques are proposed using a fixed-size sliding window, and also an edit distance-based architecture is suggested… read more here.
Keywords: text recognition; handwritten text; edit distance; line ... See more keywords
FACLSTM: ConvLSTM with focused attention for scene text recognition
Sign Up to like & getrecommendations! Published in 2020 at "Science China Information Sciences"
DOI: 10.1007/s11432-019-2713-1
Abstract: Scene text recognition has recently been widely treated as a sequence-to-sequence prediction problem, where traditional fully-connected-LSTM (FC-LSTM) has played a critical role. Owing to the limitation of FC-LSTM, existing methods have to convert 2-D feature… read more here.
Keywords: convlstm; scene; attention; text recognition ... See more keywords
A Residual-Attention Offline Handwritten Chinese Text Recognition Based on Fully Convolutional Neural Networks
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Access"
DOI: 10.1109/access.2021.3115606
Abstract: Offline handwritten Chinese text recognition is one of the most challenging tasks in that it involves various writing styles, complex character-touching, and large number of character categories. In this paper, we propose a residual-attention offline… read more here.
Keywords: text recognition; chinese text; residual attention; offline handwritten ... See more keywords
A Transformer-Based Framework for Scene Text Recognition
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3207469
Abstract: Scene Text Recognition (STR) has become a popular and long-standing research problem in computer vision communities. Almost all the existing approaches mainly adopt the connectionist temporal classification (CTC) technique. However, these existing approaches are not… read more here.
Keywords: text recognition; scene text; framework; text ... See more keywords
EMU: Effective Multi-Hot Encoding Net for Lightweight Scene Text Recognition With a Large Character Set
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Circuits and Systems for Video Technology"
DOI: 10.1109/tcsvt.2022.3146240
Abstract: Deploying a lightweight deep model for scene text recognition task on mobile devices has great commercial value. However, the conventional softmax-based one-hot classification module becomes a cumbersome obstacle when handling multi-languages or languages with large… read more here.
Keywords: multi; text recognition; scene text; multi hot ... See more keywords
The Best Protection is Attack: Fooling Scene Text Recognition With Minimal Pixels
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2023.3245984
Abstract: Scene text recognition (STR) has witnessed tremendous progress in the era of deep learning, but it also raises concerns about privacy infringement as scene texts usually contain valuable or sensitive information. Previous works in privacy… read more here.
Keywords: text recognition; scene text; attack; minimal pixels ... See more keywords
Character-Aware Sampling and Rectification for Scene Text Recognition
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Multimedia"
DOI: 10.1109/tmm.2021.3129651
Abstract: Curved scene text recognition is a challenging task in multimedia society due to large shape and texture variance. Previous methods address this challenge by extracting and rectifying text line with equidistantly sampling, which ignore character… read more here.
Keywords: rectification; scene text; text recognition; sampling rectification ... See more keywords
GLaLT: Global-Local Attention-Augmented Light Transformer for Scene Text Recognition.
Sign Up to like & getrecommendations! Published in 2023 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2023.3239696
Abstract: Recent years have witnessed the growing popularity of connectionist temporal classification (CTC) and attention mechanism in scene text recognition (STR). CTC-based methods consume less time with few computational burdens, while they are not as effective… read more here.
Keywords: glalt; text recognition; scene text; attention ... See more keywords
An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition
Sign Up to like & getrecommendations! Published in 2017 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2016.2646371
Abstract: Image-based sequence recognition has been a long-standing research topic in computer vision. In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based sequence… read more here.
Keywords: image based; recognition; text recognition; scene text ... See more keywords
Simulation of English text recognition model based on ant colony algorithm and genetic algorithm
Sign Up to like & getrecommendations! Published in 2021 at "Journal of Intelligent and Fuzzy Systems"
DOI: 10.3233/jifs-189807
Abstract: The difficulty of English text recognition lies in fuzzy image text classification and part-of-speech classification. Traditional models have a high error rate in English text recognition. In order to improve the effect of English text… read more here.
Keywords: text; text recognition; english text; ant colony ... See more keywords