Handwriting Recognition in Low-Resource Scripts Using Adversarial Learning

Bhunia, Ayan Kumar; Das, Alaka; Bhunia, Ankan Kumar; Kishore, Putha; Roy, Partha Pratim

doi:10.1109/cvpr.2019.00490

Cited by 67 publications

(31 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…No language model or lexicon is used during experiments. (Bhunia et al 2019) shows better performance on WER, their method needs cropped word images as input, while our method directly recognizes text lines. On RIMES, it is inferior to previous state-of-the-art by 0.2% on CER; but on WER, it has a great error reduction of 3.7% (relative error reduction of 29%).…”

Section: Offline Handwritten Text Recognitionmentioning

confidence: 99%

Decoupled Attention Network for Text Recognition

Wang

Zhu

Jin

et al. 2020

AAAI

204

119

View full text Add to dashboard Cite

Text recognition has attracted considerable research interests because of its various applications. The cutting-edge text recognition methods are based on attention mechanisms. However, most of attention methods usually suffer from serious alignment problem due to its recurrency alignment operation, where the alignment relies on historical decoding results. To remedy this issue, we propose a decoupled attention network (DAN), which decouples the alignment operation from using historical decoding results. DAN is an effective, flexible and robust end-to-end text recognizer, which consists of three components: 1) a feature encoder that extracts visual features from the input image; 2) a convolutional alignment module that performs the alignment operation based on visual features from the encoder; and 3) a decoupled text decoder that makes final prediction by jointly using the feature map and attention maps. Experimental results show that DAN achieves state-of-the-art performance on multiple text recognition tasks, including offline handwritten text recognition and regular/irregular scene text recognition. Codes will be released.1

show abstract

Section: Offline Handwritten Text Recognitionmentioning

confidence: 99%

Decoupled Attention Network for Text Recognition

Wang

Zhu

Jin

et al. 2020

AAAI

204

119

View full text Add to dashboard Cite

show abstract

“…This task was the first tackled using LeNet [8], and is what is currently done for ideogrammatic languages such as Chinese [9] and Japanese [10]. For alphabetic languages, HTR can be also performed at word level [11], [12], [13], i.e., decoding single words that are detected in the image. This task is performed both on digitalized documents, and in scene images [14].…”

Section: Related Workmentioning

confidence: 99%

Watch Your Strokes: Improving Handwritten Text Recognition with Deformable Convolutions

Cojocaru

Cascianelli

Baraldi

et al. 2021

2020 25th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

Handwritten Text Recognition (HTR) in free-layout pages is a valuable yet challenging task which aims to automatically understand handwritten texts. State-of-the-art approaches in this field usually encode input images with Convolutional Neural Networks, whose kernels are typically defined on a fixed grid and focus on all input pixels independently. However, this is in contrast with the sparse nature of handwritten pages, in which only pixels representing the ink of the writing are useful for the recognition task. Furthermore, the standard convolution operator is not explicitly designed to take into account the great variability in shape, scale, and orientation of handwritten characters. To overcome these limitations, we investigate the use of deformable convolutions for handwriting recognition. The kernel of this type of convolution deforms according to the content of the neighborhood, and can therefore be more adaptable to geometric variations and other deformations of the text. Experiments conducted on the IAM and RIMES datasets demonstrate that the use of deformable convolutions is a promising direction for the design of novel architectures for handwritten text recognition.

show abstract

“…Many kinds of research were conducted to improve the performance and the effectiveness of OCR system, especially the handwriting character recognition which is and still a big challenge for OCR because, in handwriting, character styles are different from one person to another. In [8], they study a common difficulty often faced by researchers exploring handwriting recognition in lowresource scripts and try to overcome the limitations of generic data augmentation strategies by proposing a modular deformation network that is trained to learn a manifold of parameters seeking to deform the features learned by the original task network. By the availability of GPU with limited memory and computing resources, researchers propose an efficient deep architecture having a limited number of parameters, which can be trained on a low memory GPU for character recognition [9].…”

Section: Related Workmentioning

confidence: 99%

Training Data Sets Construction from Large Data Set for PCB Character Recognition

Fabrice¹,

Gang²,

Lee³

2019

J Multimed Inf Syst

View full text Add to dashboard Cite

Deep learning has become increasingly popular in both academic and industrial areas nowadays. Various domains including pattern recognition, Computer vision have witnessed the great power of deep neural networks. However, current studies on deep learning mainly focus on quality data sets with balanced class labels, while training on bad and imbalanced data set have been providing great challenges for classification tasks. We propose in this paper a method of data analysis-based data reduction techniques for selecting good and diversity data samples from a large dataset for a deep learning model. Furthermore, data sampling techniques could be applied to decrease the large size of raw data by retrieving its useful knowledge as representatives. Therefore, instead of dealing with large size of raw data, we can use some data reduction techniques to sample data without losing important information. We group PCB characters in classes and train deep learning on the ResNet56 v2 and SENet model in order to improve the classification performance of optical character recognition (OCR) character classifier.

show abstract

Handwriting Recognition in Low-Resource Scripts Using Adversarial Learning

Cited by 67 publications

References 31 publications

Decoupled Attention Network for Text Recognition

Decoupled Attention Network for Text Recognition

Watch Your Strokes: Improving Handwritten Text Recognition with Deformable Convolutions

Training Data Sets Construction from Large Data Set for PCB Character Recognition

Contact Info

Product

Resources

About