On the Use of Attention Mechanism in a Seq2Seq Based Approach for Off-Line Handwritten Digit String Recognition

Lupinski, Thibault; Belaïd, Abdel; Echi, Afef Kacem

doi:10.1109/icdar.2019.00086

Cited by 3 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, Lupinski et al [36] built a new approach using Attention Mechanism in a Seq2Seq based model for HDSR, through one CNN and two RNNs (Encoder-Decoder). Beyond that, Ma et al [37] developed an end-toend system as a simplified target detector (character level) for recognition of digits in low resolution images through bounding boxes.…”

Section: B State-of-the-art In Hdsrmentioning

confidence: 99%

HDSR-Flor: A Robust End-to-End System to Solve the Handwritten Digit String Recognition Problem in Real Complex Scenarios

et al. 2020

View full text Add to dashboard Cite

Automatic handwriting recognition systems are of interest for academic research fields and for commercial applications. Recent advances in deep learning techniques have shown dramatic improvement in relation to classic computer vision problems, especially in Handwritten Text Recognition (HTR). However, several approaches try to solve the problem of deep learning applied to Handwritten Digit String Recognition (HDSR), where it has to deal with the low number of trainable data, while learning to ignore any writing symbol around the digits (noise). In this context, we present a new optical model architecture (Gated-CNN-BGRU), based on HTR workflow, applied to HDSR. The International Conference on Frontiers of Handwriting Recognition (ICFHR) 2014 competition on HDSR were used as baselines to evaluate the effectiveness of our proposal, whose metrics, datasets and recognition methods were adopted for fair comparison. Furthermore, we also use a private dataset (Brazilian Bank Check-Courtesy Amount Recognition), and 11 different approaches from the state-of-the-art in HDSR, as well as 2 optical models from the state-of-the-art in HTR. Finally, the proposed optical model demonstrated robustness even with low data volume (126 trainable data, for example), surpassing the results of existing methods with an average precision of 96.50%, which is equivalent to an average percentage of improvement of 3.74 points compared to the state-of-the-art in HDSR. In addition, the result stands out in the competition's CVL HDS set, where the proposed optical model achieved a precision of 93.54%, while the best result so far had been from Beijing group (from the competition itself), with 85.29%.

show abstract

Section: B State-of-the-art In Hdsrmentioning

confidence: 99%

HDSR-Flor: A Robust End-to-End System to Solve the Handwritten Digit String Recognition Problem in Real Complex Scenarios

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This work achieved breakthrough results on the Modified National Institute of Standards and Technology (MNIST) dataset [6]. Meanwhile, the application of attention mechanisms in sequence-to-sequence based deep learning models is introduced by T. Lupinski et al to enhance the performance of offline handwritten digit string recognition [7]. S. Ahlawat et al introduces the application of CNNs and attention mechanisms to improve handwritten digit recognition.…”

Section: Introductionmentioning

confidence: 99%

Handwritten digit recognition based on deep learning techniques

Zhang

2024

ACE

View full text Add to dashboard Cite

The identification of handwritten digits in images recognition and machine learning is a prominent research area. In order to create a handwritten digit recognition model for this investigation, deep learning is introduced. The proposed approach integrates Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and EfficientNetB0, three separate deep learning models. Specifically, the CNN model utilizes pooling layers and data augmentation techniques to enhance its classification ability, the RNN model takes advantage of its ability to process sequential data, and the EfficientNetB0 model benefits from a deeper and more complex network structure. These models are trained and evaluated using the Modified National Institute of Standards and Technology (MNIST) dataset. The experimental results demonstrate the efficacy of the proposed approach: the CNN model attains a remarkable accuracy of 98.9% on the test set, thereby showcasing its exceptional classification performance. Similarly, the RNN model achieves an accuracy of 96.7%, underscoring its suitability for analyzing sequential data. Furthermore, the EfficientNetB0 model attains an accuracy of 98.1%, thereby elucidating the benefits of the deeper network architecture. The models constructed in this study have significant real-world implications, such as improved object recognition systems, medical diagnostics, and autonomous driving. The EfficientNetB0 model produced an accuracy of 98.1% with its complex network architecture when applied to recognise handwritten digits.

show abstract

On usage of an end-to-end deep neural architecture for handwritten digit string recognition

Omidi,

BabaAli

2024

SIViP

View full text Add to dashboard Cite

On the Use of Attention Mechanism in a Seq2Seq Based Approach for Off-Line Handwritten Digit String Recognition

Cited by 3 publications

References 12 publications

HDSR-Flor: A Robust End-to-End System to Solve the Handwritten Digit String Recognition Problem in Real Complex Scenarios

HDSR-Flor: A Robust End-to-End System to Solve the Handwritten Digit String Recognition Problem in Real Complex Scenarios

Handwritten digit recognition based on deep learning techniques

On usage of an end-to-end deep neural architecture for handwritten digit string recognition

Contact Info

Product

Resources

About