A Novel Siamese Network for Few/Zero-Shot Handwritten Character Recognition Tasks

Elaraby, Nagwa; Barakat, Sherif; Rezk, Amira

doi:10.32604/cmc.2023.032288

Cited by 8 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the overall analysis, the performances of proposed method are compared with different existing methods such as HFE-MSSAE [33], Siamese Network [34] and Hybrid CNN-RNN [35] in terms of accuracy, sensitivity, specificity, precision, and F1score. The existing methods have limitations such as: HFE-MSSAE method [33] attaining high accuracy by utilizing a huge number of features is challenging, Siamese Network method [34] the fine-tuning of AlexNet in English and Kannada takes more time for training, Hybrid CNN-RNN method [35] attaining high accuracy by utilizing a huge number of features is challenging. To overcome these limitations, the MWO-OTSU method is proposed in this research for recognizing the handwritten characteristics.…”

Section: Discussionmentioning

confidence: 99%

“…The proposed method is compared with other existing methods such as HFE with MSSAE [33], Siamese Network [34] and hybrid convolutional neural networkrecurrent neural network (CNN-RNN) [35] in Chars74k dataset. The introduced model attained the highest accuracy of 99.20% when compared to the existing methods.…”

Section: Real-time Dataset In Kannada Image Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Handwritten character recognition using optimization based skewed line segmentation method and multi-class support vector machine

2023

IJATEE

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Real-time Dataset In Kannada Image Segmentationmentioning

confidence: 99%

Handwritten character recognition using optimization based skewed line segmentation method and multi-class support vector machine

2023

IJATEE

View full text Add to dashboard Cite

show abstract

“…To tackle the issue of model adaptability in few-shot transfer learning, Elaraby et al [26] proposed a novel Siamese network that utilized transfer learning to construct a pretrained AlexNet model, replacing the original Siamese CNN network. They employed a contrastive loss instead of the traditional binary cross-entropy loss, resulting in higher recog- nition performance compared to traditional Siamese models, while also reducing training time.…”

Section: B Transfer Learning In Character Recognitionmentioning

confidence: 99%

Incremental Recognition of Multi-Style Tibetan Character Based on Transfer Learning

Zhao,

Wang,

Wang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Tibetan script possesses a distinctive artistic form of writing, intricate glyph structures, and diverse stylistic variations. In the task of text recognition, effectively handling the recognition of Tibetan script with significantly different stylistic fonts remains a challenge. Existing research has made considerable progress in recognizing Tibetan script within a single style using techniques such as convolutional neural networks and convolutional recurrent neural networks. However, when dealing with multi-style Tibetan script recognition, the standard approach involves training models using a multi-label joint training method. This approach annotates the style and class of different font style samples and merges them into a single dataset for model training. Nevertheless, as the amount of data and performance requirements increase, this approach gradually faces issues such as decreasing accuracy, insufficient generalization capability, and poor adaptability to new style samples. In this paper, we propose a transfer learning-based method for incremental recognition of multi-style Tibetan script, referred to as "multi-style Tibetan script incremental recognition." This method learns and completes the recognition of new style Tibetan script gradually from models that already possess recognition capabilities for a specific style. The proposed method consists of the following stages: 1) A multi-style classifier based on the VGG-16 network is designed to extract features that enable precise differentiation between different font styles of Tibetan script; 2) A pre-training phase is conducted using a residual network on the Tibetan script's standard Uchen style, resulting in an efficient feature extractor and a classifier capable of effectively recognizing the standard style, serving as a baseline model; 3) Through transfer learning, the feature extraction part of the baseline model is frozen, forming a shared feature extractor used for feature extraction of Tibetan script in the Uchen variant and antiquarian character styles. Corresponding classifiers are trained based on different styles; 4) By combining the multistyle classifier, shared feature extractor, and category classifier, recognition of Tibetan script characters is achieved. This method incrementally recognizes new styles based on the existing recognition model for Tibetan script in the Uchen standard style. Experimental results demonstrate that this method enhances the recognition accuracy of Tibetan script in Uchen standard, variant, and antiquarian character styles to 99.04%, 98.05%, and 97.66% respectively, using the TCDB and HUTD datasets. Compared to the traditional multitask recognition approach, the overall recognition accuracy improved from 90.14% to 98.40%. This method exhibits high accuracy, strong generalization capability, and good adaptability to new style samples in multistyle Tibetan script character recognition. Furthermore, it can be applied to other tasks involving multi-style, multi-font, and multi-script recognition.

show abstract

“…One of the recent research methodologies for using the Siamese network is presented in [24], where two CNNs are applied for deep learning on handwritten input data. The transfer learning is used with the pre-trained AlexNet implemented as a feature extractor.…”

Section: Related Workmentioning

confidence: 99%

Improved Siamese Palmprint Authentication Using Pre-Trained VGG16-Palmprint and Element-Wise Absolute Difference

Ezz¹,

Alanazi²,

Mostafa³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Palmprint identification has been conducted over the last two decades in many biometric systems. High-dimensional data with many uncorrelated and duplicated features remains difficult due to several computational complexity issues. This paper presents an interactive authentication approach based on deep learning and feature selection that supports Palmprint authentication. The proposed model has two stages of learning; the first stage is to transfer pre-trained VGG-16 of ImageNet to specific features based on the extraction model. The second stage involves the VGG-16 Palmprint feature extraction in the Siamese network to learn Palmprint similarity. The proposed model achieves robust and reliable end-to-end Palmprint authentication by extracting the convolutional features using VGG-16 Palmprint and the similarity of two input Palmprint using the Siamese network. The second stage uses the CASIA dataset to train and test the Siamese network. The suggested model outperforms comparable studies based on the deep learning approach achieving accuracy and EER of 91.8% and 0.082%, respectively, on the CASIA left-hand images and accuracy and EER of 91.7% and 0.084, respectively, on the CASIA right-hand images.

show abstract

A Novel Siamese Network for Few/Zero-Shot Handwritten Character Recognition Tasks

Cited by 8 publications

References 29 publications

Handwritten character recognition using optimization based skewed line segmentation method and multi-class support vector machine

Handwritten character recognition using optimization based skewed line segmentation method and multi-class support vector machine

Incremental Recognition of Multi-Style Tibetan Character Based on Transfer Learning

Improved Siamese Palmprint Authentication Using Pre-Trained VGG16-Palmprint and Element-Wise Absolute Difference

Contact Info

Product

Resources

About