Recognition of Handwritten Gujarati Conjuncts Using the Convolutional Neural Network Architectures: AlexNet, GoogLeNet, Inception V3, and ResNet50

The broad application area and accompanying challenges make machine learning-based recognition of handwritten scripts a demanding field. Individuals’ writing practices and inherent variations in the size, shape, and tilt of characters may increase the difficulty level. Deep convolutional neural network (DCNN) models have been successful in solving pattern recognition problems, but at the expense of a considerable number of trainable parameters and heavy computational loads. The proposed work addresses these problems by using the shifted window (SWIN) transformer method to recognize handwritten Devanagari numerals for the first time. In the presented model, the SWIN transformer is finely tuned to withstand popular DCNN models, such as VGG-16Net, ResNet-50, and DenseNet-121, in terms of recognition accuracy, space requirement, and computational complexity. The model successfully attained a recognition accuracy of 99.20% with only 0.218 million trainable parameters and 0.0912 giga floating-point operations per second (FLOPs). This indicates the validity and soundness of the proposed model for recognizing handwritten Devanagari numerals. 

/pdf/deep-learning-model-for-recognition-of-handwritten-26eski6z.pdf

Deep Learning Model for Recognition of Handwritten Devanagari Numerals With Low Computational Complexity and Space Requirements

The broad application area and accompanying challenges make machine learning-based recognition of handwritten scripts a demanding field. Individuals’ writing practices and inherent variations in the size, shape, and tilt of characters may increase the difficulty level. Deep convolutional neural network (DCNN) models have been successful in solving pattern recognition problems, but at the expense of a considerable number of trainable parameters and heavy computational loads. The proposed work addresses these problems by using the shifted window (SWIN) transformer method to recognize handwritten Devanagari numerals for the first time. In the presented model, the SWIN transformer is finely tuned to withstand popular DCNN models, such as VGG-16Net, ResNet-50, and DenseNet-121, in terms of recognition accuracy, space requirement, and computational complexity. The model successfully attained a recognition accuracy of 99.20% with only 0.218 million trainable parameters and 0.0912 giga floating-point operations per second (FLOPs). This indicates the validity and soundness of the proposed model for recognizing handwritten Devanagari numerals.

https://doi.org/10.1109/access.2023.3277392

Hindi is the official language of India and used by a large population for several public services like postal, bank, judiciary, and public surveys. Efficient management of these services needs language-based automation. The proposed model addresses the problem of handwritten Hindi character recognition using a machine learning approach. The pre-trained DCNN models namely; InceptionV3-Net, VGG19-Net, and ResNet50 were used for the extraction of salient features from the characters’ images. A novel approach of fusion is adopted in the proposed work; the DCNN-based features are fused with the handcrafted features received from Bi-orthogonal discrete wavelet transform. The feature size was reduced by the Principal Component Analysis method. The hybrid features were examined with popular classifiers namely; Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM). The recognition cost was reduced by 84.37%. The model achieved significant scores of precision, recall, and F1-measure—98.78%, 98.67%, and 98.69%—with overall recognition accuracy of 98.73%.

A Fusion-Based Hybrid-Feature Approach for Recognition of Unconstrained Offline Handwritten Hindi Characters

Fusion-Based Feature Extraction Approach for Recognition of Handwritten Devanagari Numerals

Ensemble of deep learning and machine learning approach for classification of handwritten Hindi numerals

The challenges and broad application fields related to handwritten numeral recognition, attract the research communities for further development. The major challenges one has to face for developing such systems are writing practices of individuals, degree of similarity in various digit shapes, and typical structure of digits written in Hindi script. The proposed model is designed to face these challenges by implementing effective feature extraction and classification methods. The model exploited bi-orthogonal Discrete Wavelet Transform (DWT) for important feature extraction and multiple classifiers, namely, Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) for the classification task. The proposed model not only recognized the handwritten numerals quite accurately, but was also successful in reducing the size of original features to release computational loads of classifiers. The scheme has managed to attain recognition accuracies of 96.64, 99.84, and 97.04% by the mentioned classifiers, respectively.KeywordsBi-orthogonalDWTHandwrittenHindiKNNMLPAnd SVM 

Danveer Rajpal

Papers

A Fusion-Based Hybrid-Feature Approach for Recognition of Unconstrained Offline Handwritten Hindi Characters

Fusion-Based Feature Extraction Approach for Recognition of Handwritten Devanagari Numerals

Ensemble of deep learning and machine learning approach for classification of handwritten Hindi numerals

Discrete Wavelet-Based Multi-Classifier Approach for Recognition of Offline Handwritten Hindi Numerals

Deep Learning Model for Recognition of Handwritten Devanagari Numerals With Low Computational Complexity and Space Requirements