Classification of heterogeneous Malayalam documents based on structural features using deep learning models

Abstract

The proposed work gives a comparative study on performance of various pretrained deep learning models for classifying Malayalam documents such as agreement documents, notebook images, and palm leaves. The documents are classified based on their visual and structural features. The dataset was manually collected from different sources. The method of research proceeds with preprocessing, feature extraction, and classification. The proposed work deals with three fine-tuned deep learning models such as visual geometry group-16 (VGG-16), convolutional neural network (CNN) and AlexNet. The models attained high accuracies of 99.7%, 96%, and 95%, respectively. Among the three models, the fine-tuned VGG-16 model was found to perform better attaining a very high accuracy on the dataset. As a future work, methods to classify the documents based on content as well as spectral features can be developed.

ViT-based classification of oracle bones for periodization of the Shang Dynasty

“…Jayakumari and Nair [4] proposed a deep-learning-based ResNet model for the binarization of ancient horoscopic palm leaf images, achieving a high accuracy of 95.38% on a manually collected dataset. Bipin performed a comparative study on the performance of various pre-trained deep learning models for classifying Malayalam documents, utilizing three fine-tuned deep learning models, namely VGG-16, CNN, and AlexNet, which achieved accuracies of 99.7%, 96%, and 95%, respectively [5]. However, due to the distinctive noise in non-text regions of oracle bone script images, the image features related to text regions do not exhibit significant discrimination across different historical periods compared to other historical documents, making it difficult for the CNN model to correctly extract features.…”