Title: Fine-tuned convolutional neural networks for feature extraction and classification of scanned document images using semi-automatic labelling approach

Authors: Krishna Kumar; Nakkala Srinivas Mudiraj; Meenakshi Mittal; Satwinder Singh

Addresses: Department of Computer Science and Technology, Central University of Punjab, Bathinda, India ' Department of Computer Science and Technology, Central University of Punjab, Bathinda, India ' Department of Computer Science and Technology, Central University of Punjab, Bathinda, India ' Department of Computer Science and Technology, Central University of Punjab, Bathinda, India

Abstract: Organising documents into relevant categories through image classification is crucial for management and safeguarding of valuable information. Many studies have done work on it with manual intervention, but still there is a scope of improvement. After finding gaps in existing studies, this research fine-tuned a hyper-parameter of pre-trained model based on various convolutional neural networks (CNNs), specifically the EfficientNetB3 and DenseNet201 models, for feature extraction and classification. These models are fine-tuned with the subset of the Ryerson Vision Lab Complex Document Information Processing (RVL_CDIP) dataset. The dataset comprises 16,000 image-scanned documents categorised into 16 classes with semi-automatic approach of labelling. The modified models are fine-tuned by adding a few more layers. The modified models outperformed in terms of accuracy, precision, recall and F1-Score for EfficientNetB3 and DenseNet201. These results highlight a significant improvement when comparing the proposed CNN models with baseline models through the utilisation of semi-automatic labelling and fine-tuning.

Keywords: convolutional neural networks; CNNs; document image classification; deep learning; hyperparameter tuning; image based classification; semi-automatic labelling; text-based classification; transfer learning.

DOI: 10.1504/IJIEI.2024.137711

International Journal of Intelligent Engineering Informatics, 2024 Vol.12 No.1, pp.103 - 134

Received: 10 Aug 2023
Accepted: 16 Dec 2023
Published online: 02 Apr 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article