Robust Classification of Smartphone Captured Handwritten Document Images Using Deep Learning
Open Access
- 19 December 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 14922-14948
Abstract
Document classification is a challenging research problem in Document image analysis, majorly the presence of degradations like low illumination, blur, and shadows. In this paper, a deep learning-based two-level hierarchical approach is proposed for classifying smartphone-captured handwritten document images into three classes. The model is devised based on the pre-trained weights transferred from XceptionNet and the additional convolutional layers for feature extraction focused on high-frequency details from document images. A set of synthetically generated datasets concerning all three classes with two to three levels of degradation severity is considered for training the proposed deep learning model along with the real images labelled based on reference datasets. The dataset comprises blur and low illumination images with three levels of severity, and shadow images with two levels of severity. About 2,841 images from classes with 783 for blur, 828 for low illumination, and 1,230 for shadow were collected. The proposed model is compared with nine state-of-the-art deep-learning classification models. The proposed model outperforms the state-of-the-art models by addressing the problem of overfitting.Keywords
This publication has 37 references indexed in Scilit:
- DocXclassifier: towards a robust and interpretable deep neural network for document image classificationInternational Journal on Document Analysis and Recognition (IJDAR), 2024
- Image classification based on tensor network DenseNet modelApplied Intelligence, 2024
- Feature extraction using GTCC spectrogram and ResNet50 based classification for audio spoof detectionInternational Journal of Speech Technology, 2024
- Hybrid ResNet152-EML model for Geo-spatial image classificationInternational Journal of Information Technology, 2023
- De-noising the image using DBST-LCM-CLAHE: A deep learning approachMultimedia Tools and Applications, 2023
- Classification of incunable glyphs and out-of-distribution detection with joint energy-based modelsInternational Journal on Document Analysis and Recognition (IJDAR), 2023
- A feature selection model for document classification using Tom and Jerry Optimization algorithmMultimedia Tools and Applications, 2023
- Review of chart image detection and classificationInternational Journal on Document Analysis and Recognition (IJDAR), 2023
- A document image classification system fusing deep and machine learning modelsApplied Intelligence, 2022
- Multimodal Deep Networks for Text and Image-Based Document Classification2020