Results 1 to 10 of about 36,687 (158)
Self-Supervised Representation Learning for Document Image Classification [PDF]
IEEE Access, 2021 Supervised learning, despite being extremely effective, relies on expensive, time-consuming, and error-prone annotations. Self-supervised learning has recently emerged as a strong alternate to supervised learning in a range of different domains as ...
Shoaib Ahmed Siddiqui +2 more
doaj +2 more sources
Unsupervised Exemplar-Based Learning for Improved Document Image Classification
IEEE Access, 2019 Many recent state-of-the-art approaches for document image classification are based on supervised feature learning that requires a large amount of labeled training data.
Sherif Abuelwafa +2 more
doaj +3 more sources
Enhancing Document Classification Through Multimodal Image-Text Classification: Insights from Fine-Tuned CLIP and Multimodal Deep Fusion [PDF]
SensorsFoundation models excel on general benchmarks but often underperform in clinical settings due to domain shift between internet-scale pretraining data and medical data. Multimodal deep learning, which jointly leverages medical images and clinical text, is
Hosam Aljuhani +2 more
doaj +2 more sources
Document image and zone classification through incremental learning [PDF]
2013 IEEE International Conference on Image Processing, 2013 We present an incremental learning method for document image and zone classification. We consider an industrial context where the system faces a large variability of digitized administrative documents that become available progressively over time. Each new incoming document is segmented into physical regions (zones) which are classified according to a ...
Mohamed-Rafik Bouguelia, Abdel Belaid
exaly +2 more sources
Application of EfficientNet-based Transfer Learning in Image Classification of Modern Documents: Taking Shanghai Library's "Picture Gallery of Modern Chinese Literature" as an Example [PDF]
Nongye tushu qingbao xuebao, 2023 [Purpose/Significance] As important historical data, images in modern literature are increasingly valued by humanities researchers. The deep annotation of large-scale image resources has also become an important part of the construction of image data ...
YANG Min, GUO Limin
doaj +1 more source
EmmDocClassifier: Efficient Multimodal Document Image Classifier for Scarce Data
Applied Sciences, 2022 Document classification is one of the most critical steps in the document analysis pipeline. There are two types of approaches for document classification, known as image-based and multimodal approaches. Image-based document classification approaches are
Shrinidhi Kanchi +5 more
doaj +1 more source
A Novel Adaptive Deskewing Algorithm for Document Images
Sensors, 2022 Document scanning often suffers from skewing, which may seriously influence the efficiency of Optical Character Recognition (OCR). Therefore, it is necessary to correct the skewed document before document image information analysis.
Wuzhida Bao +6 more
doaj +1 more source
Image-Text Sentiment Analysis Model Based on Visual Aspect Attention [PDF]
Jisuanji kexue, 2022 Social network has become an integral part of our daily life.Sentiment analysis of social media information is helpful to understand people's views,attitudes and emotions on social networking sites.Traditional sentiment analysis mainly relies on text ...
YUAN Jing-ling, DING Yuan-yuan, SHENG De-ming, LI Lin
doaj +1 more source
Applied Sciences, 2022 In this paper, we propose a new convolutional neural network (CNN) architecture for improving document-image quality through decreasing the impact of distortions (i.e., blur, shadows, contrast issues, and noise) contained therein.
Kabeh Mohsenzadegan +2 more
doaj +1 more source
Sensors, 2021 This paper’s core objective is to develop and validate a new neurocomputing model to classify document images in particularly demanding hard conditions such as image distortions, image size variance and scale, a huge number of classes, etc.
Kabeh Mohsenzadegan +2 more
doaj +1 more source