Search Results for author:
Found 12 papers, 6 papers with code
FATURA: A Multi-Layout Invoice Image Dataset for Document Analysis and Understanding
In this paper, we introduce FATURA, a pivotal resource for researchers in the field of document analysis and understanding.
MSdocTr-Lite: A Lite Transformer for Full Page Multi-script Handwriting Recognition
In this paper, we propose a lite transformer architecture for full-page multi-script handwriting recognition.
CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition
In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition.
ST-KeyS: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documents
However, in the case of historical manuscripts, there is a lack of annotated corpus for training.
Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement
In this paper, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE), a self-supervised model designed to tackle two tasks, text recognition (handwritten or scene-text) and document image enhancement.
DocEnTr: An End-to-End Document Image Enhancement Transformer
Document images can be affected by many degradation scenarios, which cause recognition and processing difficulties.
Ranked #1 on
Binarization
on H-DIBCO 2011
Transformer-Based Approach for Joint Handwriting and Named Entity Recognition in Historical documents
Second, it allows the model to exploit larger bi-dimensional context information to identify the semantic categories, reaching a higher final prediction accuracy.
Few Shots Are All You Need: A Progressive Few Shot Learning Approach for Low Resource Handwritten Text Recognition
Since this retraining would require annotation of thousands of handwritten symbols together with their bounding boxes, we propose to avoid such human effort through an unsupervised progressive learning approach that automatically assigns pseudo-labels to the non-annotated data.
Enhance to Read Better: A Multi-Task Adversarial Network for Handwritten Document Image Enhancement
Unlike the most well-known document binarization methods, which try to improve the visual quality of the degraded document, the proposed architecture integrates a handwritten text recognizer that promotes the generated document image to be more readable.
Ranked #1 on
Binarization
on H-DIBCO 2016
One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition
Low resource Handwritten Text Recognition (HTR) is a hard problem due to the scarce annotated data and the very limited linguistic information (dictionaries and language models).
DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement
Documents often exhibit various forms of degradation, which make it hard to be read and substantially deteriorate the performance of an OCR system.
A Few-shot Learning Approach for Historical Ciphered Manuscript Recognition
Encoded (or ciphered) manuscripts are a special type of historical documents that contain encrypted text.
