Results 131 to 140 of about 471 (152)
Some of the next articles are maybe not open access.
HTR-Flor: A Deep Learning System for Offline Handwritten Text Recognition
2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2020In recent years, Handwritten Text Recognition (HTR) has captured a lot of attention among the researchers of the computer vision community. Current state-of-the-art approaches for offline HTR are based on Convolutional Recurrent Neural Networks (CRNNs) excel at scene text recognition. Unfortunately, deep models such as CRNNs, Recur-rent Neural Networks
Arthur Flor De Sousa Neto +2 more
exaly +2 more sources
Making the past readable: a study of the impact of handwritten text recognition (HTR) on libraries and their users [PDF]
This thesis considers the socio-technical infrastructure surrounding AI-enabled Handwritten Text Recognition (HTR), the process of converting images of historical textual materials into computer-readable text. Despite sectoral awareness of the technology, institutional approaches still display gaps between conceptualising and operationalising HTR.
Nockels, Joseph
openaire +4 more sources
A Research on Handwritten Text Recognition (HTR) Strategies for English Words
2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2021Anika Bhardwaj +2 more
exaly +2 more sources
A set of benchmarks for Handwritten Text Recognition on historical documents [PDF]
Pattern Recognition, 2019 [EN] Handwritten Text Recognition is a important requirement in order to make visible the contents of the myriads of historical documents residing in public and private archives and libraries world wide.
Joan Andreu Sanchez +2 more
exaly +3 more sources
2025 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)
Ryan Rhay P Vicerra
exaly +2 more sources
Ryan Rhay P Vicerra
exaly +2 more sources
End-to-End page-Level assessment of handwritten text recognition [PDF]
Pattern Recognition, 2023 The evaluation of Handwritten Text Recognition (HTR) systems has traditionally used metrics based on the edit distance between HTR and ground truth (GT) transcripts, at both the character and word levels.
Enrique Vidal +2 more
exaly +3 more sources
LLM Powered HTR: Integrating Handwritten Text Recognition System with Large Language Model
2024 IEEE Students Conference on Engineering and Systems (SCES)Mehar Prateek Kalra +2 more
exaly +2 more sources
Proceedings of the ACM Symposium on Document Engineering 2020, 2020
Offline Handwritten Text Recognition (HTR) is a task that offers a challenge in computer vision, where images are the only source of information. In fact, several approaches to optical models have been developed, such as through of Hidden Markov Model (HMM) or recurrent Bidirectional/Multidimensional layers.
Arthur Flor de Sousa Neto +3 more
openaire +1 more source
Offline Handwritten Text Recognition (HTR) is a task that offers a challenge in computer vision, where images are the only source of information. In fact, several approaches to optical models have been developed, such as through of Hidden Markov Model (HMM) or recurrent Bidirectional/Multidimensional layers.
Arthur Flor de Sousa Neto +3 more
openaire +1 more source
Data Augmentation for Offline Handwritten Text Recognition: A Systematic Literature Review [PDF]
SN Computer Science[EN] Offline Handwritten Text Recognition (HTR) systems concern the automatic recognition and transcription of handwritten text from scanned images to digital media.
Arthur Flor De Sousa Neto +2 more
exaly +2 more sources
HTR-HSS: Hybrid State-Space Modeling for Offline Handwritten Text Recognition
To address the quadratic computational cost of self-attention in Offline Handwritten Text Recognition (HTR), we propose HTR-HSS, a parameter-efficient hybrid architecture for efficient long-sequence modeling. The proposed model combines a lightweight CSP-UNet backbone for multi-scale visual feature extraction, a temporal downsampling module for ...Yuan Pan +3 more
openaire +1 more source