Logo Lanfrica

SAQR: A Synthetic-to-Real Arabic Handwriting Recognition, Retrieval, and Demographic Dataset

Domain:

natural language processing

Record type:

dataset
Creator:
SalAbdMahAbd
Publisher:
Zenodo
Host:avatar
SAQR is a benchmark dataset for Arabic Handwritten Text Recognition (HTR), Printed-to-Handwritten Retrieval/Matching, and Demographic (Gender) Analysis.  The dataset contains 2,263 aligned pairs of synthetic printed ground-truth crops and their handwritten counterpart line images written by diverse writers across 3 official splits (Train: 1,575, Validation: 335, Test: 353).

Tasks

optical character recognitioncomputer vision

Tags

Arabic HTRandwritten Text RecognitionImage RetrievalComputer VisionComputer vision

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similar

Arabic Handwriting Recognition Using VDHMM and Over-segmentation

SARD: A Large-Scale Synthetic Arabic OCR Dataset for Book-Style Text Recognition

Arabic Optical Character Recognition (OCR) is essential for converting vast amounts of Arabic print

Two-Tier Approach for Arabic Offline Handwriting Recognition

http://www.suvisoft.com In this paper we present a novel approach for the recognition

Online Arabic Handwriting Recognition Using Hidden Markov Models

http://www.suvisoft.com Online handwriting recognition of Arabic script is a difficul

Towards Accurate Children’s Arabic Handwriting Recognition via Deep Learning

Automatic handwriting recognition has received considerable attention over the past three decades. H

Comparative study of the use of geometrical moments for Arabic handwriting recognition