ReceiptSense: Beyond Traditional OCR -- A Dataset for Receipt Understanding

Abdelrahman Abdallah, Mohamed Mounis, Mahmoud Abdalla, Mahmoud SalahEldin Kasem, Mohamed Mahmoud +4 more
6/6/2024
cs.CVcs.CL

Official code: Update-For-Integrated-Business-AI/CORU (19 stars, last commit 2025-07-07).

Abstract

Multilingual OCR and information extraction from receipts remains challenging, particularly for complex scripts like Arabic. We introduce \dataset, a comprehensive dataset designed for Arabic-English receipt understanding comprising 20,000 annotated receipts from diverse retail settings, 30,000 OCR-annotated images, and 10,000 item-level annotations, and a new Receipt QA subset with 1265 receipt images paired with 40 question-answer pairs each to support LLM evaluation for receipt understanding. The dataset captures merchant names, item descriptions, prices, receipt numbers, and dates to support object detection, OCR, and information extraction tasks. We establish baseline performance using traditional methods (Tesseract OCR) and advanced neural networks, demonstrating the dataset's effectiveness for processing complex, noisy real-world receipt layouts. Our publicly accessible dataset advances automated multilingual document processing research (see https://github.com/Update-For-Integrated-Business-AI/CORU ).

View on arXivView PDF

Code Implementations(1)

Update-For-Integrated-Business-AI/CORUOfficial100%
192Jun 4, 20241 years ago

Similar Papers

KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding

80% match2025

Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction

79% match1 repo532024

Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR

79% match2025

Qalam : A Multimodal LLM for Arabic Optical Character and Handwriting Recognition

78% match2024

OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets

77% match2026

synthocr-gen: A synthetic ocr dataset generator for low-resource languages- breaking the data barrier

76% match2026

Cite this paper

@article{abdallah2024receiptsense,
  title  = {ReceiptSense: Beyond Traditional OCR -- A Dataset for Receipt Understanding},
  author = {Abdelrahman Abdallah and Mohamed Mounis and Mahmoud Abdalla and Mahmoud SalahEldin Kasem and Mohamed Mahmoud and Ibrahim Abdelhalim and Mohamed Elkasaby and Yasser ElBendary and Adam Jatowt},
  year   = {2024},
  eprint = {2406.04493},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.04493v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.04493.svg)](https://codeofpaper.com/paper/2406.04493)

Discussion