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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Abdallah, Abdelrahman, Mounis, Mohamed, Abdalla, Mahmoud, Kasem, Mahmoud SalahEldin, Mahmoud, Mohamed, Abdelhalim, Ibrahim, Elkasaby, Mohamed, ElBendary, Yasser, Jatowt, Adam
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908530967052288
author Abdallah, Abdelrahman
Mounis, Mohamed
Abdalla, Mahmoud
Kasem, Mahmoud SalahEldin
Mahmoud, Mohamed
Abdelhalim, Ibrahim
Elkasaby, Mohamed
ElBendary, Yasser
Jatowt, Adam
author_facet Abdallah, Abdelrahman
Mounis, Mohamed
Abdalla, Mahmoud
Kasem, Mahmoud SalahEldin
Mahmoud, Mohamed
Abdelhalim, Ibrahim
Elkasaby, Mohamed
ElBendary, Yasser
Jatowt, Adam
contents 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 ).
format Preprint
id arxiv_https___arxiv_org_abs_2406_04493
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ReceiptSense: Beyond Traditional OCR -- A Dataset for Receipt Understanding
Abdallah, Abdelrahman
Mounis, Mohamed
Abdalla, Mahmoud
Kasem, Mahmoud SalahEldin
Mahmoud, Mohamed
Abdelhalim, Ibrahim
Elkasaby, Mohamed
ElBendary, Yasser
Jatowt, Adam
Computer Vision and Pattern Recognition
Computation and Language
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 ).
title ReceiptSense: Beyond Traditional OCR -- A Dataset for Receipt Understanding
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2406.04493