paper-with-me

Papers

bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali Documents

2023-08-21 · Imam Mohammad Zulkarnain, Shayekh Bin Islam, Md. Zami Al Zunaed Farabe, Md. Mehedi Hasan Shawon, Jawaril Munshad Abedin, Beig Rajibul Hasan, Marsia Haque, Istiak Shihab, Syed Mobassir, MD. Nazmuddoha Ansary, Asif Sushmit, Farig Sadeque

Despite the existence of numerous Optical Character Recognition (OCR) tools, the lack of comprehensive open-source systems hampers the progress of document digitization in various low-resource languages, including Bengali. Low-resource languages, especially those with an alphasyllabary writing system, suffer from the lack of large-scale datasets for various document OCR components such as word-level OCR, document layout extraction, and distortion correction; which are available as individual modules in high-resource languages. In this paper, we introduce Bengali$.$AI-BRACU-OCR (bbOCR): an open-source scalable document OCR system that can reconstruct Bengali documents into a structured searchable digitized format that leverages a novel Bengali text recognition model and two novel synthetic datasets. We present extensive component-level and system-level evaluation: both use a novel diversified evaluation dataset and comprehensive evaluation metrics. Our extensive evaluation suggests that our proposed solution is preferable over the current state-of-the-art Bengali OCR systems. The source codes and datasets are available here: https://bengaliai.github.io/bbocr.

📄 PDF Abstract BibTeX arXiv:2308.10647

Code (1)

BengaliAI/bbocr 공식 구현 pytorch

Tasks

distortion correctionOptical Character RecognitionOptical Character Recognition (OCR)

Similar Papers 제목 키워드 기반

On Domain-Specific Post-Training for Multimodal Large Language Models

2024-11-29 · Daixuan Cheng, Shaohan Huang, Ziyu Zhu, Xintong Zhang 외

Recent years have witnessed the rapid development of general multimodal large language models (MLLMs). However, adapting general MLLMs to specific domains, such as scientific fields and industrial applications, remains l…

DiversityDomain Adaptation

ScaleEdit-12M: Scaling Open-Source Image Editing Data Generation via Multi-Agent Framework

2026-03-21 · Guanzhou Chen, Erfei Cui, Changyao Tian, Danni Yang 외 arxiv

Instruction-based image editing has emerged as a key capability for unified multimodal models (UMMs), yet constructing large-scale, diverse, and high-quality editing datasets without costly proprietary APIs remains chall…

Image Editing

A Recommender System for Scientific Datasets and Analysis Pipelines

2021-08-20 · Mandana Mazaheri, Gregory Kiar, Tristan Glatard

Scientific datasets and analysis pipelines are increasingly being shared publicly in the interest of open science. However, mechanisms are lacking to reliably identify which pipelines and datasets can appropriately be us…

Collaborative FilteringRecommendation Systems

A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering

2024-09-20 · Georgios Sidiropoulos, Evangelos Kanoulas

Speech-based open-domain question answering (QA over a large corpus of text passages with spoken questions) has emerged as an important task due to the increasing number of users interacting with QA systems via speech in…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Open-Domain Question AnsweringPassage Retrieval+4

SF-QA: Simple and Fair Evaluation Library for Open-domain Question Answering

2021-01-06 · EACL 2021 2 · Xiaopeng Lu, Kyusong Lee, Tiancheng Zhao

Although open-domain question answering (QA) draws great attention in recent years, it requires large amounts of resources for building the full system and is often difficult to reproduce previous results due to complex …

Open-Domain Question AnsweringQuestion Answering