custom-object-character-recognition-ocr-on-aws
https://github.com/pankajdevikar/custom-object-character-recognition-ocr-on-aws
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (9.4%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: PankajDevikar
- License: agpl-3.0
- Language: Python
- Default Branch: main
- Size: 3.77 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Custom Object Character Recognition (OCR) on AWS Using Appwrite Integration
Building a Custom OCR System by Combining YOLOv3, Tesseract, and Appwrite
1. Overview
This project implements a custom object character recognition (OCR) system designed to extract key information from lab reports. The system integrates a YOLOv3-based text detection model with the Tesseract OCR engine, and it uses Appwrite for cloud storage and API management. The solution automates the process of converting lab reports into editable text, and it is deployed on AWS for scalability.
2. Features
YOLOv3 Text Detection:
Detects regions of interest (text regions) within lab report images.Tesseract OCR Integration:
Extracts text from the detected regions.Appwrite Integration:
Utilizes Appwrite for cloud-based data management and API endpoints.AWS Deployment:
Designed to run on AWS for scalable and cost-efficient processing.User Interface:
A Streamlit app provides an interactive interface for uploading images, viewing detections, and displaying OCR results.
3. Architecture
3.1 Overall System Diagram
3.2 Detailed Architecture
The system consists of three main components:
- Detection Module:
Uses a YOLOv3-based model to detect text regions.
- OCR Module:
Uses Tesseract OCR to extract text from detected regions.
- Cloud & API Module:
Appwrite manages storage and API endpoints for scalable data handling.
3.3 Appwrite Integration
Appwrite is used to store training data, model outputs, and to provide RESTful API endpoints for accessing results. This enables real-time updates and monitoring through a user-friendly dashboard.
4. Installation
Prerequisites
- Python 3.x
- Virtual environment (recommended)
- AWS Account and proper credentials
- Appwrite instance for backend management
📸 Output Screenshots
Below are the screenshots demonstrating the project output:
Owner
- Login: PankajDevikar
- Kind: user
- Repositories: 1
- Profile: https://github.com/PankajDevikar
Citation (CITATION.cff)
cff-version: 1.2.0
preferred-citation:
type: software
message: If you use YOLOv5, please cite it as below.
authors:
- family-names: Jocher
given-names: Glenn
orcid: "https://orcid.org/0000-0001-5950-6979"
title: "YOLOv5 by Ultralytics"
version: 7.0
doi: 10.5281/zenodo.3908559
date-released: 2020-5-29
license: AGPL-3.0
url: "https://github.com/ultralytics/yolov5"
GitHub Events
Total
- Push event: 9
- Create event: 2
Last Year
- Push event: 9
- Create event: 2
Dependencies
- matplotlib >=3.3.0
- numpy >=1.22.2
- opencv-python >=4.6.0
- pandas >=1.1.4
- pillow >=7.1.2
- psutil *
- py-cpuinfo *
- pyyaml >=5.3.1
- requests >=2.23.0
- scipy >=1.4.1
- seaborn >=0.11.0
- thop >=0.1.1
- torch >=1.8.0
- torchvision >=0.9.0
- tqdm >=4.64.0
- ultralytics >=8.0.232
- Pillow >=10.3.0
- PyYAML >=5.3.1
- gitpython >=3.1.30
- matplotlib >=3.3
- numpy >=1.23.5
- opencv-python >=4.1.1
- pandas >=1.1.4
- psutil *
- requests >=2.32.2
- scipy >=1.4.1
- seaborn >=0.11.0
- setuptools >=70.0.0
- thop >=0.1.1
- torchvision >=0.9.0
- tqdm >=4.66.3