Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVION and PaddlePaddle.

Collections of Projects I do for Fun or whenever I have brain farts. Low Quality Projects

Automated Parking Registry using ANPR

Pyggle is a boggle solver library written in Python, and compiled to Next.js!

Flask endpoint to verify the face on a live image versus the face on an identification document and the name provided versus the name on the document using computer vision and OCR ML algorithms.

Program to Detect Number Plates and QR Code

Counter surveillance system that detects vehicles that may be following you using ALPR. Designed simply with open source projects.

License Plate Recognition using YOLOv8 + EasyOCR + NAFNet

Optical Character Recognition Component from AuRA-Ai-MED

This microservice standardizes the usage of Optical Character Recognition (OCR) engines

This project uses the Tesseract OCR library to extract text from images. The text is then parsed using regular expressions to extract the numbers. The numbers are then written to a text file in the output directory. To use this project, simply place the input images in the input_images directory and run the Python script.

This repo focuses on my works in the field of Computer Vision

使用 Python + OpenCV 讓 User 能夠透過字卡自行控制臉部特效

Custom C++ implementation of deep learning based OCR

A simple RAG/OCR application. It does its best to figure out a receipt image and add the content to a csv file.

BizCardX: Extracting Business Card Data with OCR | Technologies: OCR,streamlit GUI, SQL,Data Extraction

Advanced real-time screen translator for games, hardcoded subtitles in videos, static text and etc.

This is the capstone project that utilizes the ocr and MySQL to create a business card extractor and we can edit the extracted information from the business cards.

This project focuses on automating the extraction of registration numbers from scanned handwritten documents. By leveraging EasyOCR, an Optical Character Recognition (OCR) tool, and implementing various computer vision techniques, we have developed an effective solution for this task.

In this project I create a crossplatform app in python which can help capture text on the screen as an image and extract text from that image