You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Developing a Streamlit application that enables users to upload business card images and extract key details using easyOCR. The app allows users to manage the extracted data (view, update, delete) and securely stores it in a MySQL database. It also highlights extracted text directly on the business card image using Pillow.
With local (Ollama setup, codellama), The Code Assistant project is a web application designed to extract code snippets from images using Optical Character Recognition (OCR) technology.
MyLittleOCR 是一个统一的 OCR 库包装器,提供一致的 API,便于集成和切换多个 OCR 引擎。 MyLittleOCR is a unified OCR wrapper providing a consistent API for seamless integration and switching between multiple OCR engines.
An automatic tracking system through cameras to detect license plates of traffic violators, which uses the YOLOv8 model to recognize the license plate and apply OCR to read it
Image-To-Text-Tool is a Python application that converts images into editable text using OCR technology. Leveraging Tesseract OCR, this tool accurately extracts text from various image formats, supporting Vietnamese language. It's designed for easy use, helping users digitize documents efficiently and enhance accessibility.
This Django application helps extract data from Egyptian national IDs written in Arabic using pre-trained models. The application leverages EasyOCR and OpenCV to process images of IDs and extract important details such as name, ID number, birth date, and more.