GPU-enhanced OCR pipeline for historical newspapers using Google Vision or Tesseract

A discord bot that authenticates discord members as university students by providing a photo of their student ID.

This web app allows users to upload health reports (PDFs or images), automatically extract key parameters using OCR (Google Vision API), and view the data in a clean, interactive table with basic insights and trend simulation.

[see-realview] 프로젝트 저장소입니다. 네이버 블로그 포스트를 검색하여 해당 포스트의 광고 여부를 분석합니다.

This repository hosts a comprehensive open data project focused on food information, integrating web scraping, OCR, and data parsing to build a structured database of food products, categories, and nutrition facts.

Using Google Vision API to Get Text From (Unreadable) Electoral Rolls

텍스트 추출기 - 이미지를 txt로 변환

This library aims to provide a unified approach for representing generative AI components, and enable seamless integration and interoperability with AI services from various providers such as Azure OpenAI, Amazon, Google and Aliyun/Alicloud. Compatible to .NET standard 2.0 and .NET 8.0+.

Web framework to convert 7/12 Extract pdf using OCR to editable excel file. TEAM NAME: X Æ A-3

Using Google Vision AI

A basic template to include Google-Vision-OCR in your project

Dokra is an intelligent backend API for analyzing and extracting structured information from documents (PDFs, images, and plain text), powered by LLMs.

A platform designed for students to automate their study process by digitizing handwritten notes and creating study materials such as Quizzes, short QnAs for efficient exam preparation.

Discord text recognition(ocr) bot