A comprehensive sudoku solver. Can solve boards on a web browser, an android app and in the terminal

Vehicle Number Plate detection - Identify the license place in the image and do an OCR to extract the characters from the detected license plate

OCR WorkShop for ODS.ai DataFest 2020

converting scanned pdf to text document

Intelligent File Delivery Tool

Built a tool that detects and corrects faulty images uploaded,using OpenCV and OCR technologies.Useful when uploading data in identity verfication portals. Won an internal hackaton and quali- fied for nationwide event.

Python OCR Tool: Text from Images in a Snap! This Python app with a user-friendly GUI lets you extract text from pictures (JPEG, PNG) and save it in your preferred format (TXT, DOCX, etc.). No more manual typing - just point, click, and extract!

Simple python GUI app to convert screenshot to text (OCR)

Proyecto de prácticas de la asignatura Inteligencia Ambiental.

This is the code from the article I published on a Medium blog. It demonstrates how to extract the count of votes after the 2020 US election day using images published on a news media.

A simple web app that allows users to convert PDFs to various file formats, as well as perform OCR (Optical Character Recognition) on image files to extract text.

Columbia University: COMS 4995 Applied Computer Vision, US license plate OCR fine-tune

This project aims to simplify document processing by offering a streamlined solution for extracting, reading, and translating text from PDF files, leverages advanced OCR technology to extract text with precision. Users can not only read the extracted text in its original language but also translate it into various languages.

Computer vision for object detection, license plate recognition and identification

This Flask application empowers users to seamlessly upload image files like invoices or receipts, extract text using robust OCR technologies, and efficiently isolate key fields using precise regular expressions and multiprocessing to streamline data extraction and enhance productivity.

Data capture (OCR recognition, NLP extraction), data cleansing (data proofreading), and data integration (integration of different materials into a single system) will be performed on three types of data

Integrated with screen shooter OCR program

Python OCR (Optical Character Recognition)