A machine learning application to automatically evaluate examination papers. Handwriting Recognition, Semantic segmentation, NLP, Android, Web, Python Backend, SQL, etc.

Fit-O-Fine is a Real-time medical test report store and retrieve using Blockchain and MongoDB • Developed secure login system using web3.js, created a RESTful api using Express.js • Integrated Gemini pro model with chat system to find medical queries and realtime doctor availability in the locality using langchain.js, Google generative AI.

A full-stack application designed to help users manage their daily medicine intake and dosage schedules. The app allows users to plan, track, and get reminders for their pills, ensuring they never miss a dose.

Computer Vision and IOT projects (ML and DL techniques)

Repository for HackUMBC 2020 submission ( Winners of education track advanced) .A fully voice controlled website with OCR based feature to convert pdf to audio books along with speech to text feature for visually impaired people.

This repository aims to implement a Machine learning model which can take any invoice image as an input and give a json file containing fields like invoice date, seller name, buyer name, addresses, due date as an output.

AI powered calculator, where the input equations and problems could be input just like writing on a paper.

Recognizes text from any image and prints them

In this project, we are aiming to build real-time text detection and translation glasses.

Đồ án Summer24 sự dẫn dắt của Thầy Nguyễn Thành Ý cùng với đồng đội G63

EzReceiptz is a desktop application built with Electron that extracts data from receipt files using OCR and uploads the information to a Google Sheet. The interface lets you drag and drop PDF or PNG receipts, run OCR with Tesseract.js, and then send the recognized data directly to a spreadsheet.

Project where we analyzed school curriculums by converting school textbooks to knowledge graphs.

Simple Vite+React client app, that can OCR images or PDFs using tessaract-js and pdf.js from Mozilla, all on client side.

Advanced Python toolkit for extracting Hindi text from scanned book images. Leveraging Tesseract OCR with intelligent OpenCV preprocessing for superior accuracy. Transform your digitization workflow with this powerful OCR solution designed specifically for Hindi manuscripts and books.

This project implements a dual-mode attendance system using: Face Recognition (ArcFace + classifier) - Card-Based Attendance (OCR extraction of registration/roll number)

real time text detection with deep learning

Get text from images.

Newspaper mining and the analysis of the results using python. Cleaning the text using OCR.

A collection of prebuilt binaries for working with android and OCR as a python package\n - adb \n -scrcpy \n - keyboardservice \n - tessaract

My contribution includes building an intelligent pipeline that extracts resume text via Tesseract OCR, processes it through OpenAI's API to identify optimal job titles, and feeds these to a custom LinkedIn scraper for real-time, personalized job recommendations based on users' experience and skills