:mag: Data pipeline for crawling PDFs from the Web and transforming their contents into structured data using AWS textract. Built with AWS CDK + TypeScript

ATS Buddy is a production-ready, serverless AI resume analyzer built on AWS Bedrock (Nova Lite). It intelligently compares resumes against job descriptions, providing compatibility scores, missing keyword detection, and AI-powered resume enhancements—all while ensuring enterprise-grade PII protection and cost-efficient auto-scaling.

Virtual patient-doctor connections via video calls, with additional chatbot and AI doctor interaction options. Patients can conveniently upload reports for OCR-based summarization.

Extract text and data from any document using Amazon Textract in Node.js

:white_square_button: A flask webapp to solve sudoku from image input

Aws Textract Helper

Using Serverless to consume and processing WA Animals adoption forms using Amazon Textract and placing that data in DynamoDB

REST API (built using AWS Lambda and Amazon Textract) to extract structured text data from images of Indian OVD(s) (Officially Valid Documents) like Aadhaar card, PAN Card, Driving License, Passport, etc.

A image OCR scanner based on AWS Textract, built as a serverless microservice

Real-time object detection (YOLOv8), tracking (SORT), and text recognition (EasyOCR) pipeline deployed on AWS using producer-consumer architecture with Kinesis Video Streams, EC2, SQS, Lambda, S3, Textract and DynamoDB.

Exemplos para utilização de plataforma de Machine Learning no modelo SaaS como alternativa para aceleração de funcionalidades baseadas em AI em produtos digitais.

Convert an image to an HTML form using Amazon Textract and NodeJS

This AWS application extract the whole text from scanned documents. Text + Extract = Textract ( Image to Text )

Implementación sobre los servicios de AWS para analizar recibos de bancos ecuatorianos mediante inteligencia artificial y poder integrarse con cualquier sistema de administración de pagos.

Sample AWS Lambda functions using Textract and Comprehend Medical to pull entities from images and PDFs

The ai-alfresco project is a solution that integrates Alfresco Content Services with AWS artificial intelligence services such as Textract, Translate, and Polly.

A web application that identifies all Artist's Exhibition Titles from a given CV. The text detection is handled by AWS Textract and title detection is handled by AWS Comprehend.

In this project, we will build a practical intelligent document processing system that automatically extracts data from forms, invoices, receipts, contracts, etc. We will utilize Python, Amazon Textract, and AWS-managed Amazon Bedrock.

Extracting text,form,table using Textract

This platform is an AI-powered solution designed to enhance UPSC preparation for aspirants.

Cloud based OCR for Statutory Forms and Documents

:robot: Ferramenta que lê os arquivos PDFs, realiza OCR e salva em JSON.

A simple web interface which extracts texts from Images & PDF files using AWS Textract service

Detection of Car number plate and extraction of number.

Microservice responsible to extract text from image using AWS Textract service

By anticipating the unpleasant side effects of the medication based on its features, you can assist the doctor in prescribing a medication that has fewer or no side effects.

A Golang HTTP API for extracting text from documents and images using AWS Textract, featuring API key authentication and designed for serverless deployment on AWS Lambda.

An event-driven pipeline for extracting text from an email attachment (in progress)

This project automates the extraction, summarization, and analysis of various document formats (PDF, TXT, CSV, images) without requiring manual review.

Demo for AWS Textextract and Bedrock