Gemma-3 OCR exemplifies the confluence of abstruse computer vision and arcane NLP, leveraging Gemma-3 Vision’s neural framework for precise OCR and semantically refined text curation. Powered by Streamlit and Ollama, this hermetic system converts visual data into perspicuous, markdown-rendered output, ensuring maximal accuracy and confidentiality.

A very simple news crawler with a funny name

أداة متقدمة لمعالجة الكتب المصورة وتحويلها إلى نصوص قابلة للبحث باستخدام OCR

Official Implementation of Fin-ExBERT: A GNN augmented BERT model finetuned on financial data capable of performing Natural Language Inference and User instructed Text Extraction tasks

File Extractor Pro is a GUI application to extract and process files based on specified criteria. It allows users to include or exclude files based on extensions, include hidden files, and generate detailed extraction reports.

AI-based Media and Misinformation Content Analysis Tool: Analyze text and images

A Flask-based web app integrated with Twilio that automatically receives resumes via WhatsApp, extracts candidate details (name, email, phone), and stores them in Google Sheets and Drive using NLP and regex-based text extraction.

Minimal text dataset builder for ML students - zero dependencies, simple API, auto deduplication

Toolkit for the Målfrid project

python parser for human readable dates

A Python tool to translate PDF documents page-by-page using the Google Gemini, maintaining translation context.

Advanced PDF layout analysis engine for extracting figures, tables, and structured content from complex engineering documents using computer vision and machine learning.

Extract text from images using multiple AI providers - local SmolVLM, Ollama LLaVA, or OpenAI GPT-4o

Extract links from Markdown files

A powerful Python tool for validating OCR accuracy by comparing extracted text from images against expected results, with real-time monitoring capabilities and detailed similarity metrics.

Dataiku DSS plugin to perform optical character recognition (OCR) using the Tesseract engine.

🔧 AI-powered P&ID PDF processor with custom YOLO detection & multi-OCR support. Extract components & text from engineering diagrams automatically.

Automated Resume Parser – Built at Codec Technologies during internship. Designed an intelligent parser that extracts candidate details (name, contact, skills, experience, education) from PDF/DOCX resumes and converts them into structured data, enhancing recruitment efficiency.

AI-powered document analysis service combining AWS Textract, Bedrock, and intelligent blur detection. Supports CLI and serverless Lambda API for Malaysian documents (licenses, receipts, ID cards, utility bills).

Extract price amount and currency symbol from a raw text string