Skip to content
View venkatdurga's full-sized avatar

Highlights

  • Pro

Block or report venkatdurga

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
venkatdurga/README.md

Hi 👋, I'm Kondepudi Venkata Durga

AI Engineer | Computer Vision | Deep Learning | Backend Systems | Cloud | System Design

AI Engineer with 2+ years of experience building production-grade computer vision and deep learning systems. Specialized in real-time AI pipelines, OCR systems, spoof detection, and scalable backend deployments.


👨‍💻 MySelf

I design and deploy end-to-end AI systems that move beyond research into real-world impact.
My work focuses on combining deep learning models with robust backend infrastructure to deliver scalable and reliable AI-powered applications.

✔ Production AI APIs
✔ Real-time Computer Vision Systems
✔ Intelligent OCR & Document Processing
✔ Secure AI-based Identity & Liveliness Detection
✔ Scalable containerized deployments


🚀 Core Expertise

🧠 Artificial Intelligence & Deep Learning

  • CNN Architectures for Vision Tasks
  • Model Optimization & Threshold Tuning
  • Multi-Stream Neural Networks
  • Real-time Inference Systems

👁️ Computer Vision

  • Object Detection (YOLO-based systems)
  • OCR Pipelines (Tesseract, EasyOCR, DocTR)
  • Image Preprocessing & Enhancement
  • Spoof & Liveliness Detection

🌐 Backend & APIs

  • Flask & FastAPI production services
  • REST API design for ML systems
  • Asynchronous processing & job queues
  • Logging, monitoring & error handling

⚙️ System Design & Deployment

  • Docker & Podman containerization
  • NGINX reverse proxy configurations
  • Multi-instance API deployments
  • Redis-based task queues & caching
  • On-premise server deployments (Linux/RHEL)

🏗️ Notable Projects

🔹 AutoPlateX — AI Vehicle Number Plate Detection & OCR Platform
A real-time computer vision system for automatic number plate detection and text extraction, designed for traffic monitoring, enforcement automation, and smart transport systems.

🔹 SPoD (Spot the Dupe) — Liveliness & Spoof Detection System
Deep learning–based identity verification platform with facial liveliness checks, motion validation, and advanced anti-spoofing techniques for secure authentication workflows.

🔹 Production OCR API Platform
Scalable multi-engine OCR backend supporting images and PDFs, built for high-volume document digitization and structured data extraction pipelines.

🔹 TransBot — Offline AI Chatbot for Government Transport Services
Retrieval-Augmented Generation (RAG) powered assistant designed for fully offline deployment using local LLMs to deliver accurate transport and vehicle-related information.

🔹 ATS (Automatic Testing System) — AI Vehicle Inspection Platform
AI-driven vehicle testing and compliance analysis system built to automate inspection workflows and improve accuracy in automated testing centers.


🛠️ Tech Stack

Languages
Python • SQL • Bash

AI/ML Frameworks
TensorFlow • PyTorch • OpenCV • Scikit-learn

OCR & Vision Tools
Tesseract • EasyOCR • DocTR • YOLO

Backend & Databases
Flask • FastAPI • PostgreSQL • Redis

DevOps & Infrastructure
Docker • Podman • NGINX • Linux (RHEL/Ubuntu)

📊 GitHub Activity

Venkat's GitHub Stats

Top Languages


📬 Let's Connect!

Always excited to collaborate on large-scale MLOps design patterns, low-latency vision architectures, and real-world AI applications.

Pinned Loading

  1. venkatdurga venkatdurga Public

  2. Seatbelt-Detection-Using-DWYOLOv8-Model Seatbelt-Detection-Using-DWYOLOv8-Model Public

    This project automates seat belt detection in two phases: 1) Detecting vehicle windshields using YOLOv5, and 2) Identifying seat belt usage within the detected region using a custom DW-YOLOv8 model…

    Jupyter Notebook 1

  3. Flutter_Projects Flutter_Projects Public

    Collection of Flutter applications for vehicle analysis: license plate detection, vehicle type identification, and spoof detection. Built with camera integration, image processing, and REST API con…

    Dart

  4. OCR_interface OCR_interface Public

    Forked from KorkanaRahul/OCR_interface

    OCR_interface

    Jupyter Notebook

  5. PDF_QA_CHATBOT PDF_QA_CHATBOT Public

    PDF Q&A Chatbot - An intelligent chatbot system that extracts Q&A pairs from PDF documents and uses fine-tuned DistilBERT models to answer questions with high accuracy. Includes a FastAPI backend, …

    Python

  6. SmartTradeAI SmartTradeAI Public

    SmartTradeAI is an AI-powered Chrome extension that provides real-time market analysis and trading signals for Binance using moving average, RSI, and MACD strategies.

    JavaScript