Skip to content
View aryanthakur-04's full-sized avatar

Block or report aryanthakur-04

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
aryanthakur-04/README.md

💫 About Me:

I'm currently working on:
Wrapped up an R&D internship at Rapiscan Systems as sole developer on an AI-assisted Image Quality Report Generation Tool — a YOLOv8-OBB + OpenCV pipeline that automates X-ray machine qualification testing across 4 industry standards (ASTM, BCAS, RTP, EWSTP), shipped across 3 production releases. Also built X-TADS, an AI-powered X-ray threat detection system on YOLOv5.

I'm looking to collaborate on:
Computer vision projects that have to survive contact with the real world and not just look good in a demo. If you're building something detection-heavy, I'm interested.

I'm looking for help with:
Getting sharper at full-stack work (React in particular), and figuring out how ML models actually hold up once they leave the notebook and hit production.

I'm currently learning:
How to run engineering projects without losing my mind along the way, Agile in theory is not the same thing as Agile in practice.

Ask me about:
YOLO, X-ray threat detection, or how to organize a hackathon without it turning into chaos.

Fun fact:
Somewhere between internships and exams I ended up treasurer of a comedy club.

🌐 Socials:

LinkedIn email

💻 Tech Stack:

Java HTML5 Python Anaconda FastAPI NodeJS OpenCV React React Native MySQL SQLite Prisma Figma NumPy Matplotlib Pandas PyTorch scikit-learn Scipy TensorFlow Keras GitHub Notion Raspberry Pi Docker Postgres

✍️ Random Dev Quote

Pinned Loading

  1. traffic-sign-recognition-system traffic-sign-recognition-system Public

    Hybrid CNN + YOLOv5 pipeline for German Traffic Sign Recognition (GTSRB): a Keras CNN classifies cropped signs into 43 classes while a fine-tuned YOLOv5 detects and labels signs in full images.

    Jupyter Notebook

  2. face-recognition-service face-recognition-service Public

    ONNX-based face detection & identification microservice (FastAPI + SQLite), refactored from a Colab notebook into a production-grade Python project.

    Jupyter Notebook

  3. pii-redaction-pipeline pii-redaction-pipeline Public

    YOLOv5 + OCR pipeline that detects, extracts, and redacts PII/PHI text burned into medical images. Config-driven, tested, Gradio UI.

    Python

  4. diabetes-prediction-pipeline diabetes-prediction-pipeline Public

    Modular ML pipeline predicting diabetes onset (Pima Indians dataset) — SMOTE, 4-model comparison, SHAP explainability, rule-based risk scorecard.

    Python