Skip to content
All ProjectsHASEEBΛI.
Computer Vision

Pakistani Currency Classifier

EfficientNetOpenCVTensorFlowKeras

The Challenge

Visually impaired individuals and automated cash-handling systems need instant, reliable identification of currency notes in real-time video streams.

The Solution

Fine-tuned the EfficientNet architecture on a curated dataset of Pakistani notes. Integrated with OpenCV for live video processing and real-time inference.

Key Results

  • Achieved 99% accuracy in recognition tasks.
  • Enables fast, secure automated cash-handling workflows.
  • Real-time processing capability via OpenCV integration.

Project Details

CategoryComputer Vision
RoleLead Developer
CompletedDecember 2023

Related case studies

Agentic RAG

Malakah: Agentic RAG Legal Assistant

97–98%

Agentic RAG legal assistant for Saudi regulatory law. 97–98% recall@10 across a bilingual English-Arabic corpus validated by legal domain experts.

Agentic RAG

Enterprise AI Search and Chatbot: Energy Sector

90%+

Agentic RAG platform indexing 300+ GB of petroleum engineering documentation. 90%+ retrieval hit rate on domain-heavy technical queries.

AI SaaS

Multi-Tenant AI SaaS Platform: Document Intelligence

32

AI-powered document intelligence platform with multi-tenant architecture, RBAC, and hybrid retrieval.

Previous

Bilingual Voice Agent on LiveKit

Real-time bilingual voice agent for a datacenter reception kiosk, running LLM and TTS inference on CPU‑only compute under live event conditions.

Next

Urdu Sentiment Analysis — FYP & Publication

Hybrid CNN-RNN model for Urdu sentiment classification, published in a peer-reviewed journal with 96% F1 score.