BIBORA VISION AI
Back to Articles
AI Solution

Pilot Testing Bibora Vision AI Kiosk at Kantin Guru SK Presint 11 (2) Putrajaya

October 4, 2026 3 min read

Real-World Deployment at SK Presint 11 (2) Putrajaya

Bibora Vision AI has officially kicked off pilot testing at Kantin Guru (Teachers Canteen), SK Presint 11 (2) Putrajaya. This real-world deployment marks a significant milestone in bringing AI-powered visual self-checkout to school and canteen environments.

"Bibora Vision AI is currently pilot testing at Kantin Guru SK Presint 11 (2) Putrajaya, achieving 82% accuracy in scanning and identifying complex Nasi Campur plates in real time."
Pilot Testing at Kantin Guru SK Presint 11 (2) Putrajaya

Why Nasi Campur Presents a Unique AI Challenge

Nasi Campur is notorious for being one of the hardest food categories for traditional automated billing. Dishes feature overlapping curries, varying gravy density (kuah banjir), and different portion cuts of chicken, fish, and vegetables placed closely together on a single plate.

Despite these visual complexities, our overhead computer vision model is already achieving 82% accuracy in identifying distinct dishes and portion sizes during peak lunch hours.

Key Highlights of the Pilot Test

  • Location: Kantin Guru, SK Presint 11 (2) Putrajaya
  • Current Recognition Accuracy: 82% (and continuously improving with daily model training)
  • Primary Dish Focus: Nasi Campur, side dishes, traditional curries, and beverages
  • Target Outcome: Drastically reduce queue times for teachers during short break intervals so they can spend more time resting and preparing for classes.

Step-by-Step AI Scanning Process

  1. Plate Placement: Teachers place their Nasi Campur plate directly under the Bibora Vision AI kiosk's overhead camera.
  2. Instant Instance Segmentation: The camera captures the plate visual and runs neural network instance segmentation to detect rice, gravies, meats, and vegetables.
  3. Itemized Billing & Pricing: The kiosk calculates the exact bill based on detected dishes and displays the total in under 1 second.
  4. Cashless Checkout: Teachers scan and pay instantly using DuitNow QR or e-wallets, completing checkout in seconds.

Next Steps and Model Optimization

With active data ingestion from Kantin Guru SK Presint 11 (2), our deep learning model receives continuous dataset updates daily. As more plate variations are scanned, the neural network's confidence score continues to rise toward our target 99%+ accuracy threshold across all Malaysian canteen menus.