Seeing Machines
Computer Vision with OpenCV & CNNs
- Saturday, 10 October 2026
- 9:30 am – 4:30 pm IST
- Main Seminar Hall, Block A, College of Engineering Kidangoor
Pixels are just numbers — until you know what to do with them. Start with classic OpenCV (filters, edges, contours), then build and train a convolutional neural network that classifies images, and finish by running real-time object detection on your own webcam feed.
You'll be able to…
- Process images and video streams with OpenCV
- Explain convolutions, pooling and feature maps visually
- Train a CNN and use transfer learning with a pre-trained model
- Run real-time object detection on a webcam
Prerequisites
- Step 03 or basic ML knowledge
- Comfortable with Python
What to bring
- Laptop (8 GB RAM recommended) and charger
- Python 3.11+ installed
- A Google account for Colab
- Curiosity — plenty of it
- OpenCV installed (pip install opencv-python)
- A working webcam
Agenda
- 09:30Check-in & coffeeGrab your badge, find a seat, connect to Wi-Fi.
- 10:00How machines see: from pixels to features
- 11:30Short break
- 11:45Guided walkthroughLive coding with the speaker — follow along on your laptop.
- 13:00Lunch
- 14:00Build a real-time mask/no-mask detectorWork in pairs. Mentors float between tables.
- 16:00Show & tellThree teams demo what they built.
- 16:30Wrap-up & next step preview
Speakers & mentors
Arjun Pillai
Embedded AI Engineer, Edgeworks Robotics, Technopark
Arjun puts neural networks on microcontrollers for agricultural drones. He believes every model should fit on a ₹500 board.
Sneha Thomas
Computer Vision Researcher, IIIT Kottayam
Sneha works on generative models for medical imaging and runs a weekend art collective that paints with diffusion models.
Venue
Main Seminar Hall, Block A, College of Engineering Kidangoor
Kidangoor South P.O., Kottayam, Kerala 686583, India