Student research opportunities

Card Counter: Recognizing a Set of Planar Textures using Mobile Phone Camera

Project Code: CECS_1147

This project is available at the following levels:
CS single semester, Engn4200, Engn R&D, Honours, Summer Scholar, Masters

Keywords:

Computer Vision, Image Processing, Machine Learning

Supervisor:

Professor Fatih Porikli

Outline:

This project aims for developing software that can process in real-time images acquired by a mobile phone to detect and track multiple textures such as playing cards on a table.

Goals of this project

- Train a multi-classifier offline
- Apply the multi-class classifier in real-time to detect and recognize textures
- Develop solutions that are invariant to affine transformations

Requirements/Prerequisites

- Programming skills (C++, Java, etc for apps)
- Strong background in computer vision and image/video processing

This is a more practical than theoretical project however, you will need to have some analytical and mathematical skills to traverse certain problems.

Student Gain

- Learn how to recognize visual textures
- Learn how to capture visual data
- Learn fundamental computer vision and machine learning methods
- Chance to work on an exciting computer vision application
- Gain valuable experience on challenging real-world problems
- Experience working with web software development practises
- Explore the possibilities of a research career in academia or an applied research career in industry
- Possibility of seeing their work commercialised as part of the wider project goals

Contact: