Damien Matti

MSc Semester Project

Title

Mushroom recognition

Candidate

Damien Matti

Supervisor

Prof. Dr. Touradj Ebrahimi

Assistant: Peter Vajda

Expected

June 11, 2010

Place

EPFL

Description

Imagine a scenario where you are collecting mushrooms in the forest with your friends. You take a picture of a mushroom with your mobile phone and send it to a server which will provide on your mobile phone some information on the specific mushroom. For example, in this way you can discover whether this mushroom contains poison: you can SAVE LIFE with this application! The application can be interactive and use the environment variables such as GPS data or date.
The goal of this project is to develop a mushroom recognition application based on special visual features of mushrooms, extracted from the picture of the object. These features are based on the real features that a biologist would use for mushroom classification. The following tasks should be performed:

  1. Review the state of the art on mushroom recognition.
  2. Study biological point of view of mushroom recognition.
    1. Meet and discuss the task with a professional scientist in this field.
  3. Collect or create a small mushroom database.
  4. Implement and validate a mobile client application on an Android phone, containing the following parts:
    1. GUI for mobile phone, which allows capture and display of a flower.
    2. Communication module through a wireless channel to exchange data/image with a server.
  5. Implement and validate a server side application. This application can use existing methods and do not need to be re-implemented all from scratch. It should contain:
    1. Communication framework with mobile through wireless channel.
    2. Modular and extensible framework for feature extractions.
    3. Feature extractions with distance measurement including the following features categories: Color features, Shape features.
    4. Segmentation.
    5. Database search.
  6. Assessment and comparison of different features and their respective distance metrics.
  7. Demonstration application on mobile phone in such a way that it can be used by native users.