Fungus Detection System

Fungus is the main risk for food logistics and millions of euro lost per annum just due to different kinds of fungus. The main aim of this research is to develop an automated system for the detection of fungus spores in air. We are developing a novel system for fungus detection which is based on computer vision. Air samples are collected on the glass slides and then placed these samples under microscopic camera and images of air samples are obtained. Pre processing techniques, as images have noise regions and spores boundaries are not clear, have been applied and different filters have been used. Which is followed by thresholding and morphologic operation. Then features are extracted and feature vector were formed. After that Support Vector Machine (SVM) was used for the purpose of classification.