The aim of this project is to apply data science in the field of plant biotechnology to study seed viability with infrared thermography. Seed samples will be prepared with the different viability by using various artificial treatments for germination purpose. Thermal and visible images will be recorded periodically for the germinating seeds during the standard five day germination test. Each individual seed area in the visible images will be segmented with an edge detection method, and the average temperature of the corresponding area in the infrared images will be calculated as the representative temperature for a seed at that time. Different characteristic parameters extracted from the recorded temperature will be analyzed to show the difference of the temperature fluctuations between the seeds samples with different viability.
