An automated system for vigor testing three-day-old soybean seedlings

An image processing computer application to automatically assess the vigor of three-day-old soybean (Glycine max [L.] Merrill.) seedlings was developed. The software operates on acquired digital images of soybean seed lots placed on a paper towel. Soybean seedlings were extracted away from the paper towel and converted into various digital representations. These representations were used to analyze the seedlings and segment them into normal and abnormal categories. The normal seedlings were further processed so that a one-pixel-wide summary structure of the shape of the seedling was produced. From this summary structure, the software classified the seedlings into six type categories based on their shape. Each normal seedling was processed to remove the cotyledon portion of the summary structure based on the type category it fell into. The remaining summary structure, with the cotyledon removed, was then used to compute the length of each seedling in pixels. From these length measurements, speed of growth and uniformity of growth values were computed. These two values were normalized and combined into a zero to 1,000 vigor index for the seed lot. Combined with the post-processing corrective features, this computer software was able to achieve highly accurate and standardized measurements of each soybean seedling, providing an alternative to the current method of manually measuring soybean seedlings for speed and uniformity of growth when performing a vigor test.