BACKGROUND SEGMENTATION AND DIMENSIONAL MEASUREMENT OF CORN GERMPLASM

An automatic thresholding technique was developed to segment the backg round from the images of corn germplasm (ears of corn), The technique was a modification of Otsu's algorithm using probability theory Three different measures were used to evaluate the performance of the modifi ed Otsu's algorithm for background segmentation and subsequent dimensi onal measurement of corn germplasm, Modified Otsu's algorithm was foun d to perform better than Otsu's algorithm and was successful in automa tic background segmentation of all 80 images of corn germplasm include d in the study. This modified algorithm also eliminated the misclassif ication of exposed cob in the image as background which occurred with Otsu's algorithm. Subsequent dimensional measurements based on the seg mentation by the modified algorithm were also highly accurate.