DIGITAL IMAGE-ANALYSIS FOR SOFTWARE SEPARATION AND CLASSIFICATION OF TOUCHING GRAINS .1. DISCONNECT ALGORITHM

An algorithm to segment connected grain kernel image regions is descri bed. The algorithm attempts to eliminate the need for well-separated k ernels in machine-vision-based grain grading experiments. The algorith m uses image transforms from the discipline of mathematical morphology . The algorithm was tested on 746 connected kernels of hard red spring (HRS) wheat, 391 connected kernels of durum wheat, 376 connected kern els of barley, 286 connected kernels of oats, and 393 connected kernel s of rye. The spatial arrangement of the touching kernels was random i n all of the images used. The algorithm was successful in disconnectin g kernels of HRS wheat, durum wheat, barley, oats, and rye with accura cies of 95, 95, 94, 79, and 89%, respectively. The important limitatio n of the algorithm was that it failed when the connected kernels forme d a relatively long isthmus or bridge between them.