Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

The images containing touching kernels of hard red spring (HRS) wheat, durum wheat, barley, oats, and rye were processed for software-separation using a disconnect algorithm. The kernels were imaged again after they were manually separated. Geometrical features were extracted from both software-separated and physically separated kernels. Software-separation did not cause appreciable change in the geometrical features of the grains except for the area of oats. An overall classification success of 93.3% was achieved in a five-way classification among HRS wheat, durum wheat, barley, oats, and rye for the software-separated kernels. Classification of physically separated kernels resulted in 95.0% correctly classified kernels.