Accurate seed sorting with machine vision

Seed sorting - Copy

Agricultural Research Service (ARS) engineer Thomas C. Pearson has developed a highly-accurate portable machine that uses machine vision to sort seeds, according to an ARS press release.

Pearson had previously developed similar machine vision equipment, but with this seed-sorting model, the work is simpler and faster, according to Pearson. Seeds are placed into a vibrating hopper where they slide down any of the three chutes. Once the seeds fall from the chute, an ARS-developed color camera with a CMOS image sensor captures images of the seeds and sends it via a circuit board to a chip for image processing.

The chip, which is equipped with pre-programmed data that determines whether a seed’s surface texture and RGB color values more closely match those of an “accept” seed rather than those of a “reject." Seeds that closely match the parameters defined for “rejects” are quickly dislodged from the machine via an air blast into the reject container, while those seeds that pass fall into the “accept” container.

In Pearson’s tests at his ARS laboratory at the Center for Grain and Animal Health Research, he showed that the sorter can help wheat breeders to separate kernels of hard red wheat from kernels of hard white winter wheat with 98.6% accuracy. In addition, the sorter was accurate 94% of the time when separating yellow flax from brown flax seed.

View the ARS press release.

Also check out:
Package inspection system tracks and traces fresh produce
Robot lettuce pickers and the future of farming
Factory automation market could reach $185 billion by 2016
(Slideshow) Five applications we never thought of for 3D scanning technology

Share your vision-related news by contacting James Carroll, Senior Web Editor, Vision Systems Design

To receive news like this in your inbox, click here.


Featured Vision Photos


10 important considerations for designing a machine vision system

Developing a machine vision system is a complex activity involving optical engineering, electrical engineering, programming, and mechanical engineering.  Moving from inception through installa...

Vision technologies for robotics: Application do’s and don’ts

This webcast will offer tips and examples for integration of machine vision systems in robotics applications. Expert Jeff Boeve of JR Automation will explain how to clearly define your pass/fa...
December 9, 2014

Solving factory automation challenges with machine vision

What do you need to know to implement your machine vision setup for industrial automation? This webcast will answer that question using real-world application examples—such as inspection, assembly,...
November 18, 2014

Performing effective 2D and 3D pattern matching in machine vision applications

This webcast, sponsored by MVTec, will explain how pattern matching works and in what applications is being used.

October 30, 2014


Click here to view archived Vision Systems Design articles