When it comes to farming veggieslike cucumbers, the sorting processcan often be just as hard and tricky as actually growing them. That’s why Makoto Koike is using Google’sTensorFlow machine learning technology to categorize the cucumbers on his family’s farm by size, shape and color, enabling them to focus on more important and less tedious work.
A camera-equippedRaspberry Pi 3 is used totake images of the cucumbers and send them to a small-scale TensorFlow neural network. The pictures are then forwarded toa larger network running ona linux server to performa more detailed classification. From there, thecommands are fed to anArduino Microthat controls aconveyor belt systemthathandles the actual sorting, droppingthem into their respective container.
You can r ead all about the Google AI project here , as well as see it in action below!