If you haven't looked at Google’s open source TensorFlow machine learning platform, you could be missing an opportunity.
A small family cucumber farm in Japandid just that. Cucumbers need to be sortd and categorised based on size, shape, color, and other characteristics, a difficult, labour intensive and time-consuming process. Automating the process, and employing a mechanical arm delivered a 70 percent accurate solution reducing human labor.
Makoto first got the idea to explore machine learning for sorting cucumbers from a completely different use case: Google AlphaGo competing with the world's top professional Go player. "When I saw the Google's AlphaGo, I realized something really serious is happening here,” said Makoto. “That was the trigger for me to start developing the cucumber sorter with deep learning technology." Using deep learning for image recognition allows a computer to learn from a training data set what the important "features" of the images are.
