We salute hackers who make technology useful for people in emerging markets. Leigh Johnson joined that select group when she accepted the challenge to build portable machine vision units that work offline and can be deployed for under $100 each. For hardware, a Raspberry Pi with camera plus screen can fit under that cost ceiling, and the software to give it sight is the focus of her 2018 Hackaday Superconference presentation. (Video also embedded below.)
The talk is a very concise 13 minutes, so Leigh flies through definitions of basic terms, before quickly naming TensorFlow and Keras as the tools she used. The time she saved here was spent on explaining what convolutional neural networks are and how they work, just enough to prepare the audience. But all of that is really just background, the meat of the talk is self-contained examples that Leigh has put together and made available online. I love to see that since it means you go beyond just watching and try it out for yourself. Continue reading “Leigh Johnson’s Guide To Machine Vision On Raspberry Pi”








The first thing to catch one’s eye might be that leftmost seven-segment digit. There is a simple reason it doesn’t match its neighbors: [Juan] had to use what he had available, and that meant a mismatched digit. Fortunately, 3D printing one’s own enclosure meant it could be gracefully worked into the design, instead of getting a Dremel or utility knife involved. The next is a bit less obvious: the display lacked a decimal point in the second digit position, so an LED tucked in underneath does the job. Finally, the knob on the right could reasonably be thought to be a rotary encoder, but it’s actually connected to a small DC motor. By biasing the motor with a small DC voltage applied to one lead and reading the resulting voltage from the other, the knob’s speed and direction can be detected, doing a serviceable job as rotary encoder substitute.