AI Digit Recognition with PiCamera #celebratephotography
From Dimiter Kendri on Hackster.io:
In this project, we are going to train a deep convolutional neural network to transcribe digits. Then we are going to use the data from the learning stage to allow the Pi Camera to read and recognize digits. The AI pipeline will be implemented using Scikit and OpenCV 3.3 for image manipulation and Keras which uses Tensorflow as a back-end for the deep learning part.
To keep this easy no feature localization stage is done so you’ll have to shove the image in front of the camera lens so that it’s the only feature that it sees.
The MNIST dataset will be used. It is comprised of 60,000training examples and 10,000 test examples of the handwritten digits 0–9,formatted as 28×28-pixel monochrome images.
We #celebratephotography here at Adafruit every Saturday. From photographers of all levels to projects you have made or those that inspire you to make, we’re on it! Got a tip? Well, send it in!
If you’re interested in making your own project and need some gear, we’ve got you covered. Be sure to check out our Raspberry Pi accessories and our DIY cameras.