Overview
We no longer maintain this tutorial. Here are some up-to-date image recognition tutorials that you can view:
- Adding sight to your sensors using the OpenMV Cam H7 Plus and Edge Impulse
- Learn how to use Tensorflow Lite for Microcontrollers to run a neural network to recognize people in images
This guide shows you how to perform real-time image recognition on a low-power Arm Cortex-M7 processor, using the Arm CMSIS-NN library, version CMSIS 5.7.0. The Cortex-M7 processor is found in a range of solutions from various microcontroller vendors.
Watch a video demo of the steps in this guide:
Increased compute performance in the smallest Cortex-M-based devices is enabling more data processing to move to the edge. Machine learning (ML) no longer needs to take place in the cloud or only on advanced application processors. Now, you can take advantage of the benefits afforded by edge computing, such as reduced bandwidth and time-to-decision, increased privacy and reliability, all without relying on an internet connection.
ML at the edge offers new possibilities for new real-time decision-making applications, from voice recognition for smart speakers to facial detection for surveillance cameras.