Face identification with ID3 Technologies
End-to-end AI solution for face identification running on STM32 microcontrollers.
In today's fast-paced world, smart homes and access control systems have become a necessity for people who value safety and efficiency.
With AI face identification running on STM32 microcontrollers, anyone can now experience security-grade applications without compromising performance or biometric data privacy.
ID3 Technologies, an ST authorized partner company, has developed a tiny, fast and accurate AI software solution for face recognition. It is already available on STM32H7 and can be easily ported on high-performance STM32 MCUs and MPUs.
This turnkey solution is ready for a commercial application. Contact us to learn more.
Demonstration based on B-CAMS-OMV. Can be adapted on any CMOS RGB image sensors.
Embedded biometric libraries:
Faces detection process < 0.4 s on STM32H747 (Cortex M7) @ 400 MHz
Faces recognition process <1.2 s on STM32H747 (Cortex M7) @ 400 MHz
With AI face identification running on STM32 microcontrollers, anyone can now experience security-grade applications without compromising performance or biometric data privacy.
ID3 Technologies, an ST authorized partner company, has developed a tiny, fast and accurate AI software solution for face recognition. It is already available on STM32H7 and can be easily ported on high-performance STM32 MCUs and MPUs.
This turnkey solution is ready for a commercial application. Contact us to learn more.
Key features
- Records up to 1000 faces with excellent accuracy
- Trained with over 40 million labeled images
- Detects multiple faces simultaneously
- On-board enrolment
- Supports indoor/outdoor scenario
- Includes user application
- Recognizes faces at distances greater than 3 meters (camera-dependent)
- Thoroughly validated on people of diverse ages, ethnicities, and in various scenarios
Sensor
Demonstration based on B-CAMS-OMV. Can be adapted on any CMOS RGB image sensors.
Memory footprint
Embedded biometric libraries:
- Flash: 4 Mbytes for AI libraries
- External Ram: 768 Kbytes
- Internal Ram: 433 Kbytes shared with user application
Inference time
Faces detection process < 0.4 s on STM32H747 (Cortex M7) @ 400 MHz
Faces recognition process <1.2 s on STM32H747 (Cortex M7) @ 400 MHz
Resources
Optimized with STM32Cube.AI
A free STM32Cube expansion package, X-CUBE-AI allows developers to convert pretrained AI algorithms automatically, such as neural network and machine learning models, into optimized C code for STM32.
Compatible with STM32H7 series
The STM32 family of 32-bit microcontrollers based on the Arm Cortex®-M processor is designed to offer new degrees of freedom to MCU users. It offers products combining very high performance, real-time capabilities, digital signal processing, low-power / low-voltage operation, and connectivity, while maintaining full integration and ease of development.
