The reference design deals with the design of implementing facial recognition using a microcontroller instead of a processor used earlier for the technology.
A facial recognition system is a technology capable of identifying or verifying a person from a digital image or a video frame from a video source. There are multiple methods in which facial recognition systems work, but in general, they work by comparing selected facial features from the given image with faces within a database.
The systems currently working on Facial recognition use Digital Image Processing as a basic algorithm for running a recognition system. Digital image processing is the use of computer algorithms to perform image processing on digital images. It is advantageous over analogue image processing as it allows a much wider range of algorithms to be applied to the input data and can avoid problems such as the build-up of noise and signal distortion during processing.
The reference design is released by NXP semiconductors on their product IMXRT smart recognition systems.
The main features which the Designed system Provides are –
- It consists of a 32-bit high-end Arm-based processor able to do multiprocessing and multithreading tasks at the same time. As the images are converted into matrices, it requires a fast execution of processes and algorithms and a good amount of size.
- The system mode of communication is an essential part of the design as it increased the scalability of the product. The design supports JTAG, PLL OSC, eDMA, 4x Watch Dog, 6x GP Timer, 4x Quadrature ENC, 4x QuadTimer, 4x FlexPWM and IOMUX.
- The operating system plays an important role in digital processing. The design supports Free Rtos as a primary firmware which integrates RGB and IR sensors for colour detection.
- The design comes with pre-configured software and development tools which are interactive and can be configured according to the need of the user.
- The design supports different applications such as Face detection, Face tracking, Face alignment and Face recognition.
- The design works on 5 Volts and can be powered through micro-USB and 5V adapters.
- Memory plays an important role in the digital processing system as the system follows the ‘ test and train ‘ method which means all the images are stored and are processed to identify a particular pattern to distinguish every gesture different from other gesture. The internal storage in the processor is 1 MB and the external capacity for the system is 32 MB.
These are some of the features which are essential for the design and development of a feasible image recognition system. The design contains implementation and full design files. All the documents can be downloaded here.