Facial landmark detection technology is the foundation of emotion recognition and expression analysis. Features of the face, such as movements in the eyes, mouth, and eyebrows, can reflect human emotional states and levels of fatigue. With the latest machine learning software stack and facial landmark detection models, this technology can run on the NuMicro M55M1 microcontroller equipped with a Neural Processing Unit (NPU).

As technology continues to advance, artificial intelligence (AI) is becoming an essential part of modern life. However, for many developers, getting started with AI can still be challenging, especially when it involves writing a lot of code and requires specialized knowledge. These hurdles have discouraged many from exploring AI development. Fortunately, as tools and platforms evolve, even users without programming backgrounds can now join the AI development wave. The NuEzAI-M55M1 development board is one of the key products driving this shift.

With the rapid development of artificial intelligence technology, gesture recognition systems have become increasingly popular in fields such as smart homes, human-computer interaction, and virtual reality. These technologies not only enhance user convenience but also introduce revolutionary ways of interaction. To meet these application needs, Nuvoton Technology has introduced a reference design for a gesture recognition system, aimed at providing a low-power, high-performance solution for various real-time application scenarios.

The core hardware of this system adopts the Arm® Cortex®-M55- and Arm® Ethos™-U55- based microcontroller. This NuMicro® M55M1 microcontroller not only offers powerful computing capabilities but also features excellent low-power characteristics, making it especially suitable for resource-constrained embedded systems.

The NuMicro® M55M1 comes with 1.5 MB of built-in SRAM and supports a variety of external memory options, including QSPI, SDHC, EBI 16-bit, and HYPERRAM™. Most importantly, the system integrates a powerful Neural Processing Unit (NPU) — the Arm Ethos-U55 — specifically designed to provide robust AI processing power for embedded applications, while also maintaining exceptional energy efficiency. With this hardware architecture, we can run lightweight YOLO models in embedded environments, enabling real-time gesture recognition and providing flexible and efficient solutions for various applications.

With the rapid development of machine learning and automation technology, medicine classification and recognition systems have become important applications in the medical field. Using the NuMicro^® M55M1 series microcontroller evaluation board from Nuvoton, we can design efficient and accurate medicine classification and recognition systems. These systems assist medical professionals in quickly identifying pills, improving operational efficiency, and reducing errors. They also provide an additional safety mechanism during patient rounds and consultations, preventing accidental administration of the wrong medication. Furthermore, they enhance the safety for elderly individuals with declining vision when taking medication at home, effectively warn and remind them of any irregularities in their medication.

In this thriving era of artificial intelligence (AI), developers can easily deploy Edge AI algorithms on edge devices. Keyword Spotting technology, using machine learning methods, enables microcontrollers to recognize human voice commands. By integrating voice control, these microcontrollers can execute specific operations based on these commands, providing users with a more intuitive and convenient interaction method. The practical application of this technology is wide-ranging, from household appliances to industrial control systems, all benefiting from the enhanced convenience and efficiency of voice control, especially in hands-free operation scenarios or where operational safety is paramount. As machine learning technology advances and microcontroller performance improves, we can anticipate that more devices will be able to understand and execute human voice commands, paving the way for a more intelligent and human-friendly mode of interaction. 

Under the global trend of smart manufacturing and industrial automation, we are honored to introduce the launch of the NuMicro® MA35D1 microprocessor, a high-performance microprocessor designed for industrial Human-Machine Interface (HMI) applications. The MA35D1 microprocessor not only sets new standards for automation technology but also showcases its limitless potential for innovative applications in the smart catering service domain.

With the continuous advancement of industrial automation and intelligent technology, our company is committed to continuously innovating and optimizing product solutions under the push of cutting-edge technology. We are honored to introduce the NuMicro® MA35D1 microprocessor – an innovative microprocessor specifically designed for high-performance industrial Human-Machine Interface (HMI) applications. Through its powerful processing capability and advanced technical features, the MA35D1 microprocessor plays a key role in automated warehouse management systems, especially in the automatic classification and management of objects using machine learning technology.

In the current year of industrial automation and intelligent internet, technological innovations continue to drive breakthroughs in the Human-Machine Interaction (HMI) domain. In light of this trend, we are honored to introduce the NuMicro® MA35D1 microprocessor – a microprocessor designed specifically for high-performance industrial HMI applications. This microprocessor not only demonstrates excellent technical specifications but also proves its outstanding performance in machine learning applications for conference room people counting, providing an effective solution for spaces requiring precise control over occupancy.