Using Nuvoton M487 Series to Recognize Vehicle License Plate
The global market of machine learning is flourishing recently with the advancement of technology. Machine learning refers to an accumulative and autonomous behavior enhancement from a machine through a series of learning process. The learning process is to give training data to mathematical data models, and it could be categorized into supervised, unsupervised and reinforcement learning.
The idea of machine learning can be realized in almost every field; social media features, product recommendations on the internet, image recognition, language translation are all examples of machine learning. According to Fortune Business Insights, the revenue of global machine learning market is predicted to grow dramatically to hit USD 117.19 billion by the end of 2027, with a CAGR of 39.2% comparing to the revenue of USD 8.43 billion in 2019.
With DNN (Deep Neural Networks) support and CNN (Convoltuion Neural Networks) support machine learning networks, the NuMicro® M487 Ethernet series from Nuvoton is suitable to be used in related applications. M487, with operating voltage from 1.8 to 3.6V, is powered by Arm® Cortex®-M4F core with DSP extension; and it can run up to 192 MHz with 175 µA/MHz dynamic low power consumption. M487 has up to 2.5 MB Flash memory and 160 KB embedded SRAM, which includes 32 KB cache to speed up external SPI Flash code execution. Furthermore, it is equipped with 10/100 Mbps Ethernet MAC with RMII and hardware cryptography engine.
One use case of M487 is vehicle license plate recognition. A M480 platform (with M487 on it) could recognize any vehicle license plate by using its learning neural network algorithms. A CMOS sensor is required to capture the plate image and it takes around 200 ms to identify the image. M487 supports the image resolution of QVGA 320 x 240.
M487 series is a high performance and low power microcontroller which suits to machine learning applications. Come visit TECHDesign to shop around!
