ZTE, manufacturer of Axon smartphone series, and Intel had a breakthrough in facial recognition by processing more than 1000 photos per second thanks to deep learning systems #fotomagic
The Chinese company’s engineers ran the test in Nanjing, using Intel’s Arria 10 FPGA (field-programmable gate array) for a cloud inferencing application using deep learning ( as in CNN – convolutional neural networks ) algorithm.
They managed to process more than one thousand images per second with “theoretical high accuracy” for its custom topology. In the same time, Intel’s integrated circuit accelerated the raw design performance more than 10 times while maintaining the accuracy.
“Perception, such as recognizing a face in an image, is one of the essential goals of the ZTE 5G System,” said Duan Xiangyang, vice president of ZTE Wireless Institute. “Deep learning technology is very important as it can enable such perception in mobile edge computing systems, thus making ZTE’s 5G System smarter.”
Also, Intel believes that the performance of deep learning designs such as this one can be further improved by integrating them to its Stratix 10 FPGA family.
It’s refreshing to see big companies collaborating for the progress of technologies that can make devices faster and smarter.