Samsung introduces new application processor with enhanced image processing and biometrics capabilities
Samsung has announced the launch of the Exynos 9 Series 9810 application processor to provide smart phones and devices with advanced capabilities, including sophisticated image processing with deep-learning based software.
The neural network-based deep learning of the Exynos 9 Series 9810 enables recognition of people or objects from photos, as well as depth sensing for 3D “hybrid” face detection, according to the company. Hybrid face detection utilizes hardware and software to enable realistic face-tracking filters and stronger security for unlocking the device. The processor also includes a dedicated security processing unit to store personal information such as facial, iris, and fingerprint biometrics.
The processor features 10nm process technology Samsung calls the industry’s most advanced, to enable seamless multi-tasking, and has a new eight-core CPU. Four of the cores are third-generation custom cores reaching 2.9 GHz, and the other four are optimized for efficiency, while its architecture improves cache memory, and single-core and multiple-core performance are enhanced by double and roughly 40 percent, respectively.
“The Exynos 9 Series 9810 is our most innovative mobile processor yet, with our third-generation custom CPU, ultra-fast gigabit LTE modem and, deep learning-enhanced image processing,” said Ben Hur, vice president of System LSI marketing at Samsung Electronics. “The Exynos 9810 will be a key catalyst for innovation in smart platforms such as smartphones, personal computing and automotive for the coming AI era.”
Other features in the Exynos 9 Series 9810 include an embedded 1.2Gbps LTE modem, a dedicated image processing and upgraded multi-format codec (MFC).
The Exynos 9 Series 9810 has been selected as a CES 2018 Innovation Awards Honoree in the Embedded Technologies product category, and is currently in mass production.
SensibleVision CEO George Brostoff wrote about the benefits of custom processors and the impending rise of neural network-enabled mobile devices in a Biometric Update guest post last month.