Convolutional neural network on-a-chip promises always-on face recognition
Using such embedded artificial intelligence, the researchers claim their solution consumed only 1/5000 the power that would be required by a GPU performing the same tasks.
This unique processor owes its incredibly low power consumption thanks to its CNN whose circuitry, architecture, and algorithms have all gone through optimization steps. On-chip memory has been integrated in the CNNP so it could be read in a vertical direction as well as in a horizontal direction, reports KAIST. In the CNNP, 1024 multipliers and accumulators operate in parallel and the chip is capable of directly transferring the temporal results to any of those without access to external memory or to an on-chip communication network. The chip which was presented at the International Solid-State Circuit Conference (ISSCC) held in San Francisco last February performs convolution calculations with a two-dimensional filter in the CNN algorithm, approximated into two sequential calculations of one-dimensional filters to achieve higher speeds and lower power consumption.
On the basis of this chip developed by Kyeongryeol Bong, a Ph. D. student under Professor Hoi-Jun Yoo of the Department of Electrical Engineering, and in collaboration with Korean start-up UX Factory Co., the researchers developed a wearable face recognition system they hope to bring to market by the end of the year.
Dubbed K-Eye series, the face detection and recognition device can be used with a smartphone via Bluetooth, and can operate for more than 24 hours on one battery charge. The device which could be manufactured as a dongle combines an analogue processor with a CMOS image sensor to distinguish the background area from the area likely to include a face. Then a digital processor detects the face only in the selected area, making the system very effective in terms of frame capture, face detection processing, and memory usage.
In effect, the K-Eye series has been designed as a very low power (less than 1mW) “Always-on” image sensor that can determine if there is a face in its camera range. It only capture frames and set the device to operate when a face has been detected, then the CNNP performs its recognition task.
In a demonstration video, K-Eye is used as a smartphone add-on that allows users to authenticate themselves by looking at their camera, allowing financial transactions. In another example, a policeman wears it around his neck and by accessing a registered database, can automatically check information about the persons he comes across. KAIST also believes the K-Eye could displace other forms of authentication on smartphones, including today’s passwords, fingerprint, or iris authentication.
KAIST – www.kaist.edu
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
