An Ultra-Low-Power Analog-Digital Hybrid CNN Face Recognition Processor Integrated with a CIS for Always-on Mobile Devices

An ultra-low-power analog-digital hybrid always-on face recognition (FR) processor integrated with a CMOS image sensor (CIS) is proposed for the wearable mobile devices applications such as user authentication. The proposed processor is the first IC with full process of FR in a single chip. The proc...

Full description

Saved in:
Bibliographic Details
Main Authors: Ji-Hoon Kim, Changhyeon Kim, Kwantae Kim, Hoi-Jun Yoo
Format: Conference Proceeding
Language:English
Subjects:
always-on
Analog memory
Analog-digital conversion
analog-digital hybrid
CMOS image sensor
CNN
Computer architecture
Convolution
Face
face detection
Face recognition
mixed-mode
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:An ultra-low-power analog-digital hybrid always-on face recognition (FR) processor integrated with a CMOS image sensor (CIS) is proposed for the wearable mobile devices applications such as user authentication. The proposed processor is the first IC with full process of FR in a single chip. The processor adopts analog-digital hybrid convolution operation for efficient integration of CNN processor with CIS. The analog convolution processor is proposed for the computation of the 1 st layer of CNN and the quantization operation without an ADC that can achieve 15.7% power reduction with 1.3% minimal accuracy loss. In addition, the analog weighted-sum unit with low power ( 5.18TOPS/W) is proposed with switched-drain regulation (SDR) current mirror which can achieve less than 6% mirroring error. The processor is simulated in 65-nm CMOS technology, 15.84mm 2 area with 2.5V and 1.2V for analog domain and 0.77-1.1V for digital domain. It consumes 0.6198mW to evaluate one face at 1 fps and achieves 96.18% FR accuracy in LFW dataset.
ISSN:2158-1525
DOI:10.1109/ISCAS.2019.8702698