Abstract
In this paper, we present the architecture of a smart imaging sensor (SIS) for face recognition, based on a custom-design smart pixel capable of computing local spatial gradients in the analog domain, and a digital coprocessor that performs image classification. The SIS uses spatial gradients to compute a lightweight version of local binary patterns (LBP), which we term ringed LBP (RLBP). Our face recognition method, which is based on Ahonen’s algorithm, operates in three stages: (1) it extracts local image features using RLBP, (2) it computes a feature vector using RLBP histograms, (3) it projects the vector onto a subspace that maximizes class separation and classifies the image using a nearest neighbor criterion. We designed the smart pixel using the TSMC 0.35 μm mixed-signal CMOS process, and evaluated its performance using postlayout parasitic extraction. We also designed and implemented the digital coprocessor on a Xilinx XC7Z020 field-programmable gate array. The smart pixel achieves a fill factor of 34% on the 0.35 μm process and 76% on a 0.18 μm process with 32 μm × 32 μm pixels. The pixel array operates at up to 556 frames per second. The digital coprocessor achieves 96.5% classification accuracy on a database of infrared face images, can classify a -pixel image in 94 μs, and consumes 71 mW of power.
Highlights
The attention of the scientific and industrial community in image-based biometric methods has fostered a growing interest in smart imaging systems (SIS) that can handle the computational requirements of real-time video analysis
One of the most popular biometric techniques is face recognition [2], which has abundant applications [3,4,5] in various areas, such as: (1) security, including identity verification [6,7], computer or mobile device unlock [7,8], criminal records search, and voter registration; (2) surveillance, such as cameras used on closed circuit television (CCTV) [9]; and (3) access control that could grant access to a specific place or an electronic account to a group of people [10] using their faces as a credential
The pixel-level circuit that we present in this paper is based on a capacitive transimpedance amplifier (CTIA) pixel architecture, which is suitable for IR and low-light applications; our SIS architecture is an attractive solution for IR face recognition in embedded and mobile systems
Summary
The attention of the scientific and industrial community in image-based biometric methods has fostered a growing interest in smart imaging systems (SIS) that can handle the computational requirements of real-time video analysis. Biometrics is described as a pattern-recognition technique for individual identification, based on their physical, chemical, or behavioral characteristics [1,2]. One of the most popular biometric techniques is face recognition [2], which has abundant applications [3,4,5] in various areas, such as:. As described by Das et al [11], there is a growing attention from the scientific community on mobile devices with biometric recognition. This attention is mainly fueled by the commercial interest in robust authentication methods for smartphones, laptops, tablets, and other mobile devices [7,8].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
