ITOF Sensor Research For 3D Face Recognition Of Mobile Phone Front Camera

Since iPhone X distributed with Face ID,more and more enterprises focus on 3D face recognition.3D face recognition has the potential to achieve better accuracy than its 2D counterpart by measuring geometry of rigid features on the face.This avoids such pitfalls of 2D face recognition algorithms as change in lighting,different facial expressions,make-up and head orientation.The main technological limitation of 3D face recognition methods is the acquisition of 3D image,which usually requires a range camera.By using smart CMOS image sensors,3D range finder or image acquisition associated with distances can be realized.Several approaches suitable for 3D rang finding have been investigated.Their principles are based on Binocular,structure light and time-of-flight(TOF).Compared with other two principles,TOF has advantages in Signal-to-noise ratio,detection range and algorithm complexity,and power consumption,and is more suitable for implementing on mobile 3D face recognition front camera.The sensor suitable for implementing on mobile 3D face recognition front camera needs the following important features.The sensor can achieve a linearity error lower than 0.5% over a detection range of 25 cm to 100 cm.The sensor chip is smaller than 6mm x 4mm,includes a 320×240 pixel array with 10?m pixel pitch fabricated in SMIC 0.13 um CMOS imaging technology.Low-power mechanism and 150 klx background light suppression assembled in ITOF rang detection system setup.A dual FD 5T-APS and its correlated double sampling(CDS)readout circuit are realized.This paper presents the design of ITOF sensor pixel array,Shared CDS mechanism and low power management.SMIC 0.13 um CMOS imaging technology and optimized readout circuit significantly reduces the fixed pattern noise(FPN),readout noise,and amplifier noise,and improves the signal-to-noise ratio of 3D images and achieves lower linearity error.Experiential results show that ITOF sensor for 3D face recognition of mobile phone front camera is realized and performance best.