FA50M

Embedded biometric module with deep learning, facial recognition;
Binocular camera;
Alive body and mask detection;
Age, gender and emotional expressions recognition.

Social Share:

FA50M: Edge Computing Facial Recognition

FA50M is a binocular camera module designed based on high-performance heterogeneous processors. The binocular camera module has built-in facial recognition algorithms. Facial recognition algorithm helps in face detection, alive body detection, mask detection, and can recognize the age, gender, emotional expressions, and identity of a user with his/her face.

The FA50M performs algorithm calculations at the device and can use JPG images to register directly. Combines with a rich software development interface, the integrated face recognition function can be realized in a low-configuration application platform, which is widely used in attendance, access control, passages and other fields.

2MP Starlight HDR Dual-Sensor with WDR up to 105dB
Detection distance: Facial Recognition - 50 cm to 200 cm
Provides a combination recognition method of facial and palm identification
Illuminance of 0.01 lux to 50,000 lux for facial recognition
Age, gender and emotional expressions recognition algorithm
Built-in near-infrared fill light and intelligent switch control based on an image detection algorithm.
A thorough SDK available, supporting 3 primary OS (Windows, Android & Linux)
Image transmission carried out by the UVC protocol
Comparison and results are delivered through HID protocol


General	Processor	Quad-core Cortex-47 up to .5G, 1.2 TOPs for INT8
	Image Sensor	Dual 1/2.8” HDR CMOS, 2MP resolution, supports RGB+IR
	Communication Interface	USB 2.0
	Communication Protocol	UVC & HID protocol
	Power Supply	DC5V 1A (min.)
	Operating Temperature	-10°C to 50°C
	Operating Humidity	0 to 90% RH
	Dimensions (LWH)	62 * 38 * 25.3 (mm)
Optical & Image Parameters	Camera Type	Visible light	Near-infrared
	Field of View	D=73°; H=65°; V=40°	D=73°; H=65°; V=40°
	Image Resolution & Frame Rate	720*1280@25fps	720*1280@25fps
		480*640@25fps	480*640@25fps
	Wide Dynamic Range	105dB	105dB
	Distortion	≤0.5%	≤0.5%
	Default Output Format	MJPEG	NV12
	Luminance	0.01 lux to 50,000 lux	0.01 lux to 20,000 lux
	Windows	Windows XP/ Windows 7/ Windows10 (32-bit or 64-bit)
	Android	Android 4.1 or above
ZKLiveFace Algorithm	Angle Tolerance	Yaw ≤±30°, Pitch ≤±30°, Roll ≤±30°
	Face Capacity	50,000 for 1:1 and 1:N comparison
	Face Features Recognition Accuracy	Age (±5 y/o) > 85%
		Gender > 96%
		Emotional expression > 88%
	Facial Recognition Accuracy	FAR = 0.01% when FRR = 1%, FAR = 0.0001% when FRR = 5%
ZKPalm Algorithm	Angle Tolerance	Yaw ≤±30°, Pitch ≤±30°, Roll ≤30°, Bend ≤20%
	Palm Capacity	6,000 for 1:1 and 1:N comparison
	Palm Recognition Accuracy	FAR=0.001% when FRR=0.68%
	Certifications	CE, FCC, RoHS
Recognition Module	Facial Recognition Module