Thermal Imaging Face Recognition

The thermal imaging screener combines face recognition with advance AI features to detect if the employee is wearing mask before allowing entry into the premise, and also identify visitor. The thermal scanner face recognition terminal comes with an audio voice alert to remind the user to wear a protection before entering the workplace. It is capable to recognize the employee even with the protection and can screen the temperature accurately up to 0.3 degree. 8inches thermal imaging face recognition screener is suitable for employees, visitor, passengers, students temperature thermal scanner in mall, hotel, office, government, hall, library, community and schools

Thermal imaging camera
thermal imaging camera with face recognition

Main Features

  • High performance thermal imaging face recognition system
  • Anti-Spoofing for alive human detection
  • 2.0MP binocular camera with WDR and IR lamps
  • Max 30,000 faces , max 30faces in one frame
  • Recogntion: <0.5s, Accuracy:99%
  • 120*90 HD Termal Sensor
  • Fever Detection: 30-130cm, Range: 16 ℃ – 40 ℃
  • Europ temperature sensor
  • Thermal Imaging Accuracy: ±0.2℃, Response:200ms
  • 8inche IPS screen (non-touch)
  • People with mask face recognition
  • Linux OS with stable performance
  • WG26/WG34 Wiegand protocol for door control


Model IDG-1290 Thermal Imaging Face Recognition
Thermal Imaging Module
Image Sensor Vanadium Oxide Uncooled Focal Plane Arrays
Max. Resolution 120*90
Temp Distance 0.3-1.3m
Temp Accuracy ±0.2℃
Processor 4*1.5GHZ CUP+4*1GHZ VPU+800HZ MCU
OS Linux
Storage 8GB EMMC+1G DDR4
LCD 7 inches, 1024 * 600 resolution
Image Sensor 2 million effective pixels, 1920 * 1080 SONY IMX307
SNR ≥50db(AGC OFF)
WDR ≥120db
Camera Dual cameras, 650nm and 850nm NIR
Face recognition performance
Face Spoofing Support Face Spoofing Detection Using Active Near-Infrared Videos
Placed Height 1.2 ~ 2.2 meters, adjustable angle
Faces Capacity 30000
Verification Distance 0.3 ~ 2 meters, variable depending on the lens
Face angle 30 degrees left and right, 30 degrees up and down
Alarm input 2 alarm inputs
Alarm Output 1 alarm output
power supply DV12V
Network Interface 1 RJ45 10M / 100M Ethernet port
1 *2.4G wifi module (optional)
1 *4G module (optional)
usb interface 1 USB 2.0 interface
Wiegand interface 1 pair Wiegand interface
Machine parameters
Operating temperature Operating temperature: -40 ° c ~ + 60 ° c
Power Maximum power <24w, 12v power supply
Dimensions 120mm*226.5mm*33.5mm

Face Recognition Algorithm

Scenes Algorithms Description
Main Algorithm accuracy Face recognition (1: 1):

99%@0.01% (accuracy rate is 99% under 0.01% falserate)

95%@0.0001% (95% accuracy under 0.0001% false positive rate)

Angle Yaw ± 30 degrees, roll ± 30 degrees, pitch ± 15 degrees
Valid Face Face size is more than 80 * 80 pixels in images


Face live detection

Angle Yaw ± 30 degrees, roll ± 30 degrees, pitch ± 15 degrees
Face Image Face size is more than 80 * 80 pixels in images
Accuracy 98%@0.01% (real person pass rate @false person passrate)
Anti-spoofing Non-living detection for pictures, videos, coated paper, face fake models, etc.
Face detection & tracking Snapshots More than 30 people / frame
Caputre Speed 25fps
Smallest face 30*30
Adaptation angle Yaw ± 45 degrees, roll ± 45 degrees, pitch ± 30 degrees


Face attribute

Emotion Gender, age, glasses, expression (angry, calm, happy, sad, surprised), mask, race, beard, race, hat detection, hard hat detection
Algorithm Age accuracy (± 5 years): more than 85%;
General accuracy Gender accuracy: 96% or more; Skin tone accuracy: above 97%; Beard accuracy: above 97%; Glasses accuracy: more than 98%; Mask accuracy: more than 98%; Hat accuracy: above 97%;

Expression accuracy: 88% or more


Thermal Imaging camera