Panasonic’s deep learning facial recognition technology features a ‘deep learning’ core engine that has ranked as the industry’s most accurate in independent testing by NIST. The Face Server can identify faces that are difficult to recognise using conventional facial recognition technologies, including faces at an angle of up to 45 degrees to the left or right or 30 degrees up or down, and those partially hidden by sunglasses and face masks.
When combined with Panasonic’s i-PRO Extreme camera range, the Face Server technology makes use of the ‘iA (intelligent Auto) mode’ and ‘best shot feature’. This means the camera automatically adjusts its settings to shoot optimal images. The iA function enables image analysis to be performed on the camera instead of the server. As a result, only the best images are sent, reducing server and network load and total system cost.
Jointly developed with the National University of Singapore, it provides a real-time processing capacity of up to 20 cameras per server and can execute high-speed searches of up to 30,000 registered reference faces.
FacePro changes the game in terms of detection accuracy, as it does not only maintain 90%+ accuracy for faces that are partially covered by sunglasses or face masks, it also recognises faces from photographs that are up to 10 years old. The platform is already in use at Tokyo’s Haneda airport where it has replaced finger print recognition on the passport entry gates, following three years of verification testing.*1
High performance facial recognition
- High performance Deep Learning facial recognition function distinguishes face orientation, sunglasses, facial aging change
- Up to 20 cameras can be connected to one server. Reduce the system total cost such as server cost, network cost etc
*The number of cameras that can be connected is determined by the number of people passing and the retention period of the face image.
- Up to 30,000 faces can be registered and WV-ASF950 can be used in large facilities
- Face images that camera detected are stored, and it can be searched later.
- By searching the face database, you can display the result of each cameras in chronological order and find movement locus of persons.
- Specify camera or date in detected face images and display the result in the list in similarity order.
- When it is matched with registered people, alarm of face matching is output in real-time, and display an alarm
history in the list.
- Specified screen image can be played back on control monitor with double-clicking on an alarm history.
PEOPLE COUNTING, AGE AND GENDER STATISTICS
- Count people of detected face and evaluate their age and gender.
- Display the result on the screen with statistical graph.
Basic System Connection Example
*1 For more information on the Tokyo Haneda airport installation, please see: https://news.panasonic.com/global/press/data/2017/12/en171215-2/en171215-2.html
There are currently no key services available.
There are currently no other services available.
|Face Matching Speed||At 1 second in 30,000 registered faces*2|
|Max. Number of Face in Matching list||Up to 30,000 face*3|
|Max. Number of Face history||Up to 10 million items|
|Angle of View Range||Horizontal range : -45° to +45°, Vertical range : -30° to +30°|
|Max. number of client PC that can be linked with the alarm||16|
|CPU||Intel® Xeon® or CoreTM i7 series 3.40 GHz or faster (4-core 8-thread or better)|
|Memory||32 GB or more|
|HDD||1 TB or more|
|Graphics||NVIDIA® QUADRO® P5000, NVIDIA® QUADRO® RTX5000|
|Power Supply||600 W or more|
|OS||Microsoft® Windows® 10 Pro RS5 (64 bit), Microsoft® Windows Server® 2016 Standard Edition, Microsoft® Windows Server® 2019 Standard Edition|
|Supported Network Camera||WV-S1132 / WV-S1131 / WV-S1112 / WV-S1111 / WV-S2531LTN *7 / WV-S6130 / WV-SPN631*6 / WV-SPN611*6 / WV-SPN531A / WV-SPN311A / WV-SPN310A / WV-SP305 / WV-SFV631LT *7 / WV-SC385 *8|