|
FACE ALGORITHM A biometric recognition technology based on human facial feature information. Use the camera to collect the image or video stream containing the face, and automatically detect and track the face in the image, and then carry out a series of related technical analysis of the detected face, which is usually called portrait recognition and face recognition. |
 |
| TECHNICAL STRENGTH |
 |
 |
 |
| 90 Million+ Data | Large Scale Application | Second Level Response |
| More than 90 million data stored in database of real implementation. |
It has been applied on a large scale in |
Second level response to hundred |
| Face Liveness Detection Algorithm | |
 |
|
| The liveness detection algorithm covers motion, monocular RGB, binocular rgb-ir liveness detection algorithms, which can detect prosthesis attacks such as printed photos, mobile phones, high-definition screens, masks, head models, etc. The liveness pass rate is larger than 99%, and the prosthesis detection rate is above 98%. It is suitable for self-service machines, remote tellers, online banking, mobile banking (light liveness detection, face verification) and other application scenarios |
|
| Face Attribute Analysis Algorithm | |
|
|
| Quickly detect the face in the picture, return the coordinates of face key points, and automatically recognize gender, age, sentiment and other face attribute information. |
| Face Attribute Analysis | Sentiment Analysis | Facial Features Positioning | Multi Face Detection | |||||
| Accurately analyze a series of attributes such as age, gender, sentiment, hair style, binocular distance, three-dimensional rotation angle of the face, whetherthe face is covered, whether the person is making a phone call,etc. | Automatically recognize the emotional state of the face in the picture, such as joy, sadness, surprise, fear, disgust, anger, neutrality, etc. | Accurately locate the key points of the face in the picture, such as eyes, eyebrows, nose, mouth, facial contour, etc. | Automatically detect faces in pictures, record the coordinates of face key points and recognize attributes, and support the simul-taneous detection of multiple faces. |
| Face Comparison Algorithm |
|
| Compare the two face images, calculate the face similarity, analyze and judge whether it is the same person. |
|
 |
|||
| Fast Comparison Speed | LFW World No.2 | |||
| Single core comparison speed can reach 1million times per second. | Won the second place in the world in LFW competition. |
|
 |
 |
|||
| High Accuracy | Reliable | |||
| The accuracy rate is as high as 99.71%, on the field leading position of the world. | Supports the comparison of various types of face images such as certificate photos and life photos, which is accurate and reliable. |
