Luxand FaceSDK – Technical Specifications

The FaceSDK library has the following technical specifications:

Face Detection

  • Robust frontal face detection
  • Detection of multiple faces in a photo
  • Head rotation support:  –30..30 degrees of in-plane rotation and –30..30 degrees out-of-plane rotation
  • Determines in-plane face rotation angle
  • Detection speed:
    • Realtime detection (webcam resolution, –15..15 degrees of in-plane head rotation): 0.003456 sec (289 FPS) (Intel*), 0.006420 sec (156 FPS) (iOS*), 0.020 sec (50 FPS) (Android*)
    • Reliable detection (digital camera resolution, –30..30 degrees of in-plane head rotation): 0.075710 sec (Intel), 0.22235 sec (iOS), 0.642 sec (Android)
  • Returned information for each detected face: (x,y) coordinates of face center, face width and rotation angle
  • Easy configuration of face detection parameters

Face Matching

  • Matching of two faces at given FAR (False Acceptance Rate) and FRR (False Rejection Rate)
  • Enrollment time:
    • Webcam resolution, using FSDK_DetectEyes/FSDK_GetFaceTemplateUsingEyes: 0.01455 seconds (69 FPS) (Intel), 0.01311 seconds (76 FPS) (Intel Xeon*), 0.03398 seconds (29 FPS) (iOS), 0.091 seconds (11 FPS) (Android)
    • Webcam resolution, using FSDK_GetFaceTemplateInRegion (higher accuracy): 0.014603 seconds (68 FPS) (Intel), 0.013035 seconds (76 FPS) (Intel Xeon), 0.033867 seconds (29 FPS) (iOS), 0.097 seconds (10 FPS) (Android)
  • Template Size: 13 kb
  • Matching speed:
    • Single thread, templates per second: 77073 (Intel), 96899 (Intel Xeon), 80671 (iOS), 12080 (Android)
    • Multiple parallel threads, templates per second: 311526 (Intel), 442635 (Intel Xeon), 154440 (iOS), 45353 (Android)
  • Returned information: facial similarity level
  • ROC Diagram

Live Video Recognition with Tracker API

  • Assigns a unique ID to each subject detected in video
  • Allows tagging any subject in video with a name, and recognizing it further
  • No requirement for a subject to pose to be enrolled
  • Constant learning of subjects’ appearance
  • Provides with estimates of false acceptance rate and recognition rate
  • Tracks multiple faces and their facial features
  • Recognizes male and female genders
  • Recognizes facial expressions

Facial Feature Detection

  • Detection of 70 facial feature points (eyes, eyebrows, mouth, nose, face contour)
  • Detection time (using FSDK_DetectFacialFeaturesInRegion, not including face detection stage): 0.00244 seconds (408 FPS) (Intel), 0.0043 seconds (233 FPS) (iOS), 0.0115 seconds (86 FPS) (Android)
  • Allowed head rotation: –30..30 degrees of in-plane rotation, –20..20 degrees out-of-plane rotation
  • Returned information: array of 66 (x,y) coordinates of each facial feature point

Eye Centers Detection

  • Detection of eye centers only, detection time (not including face detection stage): 0.002434 seconds (410 FPS) (Intel), 0.00442 seconds (226 FPS) (iOS), 0.0112 (89 FPS) seconds (Android)
  • Returned information: two (x,y) coordinates of left eye center and right eye center

Gender Recognition

  • Recognition of different genders
  • Gender recognition time (not including face and facial feature detection stages): 0.00629 seconds (Intel), 0.0087 seconds (iOS), 0.028 seconds (Android)
  • Returned information: confidence level in each gender

Expression Recognition

  • Recognizes if the subject smiles and if the eyes are open or closed
  • Expression recognition time (not including face and facial feature detection stages): 0.00629 seconds (Intel), 0.0087 seconds (iOS), 0.028 seconds (Android)
  • Returned information: confidence level in each expression

Multi-Core Support

  • The library uses all available processor cores when executing face detection or recognition functions, to maximize the performance.

Library Size

  • The size of the redistributables does not exceed 40MB for each platform.

* Measured on Intel Core i7 4850HQ processor with 8 threads, Intel Xeon E3-1270 V2 processor with 8 threads, iPad Pro with 2 threads, Asus - MeMO Pad 7 K013 Tablet with 4 threads.


Next chapterInstallation