Enable Face and Face Attribute Recognition

FindFace Multi allows you to recognize human faces and face attributes. Subject to your needs, you can enable recognition of such face attributes as age, gender, emotions, beard, glasses, medical masks, head position, or liveness.

Face and face attribute recognition can be automatically enabled and configured during the FindFace Multi installation. If you skipped this step, you can manually do it later. Face and face attribute recognition works on both GPU- and CPU-acceleration.

Face object recognition is enabled by default. In case you removed face as a recognition object during the installation, you can add it later by following the below steps. If face object recognition is already installed, and you only need to enable face attribute recognition, jump to the steps 1.5, 1.6 and 4.1, 4.2. Other steps should be skipped.

  1. To enable face recognition, do the following:

    Specify neural network models for face object detection in the /opt/findface-multi/configs/findface-extraction-api/findface-extraction-api.yaml configuration file.

    Important

    Be sure to choose the right acceleration type for each model, matching the acceleration type of findface-extraction-api: CPU or GPU. Be aware that findface-extraction-api on CPU can work only with CPU-models, while findface-extraction-api on GPU supports both CPU- and GPU-models.

    1. Open the findface-extraction-api.yaml configuration file.

      sudo vi /opt/findface-multi/configs/findface-extraction-api/findface-extraction-api.yaml
      
    2. Specify the face detector model in the detectors -> models section by pasting the following code:

      GPU

      detectors:
      
        ...
        models:
          ...
          face_jasmine:
            aliases:
            - face
            - nnd
            - cheetah
            model: detector/face.jasmine_fast.003.gpu.fnk
            options:
              min_object_size: 32
              resolutions:
              - 256x256
              - 384x384
              - 512x512
              - 768x768
              - 1024x1024
              - 1536x1536
              - 2048x2048
      
        ...
      

      CPU

      detectors:
      
        ...
        models:
          ...
          face_jasmine:
            aliases:
            - face
            - nnd
            - cheetah
            model: detector/face.jasmine_fast.003.cpu.fnk
            options:
              min_object_size: 32
              resolutions:
              - 256x256
              - 384x384
              - 512x512
              - 768x768
              - 1024x1024
              - 1536x1536
              - 2048x2048
      
        ...
      
    3. Make sure that the objects -> face section contains the quality_attribute: face_quality and the base_normalizer: facenorm/crop2x.v2_maxsize400.gpu.fnk or the base_normalizer: facenorm/crop2x.v2_maxsize400.cpu.fnk, depending on your acceleration type:

      GPU

      objects:
        ...
        face:
          base_normalizer: facenorm/crop2x.v2_maxsize400.gpu.fnk
          quality_attribute: face_quality
        ...
      

      CPU

      objects:
        ...
        face:
          base_normalizer: facenorm/crop2x.v2_maxsize400.cpu.fnk
          quality_attribute: face_quality
        ...
      
    4. Specify the face normalizer models in the normalizers section by pasting the following code:

      GPU

      normalizers:
        ...
        models:
          crop1x:
            model: facenorm/crop1x.v2_maxsize400.gpu.fnk
          crop2x:
            model: facenorm/crop2x.v2_maxsize400.gpu.fnk
          cropbbox:
            model: facenorm/cropbbox.v2.gpu.fnk
          multicrop_full_center:
            model: ''
          multicrop_full_crop2x:
            model: facenorm/facenorm.multicrop_full_crop2x_size400.gpu.fnk
          norm200:
            model: facenorm/bee.v3.gpu.fnk
        ...
      

      CPU

      normalizers:
        ...
        models:
          crop1x:
            model: facenorm/crop1x.v2_maxsize400.cpu.fnk
          crop2x:
            model: facenorm/crop2x.v2_maxsize400.cpu.fnk
          cropbbox:
            model: facenorm/cropbbox.v2.cpu.fnk
          multicrop_full_center:
            model: ''
          multicrop_full_crop2x:
            model: facenorm/facenorm.multicrop_full_crop2x_size400.cpu.fnk
          norm200:
            model: facenorm/bee.v3.cpu.fnk
        ...
      
    5. Note

      This step is required to enable face attribute recognition.

      To enable face attribute recognition, do the following:

      In the /opt/findface-multi/configs/findface-extraction-api/findface-extraction-api.yaml configuration file, specify the extraction models in the extractors section, as shown in the example below. Be sure to indicate the right acceleration type for each model, matching the acceleration type of findface-extraction-api: CPU or GPU.

      GPU

      extractors:
        ...
        models:
          face_age: faceattr/age.v2.gpu.fnk
          face_beard: faceattr/beard.v0.gpu.fnk
          face_beard4: ''
          face_countries47: ''
          face_emben: face/mango_320.gpu.fnk
          face_emotions: faceattr/emotions.v1.gpu.fnk
          face_eyes_attrs: ''
          face_eyes_openness: ''
          face_gender: faceattr/gender.v2.gpu.fnk
          face_glasses3: faceattr/glasses3.v0.gpu.fnk
          face_glasses4: ''
          face_hair: ''
          face_headpose: faceattr/headpose.v3.gpu.fnk
          face_headwear: ''
          face_highlight: ''
          face_liveness: faceattr/liveness.web.v0.gpu.fnk
          face_luminance_overexposure: ''
          face_luminance_underexposure: ''
          face_luminance_uniformity: ''
          face_medmask3: faceattr/medmask3.v2.gpu.fnk
          face_medmask4: ''
          face_mouth_attrs: ''
          face_quality: faceattr/quality_fast.v1.gpu.fnk
          face_scar: ''
          face_sharpness: ''
          face_tattoo: ''
          face_validity: ''
      

      CPU

      extractors:
        ...
        models:
          face_age: faceattr/age.v2.cpu.fnk
          face_beard: faceattr/beard.v0.cpu.fnk
          face_beard4: ''
          face_countries47: ''
          face_emben: face/mango_320.cpu.fnk
          face_emotions: faceattr/emotions.v1.cpu.fnk
          face_eyes_attrs: ''
          face_eyes_openness: ''
          face_gender: faceattr/gender.v2.cpu.fnk
          face_glasses3: faceattr/glasses3.v0.cpu.fnk
          face_glasses4: ''
          face_hair: ''
          face_headpose: faceattr/headpose.v3.cpu.fnk
          face_headwear: ''
          face_highlight: ''
          face_liveness: faceattr/liveness.web.v0.cpu.fnk
          face_luminance_overexposure: ''
          face_luminance_underexposure: ''
          face_luminance_uniformity: ''
          face_medmask3: faceattr/medmask3.v2.cpu.fnk
          face_medmask4: ''
          face_mouth_attrs: ''
          face_quality: faceattr/quality_fast.v1.cpu.fnk
          face_scar: ''
          face_sharpness: ''
          face_tattoo: ''
          face_validity: ''
      

      The following extraction models are available:

      Extractor

      Acceleration

      Configure as follows

      age

      CPU

      face_age: faceattr/age.v2.cpu.fnk

      GPU

      face_age: faceattr/age.v2.gpu.fnk

      beard

      CPU

      face_beard: faceattr/beard.v0.cpu.fnk

      GPU

      face_beard: faceattr/beard.v0.gpu.fnk

      individual face feature vector

      CPU

      face_emben: face/mango_320.cpu.fnk

      GPU

      face_emben: face/mango_320.gpu.fnk

      gender

      CPU

      face_gender: faceattr/gender.v2.cpu.fnk

      GPU

      face_gender: faceattr/gender.v2.gpu.fnk

      emotions

      CPU

      face_emotions: faceattr/emotions.v1.cpu.fnk

      GPU

      face_emotions: faceattr/emotions.v1.gpu.fnk

      glasses

      CPU

      face_glasses3: faceattr/glasses3.v0.cpu.fnk

      GPU

      face_glasses3: faceattr/glasses3.v0.gpu.fnk

      head position

      CPU

      face_headpose: faceattr/headpose.v3.cpu.fnk

      GPU

      face_headpose: faceattr/headpose.v3.gpu.fnk

      face liveness

      CPU

      face_liveness: faceattr/liveness.web.v0.cpu.fnk

      GPU

      face_liveness: faceattr/liveness.web.v0.gpu.fnk

      face mask

      CPU

      face_medmask3: faceattr/medmask3.v2.cpu.fnk

      GPU

      face_medmask3: faceattr/medmask3.v2.gpu.fnk

      face quality

      CPU

      face_quality: faceattr/quality_fast.v1.cpu.fnk

      GPU

      face_quality: faceattr/quality_fast.v1.gpu.fnk

      Tip

      To leave a model disabled, pass the empty value '' to the relevant parameter. Do not remove the parameter itself. Otherwise, the system will be searching for the default model.

      extractors:
        face_age: ''
        face_beard: ''
        face_beard4: ''
        face_countries47: ''
        face_emben: ''
        face_emotions: ''
        face_eyes_attrs: ''
        face_eyes_openness: ''
        face_gender: ''
        face_glasses3: ''
        face_glasses4: ''
        face_hair: ''
        face_headpose: ''
        face_headwear: ''
        face_highlight: ''
        face_liveness: ''
        face_luminance_overexposure: ''
        face_luminance_underexposure: ''
        face_luminance_uniformity: ''
        face_medmask3: ''
        face_medmask4: ''
        face_mouth_attrs: ''
        face_quality: ''
        face_scar: ''
        face_sharpness: ''
        face_tattoo: ''
        face_validity: ''
      

      Important

      The face_liveness extraction model liveness.web.v0 is enabled by default. Do not disable it if you use authentication by face.

    6. Restart the findface-multi-findface-extraction-api-1 container.

      sudo docker container restart findface-multi-findface-extraction-api-1
      
  2. To enable face recognition, modify the /opt/findface-multi/configs/findface-video-worker/findface-video-worker.yaml configuration file.

    1. In the models section, specify the face neural network models by analogy with the example below:

      GPU

      sudo vi /opt/findface-multi/configs/findface-video-worker/findface-video-worker.yaml
      
      models:
        ...
        detectors:
          ...
          face:
            fnk_path: /usr/share/findface-data/models/detector/face.jasmine_fast.003.gpu.fnk
            min_size: 60
          ...
        normalizers:
          ...
          face_norm:
            fnk_path: /usr/share/findface-data/models/facenorm/crop2x.v2_maxsize400.gpu.fnk
          face_norm_quality:
            fnk_path: /usr/share/findface-data/models/facenorm/crop1x.v2_maxsize400.gpu.fnk
          ...
        extractors:
          ...
          face_quality:
            fnk_path: /usr/share/findface-data/models/faceattr/quality_fast.v1.gpu.fnk
            normalizer: face_norm_quality
      

      CPU

      sudo vi /opt/findface-multi/configs/findface-video-worker/findface-video-worker.yaml
      
      models:
        ...
        detectors:
          ...
          face:
            fnk_path: /usr/share/findface-data/models/detector/face.jasmine_fast.003.cpu.fnk
            min_size: 60
          ...
        normalizers:
          ...
          face_norm:
            fnk_path: /usr/share/findface-data/models/facenorm/crop2x.v2_maxsize400.cpu.fnk
          face_norm_quality:
            fnk_path: /usr/share/findface-data/models/facenorm/crop1x.v2_maxsize400.cpu.fnk
          ...
        extractors:
          ...
          face_quality:
            fnk_path: /usr/share/findface-data/models/faceattr/quality_fast.v1.cpu.fnk
            normalizer: face_norm_quality
      
    2. Make sure that the objects -> face section is included:

      objects:
        ...
        face:
          normalizer: face_norm
          quality: face_quality
          track_features: ''
      
    3. Restart the findface-multi-findface-video-worker-1 container.

      sudo docker container restart findface-multi-findface-video-worker-1
      
  3. To enable face recognition, open the /opt/findface-multi/configs/findface-video-manager/findface-video-manager.yaml configuration file and make sure it contains the face section in detectors that looks similar to the example below.

    sudo vi /opt/findface-multi/configs/findface-video-manager/findface-video-manager.yaml
    
    detectors:
      ...
      face:
        filter_min_quality: 0.5
        filter_min_size: 60
        filter_max_size: 8192
        roi: ''
        fullframe_crop_rot: false
        fullframe_use_png: false
        jpeg_quality: 95
        overall_only: true
        realtime_post_first_immediately: false
        realtime_post_interval: 1
        realtime_post_every_interval: false
        track_interpolate_bboxes: true
        track_miss_interval: 1
        track_overlap_threshold: 0.25
        track_max_duration_frames: 0
        track_send_history: false
        post_best_track_frame: true
        post_best_track_normalize: true
        post_first_track_frame: false
        post_last_track_frame: false
        tracker_type: simple_iou
        track_deep_sort_matching_threshold: 0.65
        track_deep_sort_filter_unconfirmed_tracks: true
        track_object_is_principal: false
        track_history_active_track_miss_interval: 0
    
  4. Note

    This step is required to enable face attribute recognition.

    Enable recognition of face attributes in the /opt/findface-multi/configs/findface-multi-legacy/findface-multi-legacy.py configuration file.

    1. In the FFSECURITY section, specify the face attributes that you want to display for the face recognition events.

      # available features: age, beard, emotions, gender, glasses, headpose, medmask
      'FACE_EVENTS_FEATURES': ['glasses', 'beard', 'age', 'gender', 'headpose', 'medmask', 'emotions'],
      
    2. Restart all FindFace Multi containers.

      cd /opt/findface-multi/
      
      sudo docker-compose restart