G06V 40/16

Definition

Diese Klassifikationsstelle umfasst:

(Für diese Definition ist die deutsche Übersetzung noch nicht abgeschlossen)

Detection, localisation, representation and recognition of the face or of facial parts.

Detection of multiple faces in an image or video, e.g. for video-conferencing.

Feature extraction based on the facial image taken as a whole, e.g. holistic features such as colour of the face region, eigenfaces, Fisherfaces, etc., or based on facial parts, e.g. local features such facial components (eyes, nose, etc.), their geometric configuration.

Face occlusion detection.

Race, gender and age detection based on facial features (e.g. skin wrinkles).

Recognition of facial expressions, e.g. static or dynamic expressions.

Spoof-by-picture using an image of the face.

Detection of faces using different types of acquisition modalities, e.g. infrared (thermal) images, or their combination.

Facial skin detection based on skin properties, e.g. skin colour.

Bildreferenz:G06V0040160000_0

Faces detected in an image

Bildreferenz:G06V0040160000_1

Acquisition of a face in 3D by means of a smartphone

Querverweise

Informative Querverweise

Recognising three-dimensional [3D] objects in scenes	G06V 20/64
Recognition of human or animal bodies in images or video, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands	G06V 40/10
Recognition of fingerprints or palmprints within images or video	G06V 40/12
Recognition of eye characteristics within images or video, e.g. of the iris	G06V 40/18
Multimodal biometrics, e.g. combining information from different biometric modalities	G06V 40/70

Spezielle Klassifizierungsregeln

Recognition using iris patterns of the eye are classified in group G06V 40/18. If the technical aspects of a document cover aspects relevant both for face recognition and iris recognition, both aspects are classified in groups G06V 40/16 and G06V 40/18.

Techniques for spoof detection of faces, e.g. spoof-by-picture, are classified in groups G06V 40/16 and G06V 40/40.

Techniques for face recognition using 3D models are also classified in group G06V 20/64.

Glossar

eigenface eigenfaces	face representation using a principal component analysis in a high-dimensional space created from images of faces. The eigenvectors of the representation are derived from the covariance matrix of the probability distribution computed in this high-dimensional vector space.
fisherface fisherfaces	linear discriminant analysis (LDA) applied in a multi-dimensional representation space created from a set of face images, resulting in a set of basis vectors defining that space.
frontal face recognition	face images are generally obtained by placing a camera in front of the subject who is asked to look at the camera while the picture is taken.
illumination-invariant recognition	recognition insensitive to changes in lighting conditions.
multiview face recognition	employs a gallery of images of every face at various poses to cover multiple views for each face.
pose-invariant recognition	recognition insensitive to changes in pose.

G06V 40/16

Definition Statement

This place covers:

Detection, localisation, representation and recognition of the face or of facial parts.