CPC Definition - Subclass G06V
This place covers:
Higher-level interpretation and cognition of images or videos, which includes pattern recognition, pattern learning and semantic interpretation as fundamental aspects. These aspects involve the detection, categorisation, identification, authentication of image or video patterns by acquiring, preprocessing, extracting distinctive features or matching, supervised or unsupervised clustering or classification of these features or representations derived from them leading to one or several decisions, related confidence values (e.g. probabilities) or classification/clustering labels for explanatory purposes or to derive a certain meaning.
Pattern recognition or pattern learning in a specific, image or video-related context that includes:
- scene-related patterns and scene-specific elements - G06V 20/00
- character recognition or recognising digital ink; document-oriented image-based pattern recognition – G06V 30/00
- human-related, animal-related or biometric patterns in in image or video data G06V 40/00.
Typical image or video understanding systems that include one or more of the following steps:
Figure 1. Processing steps involved in a pattern recognition system
These steps are provided as follows: image acquisition (G06V 10/10), image preprocessing (G06V 10/20), feature extraction (G06V 10/40), pattern recognition or pattern learning, e.g. matching, clustering or classifying techniques (G06V 10/70).
Image or video recognition can be carried out by using electronic means (G06V 10/70) or by using optical means (G06V 10/88).
Typically, a pattern recognition system involves one or more of the following techniques:
Individual data entity | Groups of data entities (classes) | |
One data sample | Authentication | Categorisation |
Several data samples | Identification | Clustering |
When a collection of data samples is provided, identification means selecting a particular sample having a (predefined) characteristic which distinguishes it from the others. Several data samples are generally matched against the one to be identified in a many-to-one process.
Authentication involves verifying the identity of a sample using a test of genuineness and it involves a one-to-one comparison with the genuine (authentic) sample.
Categorisation means assigning a data sample to a class according to certain distinguishing properties (or characteristics) of that class and it generally involves a one-to-many test in which one data sample is compared with the characteristics of several classes.
Clustering means grouping data samples in groups or classes based on their properties (or characteristics) and it generally involves a many-to-many (dis)similarity test.
Data mining and pattern recognition techniques in general are classified in G06F 18/00.
Some techniques of image or video understanding performed in the preprocessing step (Fig. 1, elem. 2) — which start with a bitmap image as an input and derive a non-bitmap representation from it — can also be encountered in general image analysis. If these techniques do not involve one of the functions of image or video pattern authentication, identification, categorisation or clustering, classification should be made only in the appropriate subgroups of subclass G06T. Some examples of these techniques are: general methods for image segmentation, e.g. obtaining contiguous image regions with similar pixels, for position and size determination of an object without establishing its identity, for calculating the motion of an image region corresponding to an object irrespective of the identity of the object, for camera calibration, etc.
Biometric recognition provided under G06V 40/00 does not cover techniques for medical image inspection or medical diagnosis.
Techniques based on coding, decoding, compressing or decompressing digital video signals using video object coding are provided under H04N 19/20.
Velocity or trajectory determination systems or sense-of-movement determination systems using radar, sonar or lidar are provided for under G01S 13/58, G01S 15/58, G01S 17/58, respectively.
General purpose image data processing, in particular image watermarking is provided under G06T 1/00, while selective content distribution, such as generation or processing of protective or descriptive data associated with content involving watermarking is covered by H04N 21/8358.
General purpose image data acquisition and related pre-processing using digital cameras and processing used to control digital cameras is provided under H04N 5/00.
Play-back, editing, or synchronising of a music score, including interpretation therefor, as well as transmission of a music score between systems of musical instruments for play-back, editing or synchronising is provided under G10H.
Examples of places where the subject matter of this place is covered when specially adapted, used for a particular purpose, or incorporated in a larger system:
Detecting, measuring and recording for medical diagnostic purposes | |
Identifications of persons in medical applications | |
Postal sorting | |
Input arrangements for interaction between user and computer | |
Testing to determine the identity or genuineness of paper currency or similar valuable papers |
Attention is drawn to the following places, which may be of interest for search:
Programme-controlled manipulators | |
Optical viewing arrangements in vehicles | |
Testing machines or structures | |
Investigating or analysing materials by determining their chemical or physical properties | |
Radio direction-finding; Radio navigation; Determining distance or velocity by use of radio waves; Locating or presence-detecting by use of the reflection or reradiation of radio waves; Analogous arrangements using other waves | |
Geophysics | |
Optical elements, systems, or apparatus | |
Photomechanical production of textured or patterned surfaces, e.g. for printing, for processing of semiconductor devices | |
Control or regulating systems in general | |
Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements | |
Content-based image retrieval | |
Fourier, Walsh or analogous domain transformations | |
Security arrangements for protecting computer systems against unauthorised activity | |
Authentication of user input in security arrangements for computers | |
Computer-aided design | |
Handling natural language data | |
Methods or arrangements for sensing record carriers | |
Record carriers for use with machines and with at least a part designed to carry digital markings | |
Computer systems based on specific computational models | |
Data processing for business purposes, logistics, stock management | |
General purpose image data processing, e.g. general purpose image acquisition, image watermarking or specific image analysis processor architectures or configurations | |
Geometric image transformation in the plane of the image, e.g. rotation of a whole image or part thereof | |
Image enhancement or restoration | |
Image analysis in general | |
Image analysis, in particular analysis of motion using feature-based methods | |
Image analysis, in particular determination of transform parameters for the alignment of images using feature-based methods | |
Image analysis of texture | |
Image analysis, in particular depth or shape recovery | |
Image analysis, in particular determining position and orientation of objects using feature-based methods | |
Image analysis, in particular determination of colour characteristics | |
Image coding, e.g. from bit-mapped to non bit-mapped | |
Contour coding, e.g. using detection of edges | |
Two-dimensional image generation | |
Three-dimensional image rendering | |
Lighting effects in 3D image rendering | |
Three-dimensional modelling, e.g. data description of 3D objects | |
Manipulating 3D models or images for computer graphics | |
Individual entry and exit registers | |
Intruder alarms using image scanning and comparing means | |
Burglar, theft or intruder alarm | |
Traffic control systems for road vehicles | |
Labels, tag tickets or similar identification or indication means | |
Speech recognition | |
Speaker recognition | |
Bioinformatics | |
Chemoinformatics and computational material science | |
Healthcare informatics | |
Semiconductor devices | |
Secret or secure communication | |
Scanning, transmission or reproduction of documents, e.g. facsimile transmission | |
Studio circuitry for television systems | |
Closed circuit television systems | |
Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using video object coding | |
Methods or arrangements for coding, decoding, compressing or decompressing digital video signals, region motion estimation for predictive coding |
The subject-matter classified in the application-oriented groups G06V 20/00 - G06V 40/00 is also classified in the groups G06V 10/10 (Image acquisition) or G06V 10/20 (Image preprocessing) when specific adaptations of the application-related context occur at the stages of image acquisition or, respectively, image preprocessing.
Pattern recognition or pattern learning techniques for images or video understanding involving feature extraction (Fig. 1, elem. 3) or matching, clustering or classification (Fig. 1, elem. 4) should be classified in G06V 10/40 or G06V 10/70 in general, thus irrespective whether an application-related context provided by the groups G06V 20/00 - G06V 40/00 exists.
In this place, the following terms or expressions are used with the meaning indicated:
Pattern | Data with inherent variability, or a representation derived from it, having some explanatory characteristic or a meaning, e.g. an object depicted in an image |
Image and video understanding | Techniques for semantic interpretation, pattern recognition or pattern learning specifically applied to images and videos |
Feature extraction | Deriving descriptive or quantitative measures from data |
Clustering | Grouping or separating patterns according to their (dis)similarity or closeness |
Classification | Assigning labels to patterns |