Skip to content
PCE
Search Classifications
Search for IPC and CPC classification codes or keywords
IPC Subclass
G06V

IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

Introduced: January 2022

Classification Context

Section:
PHYSICS
Class:
COMPUTING OR CALCULATING; COUNTING
Subclass:
IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

Description

G06V covers computer-implemented methods and systems for analyzing, interpreting, and understanding visual information from still images or video sequences. Technologies include object detection and recognition, scene understanding, face recognition, optical character recognition (OCR), motion analysis, and video indexing or retrieval. The class encompasses both the algorithmic approaches (such as pattern matching, feature extraction, and machine learning models) and the hardware architectures that enable such visual processing tasks. This classification excludes general image data processing or manipulation (covered by G06T) and focuses specifically on the recognition, understanding, or semantic interpretation of visual content.

Scope Notes

Glossary: authentication verifying the identity of a sample using a test of genuineness by undertaking a one-to-one comparison with the genuine (authentic) sample. categorisation assigning a sample to a class according to certain distinguishing properties (or characteristics) of that class; it generally involves a one-to-many test in which one data sample is compared with the characteristics of several classes. classification assigning labels to patterns. clustering grouping or separating samples in groups or classes according to their (dis)similarity or closeness. It generally involves many-to-many comparisons using a (dis)similarity measure or a distance function. feature extraction deriving descriptive or quantitative measures from data. identification in the context of collecting of samples, identification means selecting a particular sample having a (predefined). characteristic which distinguishes it from the others. Several samples are generally matched against the one to be identified in a many-to-one process. image and video understanding techniques for semantic interpretation, pattern recognition or pattern learning specifically applied to images and videos. pattern patterns data having characteristic regularity, or a representation derived from it, having some explanatory value or a meaning, e.g. an object depicted in an image. | Application references: Detecting, measuring and recording for medical diagnostic purposes Identifications of persons in medical applications Sorting of mail or documents using means for detection of the destination Input arrangements for interaction between user and computer Testing to determine the identity or genuineness of paper currency or similar valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency

4 direct subcodes

Child Classifications

Navigate with arrow keys, Enter to open