G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
Introduced: January 2022
Full Title
Arrangements for image or video recognition or understanding > Extraction of image or video features > Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
Classification Context
- Section:
- PHYSICS
- Class:
- COMPUTING OR CALCULATING; COUNTING
- Subclass:
- IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
Additional Content
Glossary
BOF bag of features, see BOW BOVF bag of visual features, see BOVF BOVW bag of visual words, see BOW BOW bag of words, a model originally developed for natural language processing; when applied to images, it represents an image by a histogram of visual words, each visual word representing a specific part of the feature space. MSER maximally stable extremal regions, a technique used for blob detection RANSAC random sample consensus, a popular regression algorithm SIFT scale-invariant feature transform superpixels superpixel sets of pixels obtained by partitioning a digital image for saliency assessment SURF speeded up robust features
Limiting references
Colour feature extraction
Top Applicants
Top 10 applicants by patent filingsfor class G06, 2013–2023, worldwide · Source: EPO PATSTAT
- SAMSUNG ELECTRONICS COMPANY KR 66,669
- IBM (INTERNATIONAL BUSINESS MACHINES CORPORATION) US 62,313
- MICROSOFT TECHNOLOGY LICENSING US 41,918
- GOOGLE US 32,969
- SGCC(STATE GRID CORPORATION OF CHINA) 30,822
- INTEL CORPORATION US 30,010
- TENCENT TECHNOLOGY (SHENZHEN) COMPANY 28,235
- HUAWEI TECHNOLOGIES COMPANY CN 26,079
- APPLE US 21,891
- HUAWEI TECHNOLOGIES COMPANY 20,505