Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features

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

Scope Notes

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