Intermediate · Computer Vision
Bag-of-words model in computer vision
Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.
TL;DR. Adapts the bag-of-words concept for images by treating visual features as words.
Technical Definition
Adapts the bag-of-words concept for images by treating visual features as words.
How it works
In computer vision, the bag-of-words (BoW) model is used to represent images by extracting local features, such as SIFT or SURF descriptors. These features are then clustered to form a 'visual vocabulary,' and images are represented as histograms of these visual word occurrences. This approach is often applied to image classification tasks.
Related Concepts
- Feature Extraction — Deriving informative numerical signals from raw data for use as model inputs.
- Bag-of-words model — A text representation that counts word occurrences, ignoring grammar and word order, to capture content.
- Computer vision — Computer vision enables computers to interpret and understand information from digital images and videos, automating tasks typically done by human sight.
- Image Classification — The task of categorizing images into one of several predefined classes.