Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Learn about the bag of visual words (BoVW) model, a pre-deep learning technique used in computer vision for creating image embeddings. Explore how this method enables image retrieval from databases, object detection, and image classification. Discover the practical applications of BoVW in building similarity-based image search systems and understanding its role in the evolution of computer vision techniques.
Syllabus
Bag of *Visual* Words for Image Classification and Retrieval
Taught by
James Briggs