Implementation and Analyzing SURF Feature Detection & Extraction on WANG Images Using Custom Bag of Features Model

EasyChair Preprint 6566

Abstract

A novel technique of image classification using BOVW model also known as Bag of Visual Words is very popular for retrieval of images using features instead of text vocabulary. The entire process first involves feature detection of images by selecting key points or forming a Grid over images, the choice made in order to speed up the process of detection. Then comes the stage of feature extraction for which SURF, a binary feature descriptor is employed. K-means clustering is then applied in order to quantize and make the bag of visual words. Every image, expressed as a histogram of visual words is fed to a supervised learning model, SVM for training. SVM is then tested for classification of images into respective classes. Matlab is used for implementation using bag class with Extractor fuction over 1000 image dataset WANG with 10 different categories.

Keyphrases: BoVW, Extractor function, K-means clustering, SURF, SVM

@booklet{EasyChair:6566,
  author    = {Roohi Ali and Manish Maheshwari},
  title     = {Implementation and Analyzing SURF Feature Detection & Extraction on WANG Images Using Custom Bag of Features Model},
  howpublished = {EasyChair Preprint 6566},
  year      = {EasyChair, 2021}}