Visual Objects Classification with Sliding Spatial Pyramid Matching

TL;DR

This paper introduces Sliding Spatial Pyramid Matching (SSPM), a novel image feature extraction method for object classification that improves accuracy by sliding a fixed-size window across images and combining multiple models.

Contribution

The paper proposes SSPM, a new variant of Spatial Pyramid Matching that enhances feature extraction for object classification using a sliding window approach and ensemble learning.

Findings

Achieved 83.46% accuracy on Caltech-101 dataset.

Outperformed traditional SPM methods.

Demonstrated effectiveness of ensemble of linear regression models.

Abstract

We present a method for visual object classification using only a single feature, transformed color SIFT with a variant of Spatial Pyramid Matching (SPM) that we called Sliding Spatial Pyramid Matching (SSPM), trained with an ensemble of linear regression (provided by LINEAR) to obtained state of the art result on Caltech-101 of 83.46%. SSPM is a special version of SPM where instead of dividing an image into K number of regions, a subwindow of fixed size is slide around the image with a fixed step size. For each subwindow, a histogram of visual words is generated. To obtained the visual vocabulary, instead of performing K-means clustering, we randomly pick N exemplars from the training set and encode them with a soft non-linear mapping method. We then trained 15 models, each with a different visual word size with linear regression. All 15 models are then averaged together to form a single strong model.