Image Retrieval Method Using Top-surf Descriptor

TL;DR

This paper explores a content-based image retrieval method utilizing the Top-surf descriptor, demonstrating preliminary results that indicate its ability to identify objects from parts or similar objects within a diverse image dataset.

Contribution

It introduces a Top-surf descriptor-based approach for image retrieval and provides initial experimental results on a multi-category dataset.

Findings

Best results obtained in the building category

Shows capability of deducing objects from parts or similar objects

Preliminary experimental results support the method's potential

Abstract

This report presents the results and details of a content-based image retrieval project using the Top-surf descriptor. The experimental results are preliminary, however, it shows the capability of deducing objects from parts of the objects or from the objects that are similar. This paper uses a dataset consisting of 1200 images of which 800 images are equally divided into 8 categories, namely airplane, beach, motorbike, forest, elephants, horses, bus and building, while the other 400 images are randomly picked from the Internet. The best results achieved are from building category.