2D Image Features Detector And Descriptor Selection Expert System

TL;DR

This paper introduces an expert system for selecting optimal 2D image features detectors and descriptors, improving object recognition in industrial parts through hierarchical classification, despite increased computational time.

Contribution

It presents a novel expert system that enhances feature detector and descriptor selection for industrial object recognition using hierarchical classification.

Findings

Hierarchical classification improves recognition accuracy.

The proposed method outperforms single-method approaches.

The system increases computational time but yields better results.

Abstract

Detection and description of keypoints from an image is a well-studied problem in Computer Vision. Some methods like SIFT, SURF or ORB are computationally really efficient. This paper proposes a solution for a particular case study on object recognition of industrial parts based on hierarchical classification. Reducing the number of instances leads to better performance, indeed, that is what the use of the hierarchical classification is looking for. We demonstrate that this method performs better than using just one method like ORB, SIFT or FREAK, despite being fairly slower.