The Classification Accuracy of Multiple-Metric Learning Algorithm on Multi-Sensor Fusion

TL;DR

This study evaluates how different similarity search metrics and multi-sensor image fusion affect supervised classification accuracy, demonstrating improved results with Euclidean Distance and fused images.

Contribution

It introduces an analysis of four spatial metrics for similarity search and assesses multi-sensor image fusion's impact on classification accuracy.

Findings

Euclidean Distance outperformed other metrics in classification accuracy.

Fused multispectral and panchromatic images yielded better results than original images.

Multi-sensor fusion enhances supervised classification performance.

Abstract

This paper focuses on two main issues; first one is the impact of Similarity Search to learning the training sample in metric space, and searching based on supervised learning classi-fication. In particular, four metrics space searching are based on spatial information that are introduced as the following; Cheby-shev Distance (CD); Bray Curtis Distance (BCD); Manhattan Distance (MD) and Euclidean Distance(ED) classifiers. The second issue investigates the performance of combination of mul-ti-sensor images on the supervised learning classification accura-cy. QuickBird multispectral data (MS) and panchromatic data (PAN) have been used in this study to demonstrate the enhance-ment and accuracy assessment of fused image over the original images. The supervised classification results of fusion image generated better than the MS did. QuickBird and the best results with ED classifier than the other did.