Optimization of Correlation Filters Using Extended Particle Swarm Optimization Technique.

Haris Masood,Kashif Iqbal,Muhammad Umair Ali,Amad Zafar,Usman Tariq,Seifedine Kadry,Muhammad Attique Khan

doi:10.1155/2021/6321860

Abstract

In the past few decades, the field of image processing has seen a rapid advancement in the correlation filters, which serves as a very promising tool for object detection and recognition. Mostly, complex filter equations are used for deriving the correlation filters, leading to a filter solution in a closed loop. Selection of optimal tradeoff (OT) parameters is crucial for the effectiveness of correlation filters. This paper proposes extended particle swarm optimization (EPSO) technique for the optimal selection of OT parameters. The optimal solution is proposed based on two cost functions. The best result for each target is obtained by applying the optimization technique separately. The obtained results are compared with the conventional particle swarm optimization method for various test images belonging from different state-of-the-art datasets. The obtained results depict the performance of filters improved significantly using the proposed optimization method.

Highlights

For the purpose of object detection and recognition in the fields of pattern recognition, computer vision, and image processing [1,2,3,4,5], correlation filters have been widely employed
The technique focuses on optimizing the tradeoff parameters pertaining to correlation filters which have not been achieved earlier
The optimization parameters achieved by using extended particle swarm optimization (EPSO) and particle swarm optimization (PSO) algorithms have been compared with the optimization values of the previously employed algorithms

Summary

Introduction

For the purpose of object detection and recognition in the fields of pattern recognition, computer vision, and image processing [1,2,3,4,5], correlation filters have been widely employed. Other fields in which correlation filters are used are object tracking [6, 7] and biometric object recognition [8,9,10]. The correlation filters are trained in a way to generate maximum correlation peaks pertaining to the objects desirous of being detected, while generation low peaks against illumination, clutter, and noise. Correlation filters date back to around three decades, when they were introduced primarily for object recognition [11]. Accurate recognition and tracking of objects can be carried out using the correlation filters.

Methods

Results

Conclusion