Author/Authors :
Masood, Haris University of Wah - Wah Cantt, Pakistan , Zafar, Amad Department of Electrical Engineering - University of Lahore - Islamabad Campus, Pakistan , Umair Ali, Muhammad Department of Unmanned Vehicle Engineering - Sejong University - Seoul, Republic of Korea , Attique Khan, Muhammad Department of Computer Science - HITEC University Taxila - Taxila, Pakistan , Iqbal, Kashif University of Wah - Wah Cantt, Pakistan , Tariq, Usman Prince Sattam Bin Abdulaziz University - Al-Khraj, Saudi Arabia , Kadry, Seifedine Faculty of Applied Computing and Technology - Noroff University College - Kristiansand, Norway
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.
Keywords :
Optimization , Technique , OT , MACH
