SCGJO: A hybrid golden jackal optimization with a sine cosine algorithm for tackling multilevel thresholding image segmentation

Multilevel thresholding is a fundamental, substantial and constructive technique that has been widely recognized and concerned in recent years. However, the computational complexity rises as the threshold level raises. The golden jackal optimization (GJO) imitates discovering prey, tracking and encircling prey, and trapping prey by employing a collaborative foraging mechanism. To eliminate the GJO's drawbacks, such as premature convergence, inferior computation accuracy and sluggish convergence rate, this paper proposes a hybrid golden jackal optimization with a sine cosine algorithm (SCGJO) based on Kapur's entropy to tackle the multilevel thresholding image segmentation, the intention is to actualize the accurate threshold values and the maximal fitness values. The SCGJO not only has fantastic adaptability and reliability to promote the complementary benefits and boost the convergence accuracy but also integrates exploration and exploitation to mitigate search stagnation and arrive at the ideal value. The experimental results demonstrate that the SCGJO is superior to the other algorithms and has a quicker convergence rate, higher computation accuracy, greater segmentation quality and stronger stability. In addition, the SCGJO is a steady and trustworthy approach for tackling image segmentation.

Automated summary

This paper proposes a hybrid golden jackal optimization with a sine cosine algorithm (SCGJO) based on Kapur's entropy to tackle the multilevel thresholding image segmentation. The experimental results demonstrate that the SCGJO is superior to the other algorithms in terms of convergence rate, computation accuracy, segmentation quality, and stability. Additionally, the SCGJO is a steady and trustworthy approach for tackling image segmentation.