Application of Improved Satin Bowerbird Optimizer in Image Segmentation

Abstract

Aiming at the problems of low optimization accuracy and slow convergence speed of Satin Bowerbird Optimizer (SBO), an improved Satin Bowerbird Optimizer (ISBO) based on chaotic initialization and Cauchy mutation strategy is proposed. In order to improve the value of the proposed algorithm in engineering and practical applications, we apply it to the segmentation of medical and plant images. To improve the optimization accuracy, convergence speed and pertinence of the initial population, the population is initialized by introducing the Logistic chaotic map. To avoid the algorithm falling into local optimum (prematurity), the search performance of the algorithm is improved through Cauchy mutation strategy. Based on extensive visual and quantitative data analysis, this paper conducts a comparative analysis of the ISBO with the SBO, the fuzzy Gray Wolf Optimizer (FGWO), and the Fuzzy Coyote Optimization Algorithm (FCOA). The results show that the ISBO achieves better segmentation effects in both medical and plant disease images.

Hybrid improved capuchin search algorithm for plant image thresholding

“…In addition to comparing the results with the original capuchin search algorithm, the results are also fully compared and analyzed with FABC (Li et al, 2016), MWOA (Anitha et al, 2021), DCOA (Li et al, 2021) et al To reflect the best performance of ICAPSA, the parameter setting is discussed first. In this paper, the number of thresholds (NT) is set to 2, 3, 4, 5. the objective function is set as the Kapur which commonly used in thresholding image segmentation (Li et al, 2022), and the parameter selection feature similarity FSIM (Pare et al, 2020) and peak signalto-noise ratio PSNR (Abualigah et al, 2022) are compared. The experiments performed in our work are run on Windows10-64bit, Intel processor and 16GB running memory and the programming software is Matlab 2016a.…”

“…Compared with the Comprehensive Learning Particle Swarm Optimizer (CLPSO) and Hybridizing Sine Cosine Algorithm with Differential Evolution (SCADE) algorithm in the corn leaf disease image in the public database of a plant village company, the results show this method to be superior to other comparison algorithms in locating the best threshold, and have higher convergence accuracy. Li et al (2022) proposed a strategy based on chaos initialization and Cauchy mutation to improve Satin Bowerbird Optimization Algorithm (SBO), and verified its values in Kaggle plant image dataset. The comparison between the fuzzy Modified Discrete Grey Wolf Optimizer with aggregation strategy (FMGWO) and the fuzzy Coyote Optimization Algorithm (FCOA) proves that the improved ISBO has higher accuracy in the field of plant image segmentation.…”

“…However, segmentation accuracy and efficiency directly affect the application of segmentation technology in plant applications. Making use of the advantages of meta-heuristic algorithms in multi-level image thresholding is thus considered an effective plant disease assisted treatment ( Li et al., 2022 ).…”

“…Meta-heuristic optimization algorithms can effectively improve the computational efficiency in multi-level image thresholding. However, there is room for further improvement in population initialization and global search ability ( Pare et al., 2020 ; Li et al., 2022 ). Therefore, this paper seeks to improve CAPSA, comparing its efficacy in plant image segmentation with other algorithms.…”

Pressure Vessel Design Problem Using Improved Gray Wolf Optimizer Based on Cauchy Distribution

“…The peak distribution of the Cauchy distribution at the origin of the coordinates is shorter, and the rest of the peak distribution is longer. In comparison to the Gaussian distribution, the Cauchy distribution exhibits a broader spread and a more pronounced propensity for dispersion [31], endowing it with the ability to produce outlier values at considerable distances from the mean. Luo [32] has observed that, while the Gray Wolf Optimizer (GWO) demonstrates exemplary efficacy in resolving optimization problems with global optima situated at the coordinate origin, its performance is marred by a marked search bias in scenarios where the optima deviate from this central point.…”