A multilevel thresholding algorithm using LebTLBO for image segmentation

Segmentation is considered as one of the most significant tasks in image processing. It consists of separating the pixels into different segments based on their intensity level according to threshold values. Selecting the optimal threshold value is the key to best quality segmentation. Multilevel thresholding (MT) is an essential approach for image segmentation, and it has become very popular during the past few years, but while increasing the level of thresholds, computational complexity also increases exponentially. In order to overcome this drawback, several metaheuristics-based algorithms have been used for determining the optimal MT levels. Learning enthusiasm-based teaching-learning-based optimization (LebTLBO) is a recently developed efficient, simple-to-implement and computationally inexpensive algorithm. It simulates the behaviors of the teaching and learning process in a classroom and gives the probability of getting the amount of information by the learner (student) from the educator. In this paper, LebTLBO is applied on ten standard test images having a diverse histogram, which are taken from Berkeley Segmentation Dataset 500 (BSDS500) (Martin et al. in a database of human segmented natural images and its application to evaluate segmentation algorithms and measure ecological statistics, 2001) benchmark image set for segmentation. The search capability of the algorithm is combined with Otsu and Kapur's entropy MT objective functions for image segmentation. The proposed approach is compared with the existing state-of-the-art optimization algorithms such as MTEMO, GA, PSO and BF for both Otsu and Kapur's entropy methods. Qualitative experimental outcomes demonstrate that LebTLBO is highly efficient in terms of performance metrics such as PSNR, mean, threshold values, number of iterations taken to converge and image segmentation quality.