Image Segmentation with Multilevel Threshold of Gray-Level & Gradient-Magnitude Entropy Based on Genetic Algorithm

Abstract

Abstract-Due to consider the gray level spatial distribution information, some image segmentation technologies based on entropy threshold can enhance the thresholding segmentation performance. However, they still cannot distinguish image edges and noise well. Even though GLGM(gray-level & gradientmagnitude) entropy can effectively solve the problem, but it cannot segment effectively multi-objective and complex image. In this paper, a GLGM entropy fast segmentation method based on GA is presented by combining Real-code-GA and GLGM entropy, and the single threshold segmentation of GLGM entropy is further extended to multilevel threshold segmentation. Our method compared with GLGM entropy multi-threshold exhaustive method, the segmentation result obtained by our method is basically the same as the result obtained by exhaustive method.

Convergent heterogeneous particle swarm optimisation algorithm for multilevel image thresholding segmentation

“…To evaluate the MTCHPSO method in terms of viability and applicability for multilevel thresholding segmentation, its performance is compared with three similar methods using a set of famous benchmark images which are well‐known in image processing literature. The GA [7, 20], the HS [22, 51] and the PSO [16, 37–42, 52] are selected among many optimisation algorithms [3, 8, 15, 17–19, 21, 51, 53–55] and for convenient we added multilevel thresholding before their names and call them as MTGA, MTHS and MTPSO, respectively. Images are the same in terms of size ( pixels) and properties [all grey‐level with the same format (.tiff)].…”

“…The application of the most popular heuristic algorithms such as particle swarm optimisation (PSO), genetic algorithms (GA), ant colony optimisation, simulated annealing and Tabu search for solving Otsu's and Kapur's problem are surveyed in [15]. So far, a huge number of similar techniques are proposed and compared with each other on benchmark images but this area is still open for research to find the better approach [6, 7, 10, 16–29].…”

A Multilevel Image Thresholding Method Based on Subspace Elimination Optimization

“…So, when the grey-level histogram methods as Otsu's and Kapur's methods are extended to multilevel thresholding problems, its efficiency becomes very low because the computational complexity of this kind method increases exponentially due to its exhaustive search [7,8]. The computational complex is one of the major reasons that so much different heuristic optimal techniques have been used in multilevel thresholding [9][10][11]. Generally, heuristic algorithms are inspired by such things as natural phenomena, physical laws, biological social activities, and evolutionary processes [10][11][12].…”

“…The speed and accuracy are improved compared to traditional methods. Chen proposed a hybrid algorithm based on a self-adaptive PSO to optimize the thresholds of Ostu's method [9]. Tang improved the parameters and evolutional process of basic PSO and used it in multilevel image thresholding based on maximum entropy [25].…”