Collective Neurodynamic Optimization for Image Segmentation by Binary Model with Constraints
- PDF / 19,710,656 Bytes
- 11 Pages / 595.224 x 790.955 pts Page_size
- 84 Downloads / 240 Views
Collective Neurodynamic Optimization for Image Segmentation by Binary Model with Constraints Shengzhan He1 · Junjian Huang1 · Xing He1 Received: 28 April 2020 / Accepted: 14 August 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Threshold method is an important image segmentation method, which has been widely used in image segmentation. For this method, it is very important to choose a good threshold. The traditional threshold segmentation algorithm is implemented by exhaustive method, which makes the solution efficiency very low. This paper presents a collective neurodynamic optimization algorithm to solve the problem of binary optimization in the image segmentation. The problem of image segmentation based on threshold is transformed into binary optimization with constraints. Then, a collective neurodynamic optimization algorithm is introduced which combined with feedback neural network and particle swarm optimization (PSO) algorithm. And the linear programming relaxation constraint method is used to relax binary constraints. It is proved by numerical simulation that the feedback neural network algorithm can converge to the exact local optimal solution of the model and the PSO algorithm can get a better local optimal solution. Finally, several sets of comparative experiments are presented. The feasibility of our proposed method is verified; the experimental results demonstrate the effectiveness of our approach in image segmentation. In this study, a collective neurodynamic optimization was proposed for the image segmentation problem. In the future, we expect that multiple centralized neurodynamic models and intelligent algorithms can be used to solve the problem and improve the convergence speed of the solved model. Keywords Image segmentation · Collective neurodynamic optimization · Binary optimization · Feedback neural network · Particle swarm optimization
Introduction Wit h the development of science and technology, image processing technology had developed rapidly in life, and image segmentation has been widely used in unmanned driving, augmented reality, security monitoring, and other industries. The essence of image segmentation is the process of dividing an image into different regions according to the gray value of the image. And image segmentation can be roughly classified into traditional segmentation algorithms [1, 2] and machine learning methods [3]. And the deep learning algorithms are becoming more and more popular with the improvement of computer hardware performance. Xing He
[email protected] 1
Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing, College of Electronic and Information Engineering, Southwest University, Chongqing, 400715, China
Through a lot of data training, the algorithm can show strong robustness. In the field of computer vision, segmentation refers to the process of dividing an image into multiple regions. Traditional image segmentation algorithms include image segmentation algorithm based on threshol
Data Loading...
