Image Segmentation Prediction Model of Machine Learning and Improved Genetic Algorithm

Authors

  • Caihong Li School of Electronic Information Engineering, Xi’an Siyuan University, Xi’an 710038, Shaanxi, China
  • Huie Zhang School of Electronic Information Engineering, Xi’an Siyuan University, Xi’an 710038, Shaanxi, China
  • Junjie Huang Foundation Department, Xi’an Siyuan University, Xi’an 710038, Shaanxi, China
  • Haijie Shen Mapúa University, Manila 1002, Philippines
  • Xinzhi Tian Mapúa University, Manila 1002, Philippines

Abstract

With the rapid development of science and technology, people’s requirements for image technology have becomemore andmore sophisticated. During segmentation, images are easily affected by external factors such as noise, offset, local effects and so on. As a result, it is difficult for the traditional segmentation algorithm to meet people’s expectations; also, the computer load is large and the segmented images are prone to many problems. In this paper, by improving the image segmentation method of the genetic algorithm (GA), in order to ensure the consistency and integrity of image information, the segmentation region is determined, and the segmentation model is established. After applying the improved genetic algorithm, the segmented image is compared in terms of CPU utilization, segmentation effect and genetic times. The results show that the accuracy of the improved
genetic algorithm is increased by 13.2%, and the genetic number is reduced by 45.2%. The improved segmentation algorithm ensures the consistency and information integrity of the segmentation area, and the segmented interface is relatively clear. It also shows that the image segmentation obtained by the improved genetic algorithm is better and more accurate than that produced by the traditional algorithm.

Keywords: image segmentation, improved genetic algorithm, machine learning, traditional algorithm

Cite As

C. Li, H. Zhang, H. Huang, H. Shen, X. Tian, "Image Segmentation Prediction Model of Machine Learning
and Improved Genetic Algorithm", Engineering Intelligent Systems, vol. 31 no. 2, pp. 115-125, 2023.










Published

2023-03-01