• 首页
  • 期刊简介
  • 编委会
  • 投稿指南
  • 收录情况
  • 杂志订阅
  • 联系我们
引用本文:李茂民,邹臣嵩.基于改进遗传算法的阈值图像分割方法[J].软件工程,2022,25(1):37-40.【点击复制】
【打印本页】   【下载PDF全文】   【查看/发表评论】  【下载PDF阅读器】  
←前一篇|后一篇→ 过刊浏览
分享到: 微信 更多
基于改进遗传算法的阈值图像分割方法
李茂民,邹臣嵩
(广东松山职业技术学院电气工程学院,广东 韶关 512126)
1056171963@qq.com; 190352915@qq.com
摘 要: 本文提出一种新的基于改进遗传算法和阈值图像分割相结合的人像图像分割方法。这种新的改进方法以遗传算法为基础,利用遗传算法具有较高的搜索效率、明显的搜索精度,提升了图像分割阈值的精度获取,提高了图像分割的抗噪能力,在提升阈值稳定的同时,提升了阈值的获取速度及获取精度,解决了传统算法应用于人像图像分割时分割效果不理想、分割精度较低的缺点。经过实验验证,利用本文改进算法能达到较好分割效果,具有较好的抗噪能力,从而缩短分割图像时间。
关键词: 人像;图像分割;遗传算法
中图分类号: TP311    文献标识码: A
基金项目: 韶关市科技计划项目(2019sn094,200811224533986).
Research on Threshold Image Segmentation Method based on Improved Genetic Algorithm
LI Maomin, ZOU Chensong
(Department of Electrical Engineering, Guangdong Songshan Polytechnic, Shaoguan 512126, China)
1056171963@qq.com; 190352915@qq.com
Abstract: This paper proposes a new portrait image segmentation method based on a combination of improved genetic algorithm and threshold image segmentation. Genetic algorithm, which has higher search efficiency and obvious search accuracy, is used as a basis in the new improved method to improve the accuracy acquisition and the anti-noise ability of image segmentation. While increasing the stability of the threshold value, it improves the speed and accuracy of the threshold value acquisition, so to overcome the shortcomings of unsatisfactory segmentation effect and low segmentation accuracy when traditional algorithms are applied to portrait image segmentation. Experiments verify that the improved algorithm in this paper achieves a better segmentation effect and has better anti-noise ability, thereby shortening the image segmentation time.
Keywords: portrait; image segmentation; genetic algorithm


版权所有:软件工程杂志社
地址:辽宁省沈阳市浑南区新秀街2号 邮政编码:110179
电话:0411-84767887 传真:0411-84835089 Email:semagazine@neusoft.edu.cn
备案号:辽ICP备17007376号-1
技术支持:北京勤云科技发展有限公司

用微信扫一扫

用微信扫一扫