摘要
复杂环境下的圆形仪表表盘识别是当今社会工业自动化进程中的一个重大难题。由于天气环境复杂、仪表背景混乱,使用霍夫变换进行圆形表盘定位精度有待提高。为了实现多圆仪表的精准定位,本文提出一种自定义的去除非目标圆干扰以及解决多圆并排摆放的算法。首先使用霍夫变换检测初始圆,然后基于基准图像的先验知识对霍夫圆进行筛选。实验的结果显示,本文所提算法可以有效去除复杂背景环境的干扰,识别准确率达98.5%,运行时间为0.37s,识别效率显著提高。
The recognition of circular instrument dials in complex environments is a major challenge in today's industrial automation process.Due to the complex weather environment and chaotic instrument background,the accuracy of using Hough transform for circular dial positioning needs to be improved.In order to achieve precise positioning of multi circle instruments,this paper proposes a custom algorithm for removing non target circle interference and solving the problem of multiple circles being placed side by side.Firstly,the initial circle is detected using the Hough transform,and then the Hough circle is filtered based on prior knowledge of the reference image.The experimental results show that the algorithm proposed in this paper can effectively remove the interference of complex background environments,with a recognition accuracy of 98.5%,a running time of 0.37 seconds,and a significant improvement in recognition efficiency.
作者
赵丽
ZHAO Li(Henan Industrial and Trade Vocational College,Zhengzhou,China,451191)
出处
《福建电脑》
2025年第6期25-28,共4页
Journal of Fujian Computer
基金
河南省科技厅科技攻关项目《基于深度学习和计算机视觉的宫颈癌检测模型创建及应用研究》(No.252102210112)
河南省科技厅科技攻关项目《基于多视角场景下的显著性目标检测方法研究》(No.252102210082)资助。
关键词
圆形仪表
表盘识别
霍夫变换
算法
Circular Instrument
Dial Recognition
Hough Transform
Algorithm
