基于视觉传达的激光成像特征识别方法
Laser Imaging Feature Recognition Method Based on Visual Communication
赵丽 1朱冰洁 1卢翠1
作者信息
- 1. 河北工程技术学院,河北石家庄 050000
- 折叠
摘要
激光成像利用激光束扫描物体,根据反射光束形成图像落差,以此反映所成图像.但是扫描过程形成的反射光束容易受外界噪声及冗余的干扰,导致激光反射图像特征出现细微形变,影响激光图像识别精度.因此,引入视觉传达提出一种激光成像特征识别方法.通过视觉系统标定法获取激光成像特征;采用卷积神经网络对激光成像特征进行降噪;利用支持向量机确定特征样本分类面,计算各类样本距离分类面的概率分布,实现激光成像特征识别.实验结果表明,所提方法的识别时间均在100 s以下,引入噪声后的识别准确率均高于94％,体现了所提激光成像特征识别技术的有效性.
Abstract
Laser imaging entails scanning objects with a laser beam,generating an image based on the reflected beam.However,exter-nal noise and redundancy during scanning often distort the laser-reflected image characteristics,impeding recognition accuracy.To ad-dress this issue,we propose a laser imaging feature recognition method incorporating visual communication techniques.Specifically,the method first obtains laser imaging characteristics through a vision system calibration process.Subsequently,a convolutional neural net-work is utilized to denoise the laser imaging features.Finally,a support vector machine determines the classification boundary for the feature samples,and calculates the probability distribution of various samples from this boundary,enabling laser imaging feature recog-nition,Experimental results demonstrate that the proposed method achieves a recognition time of less than 100 seconds,and maintains a recognition accuracy of over 94％even in noisy conditions.This indicates the effectiveness of the proposed approach in improving the robustness and accuracy of laser imaging feature recognition.
关键词
视觉传达技术/卷积神经网络/支持向量机/距离分类/模式识别Key words
visual communication technology/convolution neural network/support vector machine/distance classifica-tion/pattern recognition引用本文复制引用
基金项目
河北省人社厅项目(JRS-2021-1203)
河北省自然科学基金(C2019204032)
出版年
2024
NETL
NSTL
万方数据