摘要
针对自然场景下由LED灯组合形成的数字具有易受光照、背景和成像扭曲等因素影响识别困难的特点,提出了一种LED-LeNet卷积网络识别算法。对自采集LED灯类字体数据集按数字进行分类,将图像ROI操作、分辨率调整至32×32和数据增强等预处理后,在LeNe-5网络架构上通过卷积核重构、使用Swish激活函并数引入Dropout正则化等方法改进网络。采用自然场景下采集的交通信号灯倒计时数字图像数据库TST对算法进行了验证,算法识别正确率可达99.52%,识别速度为1 ms。实验结果表明在调整网络结构与卷积核参数并通过改变训练策略后算法识别LED灯类字体具有明显优势。
In order to solve the LED recognition problem that the number formed by the factors such as illumination,background,and image distortion in natural scene,a recognition algorithm of LED-LeNet convolutional network is proposed.Firstly,the self collected LED light font data set was classified according to the number.Image data preprocessing includes image ROI operation,resolution adjustment to 32×32 and data enhancement.The network was reconstructed by convolution kernel,swish activation function and dropout regularization which referred to LeNet-5 network.The algorithm was verified by TST digital image database of traffic signal countdown collected in natural scene.The recognition accuracy of the algorithm can reach 99.52%,and the recognition speed was 1 ms.The experimental results show that the algorithm has obvious advantages in recognizing LED light fonts after adjusting the network structure and convolution kernel parameters and changing the training strategy.
作者
王立刚
张志佳
李晋
范莹莹
刘立强
Wang Ligang;Zhang Zhijia;Li Jin;Fan Yingying;Liu Liqiang(School of Information Science and Engineering,Shenyang University of Technology,Shenyang 110870,China;Liaoning Aerospace Linghe Automobile Co.,Ltd.,Chaoyang 122599,China)
出处
《电子测量与仪器学报》
CSCD
北大核心
2020年第11期148-154,共7页
Journal of Electronic Measurement and Instrumentation
基金
国家自然科学基金(61540069)资助项目