| 王立刚,张志佳,李 晋,范莹莹,刘立强.基于卷积神经网络的 LED 灯类字体数字识别[J].电子测量与仪器学报,2020,34(11):148-154 |
| 基于卷积神经网络的 LED 灯类字体数字识别 |
| Digital recognition of LED lights based on convolutional neural networks |
| |
| DOI： |
| 中文关键词: LED-LeNet 自然场景 卷积神经网络 数字识别 |
| 英文关键词:LED-LeNet natural scene convolutional neural network digital recognition |
| 基金项目:国家自然科学基金(61540069)资助项目 |
|
|
|
|
| 摘要点击次数: 289 |
| 全文下载次数: 494 |
| 中文摘要: |
| 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。 |
| 英文摘要: |
| 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. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
