Institute of Engineering and Technology, Devi Ahilya University, Indore, M.P., 452001, India.
School of Computer Science and Information Technology, Devi Ahilya University, Indore, M.P., 452001, India.
Sci Rep. 2024 Oct 3;14(1):23019. doi: 10.1038/s41598-024-71270-0.
This manuscript proposes an automatic reading detection system for an analogue gauge using a combination of deep learning, machine learning, and image processing. The study suggests image-processing techniques in manual analogue gauge reading that include generating readings for the image to provide supervised data to address difficulties in unsupervised data in gauges and to achieve better accuracy using DenseNet 169 compared to other approaches. The model uses artificial intelligence to automate reading detection using deep transfer learning models like DenseNet 169, InceptionNet V3, and VGG19. The models were trained using 1011 labeled pictures, 9 classes, and readings from 0 to 8. The VGG19 model exhibits a high training precision of 97.00% but a comparatively lower testing precision of 75.00%, indicating the possibility of overfitting. On the other hand, InceptionNet V3 demonstrates consistent precision across both datasets, but DenseNet 169 surpasses other models in terms of precision and generalization capabilities.
本文提出了一种使用深度学习、机器学习和图像处理相结合的模拟仪表自动读数检测系统。该研究在手动模拟仪表读数中提出了图像处理技术，包括为图像生成读数，以提供有监督的数据来解决仪表中无监督数据的困难，并使用 DenseNet 169 实现比其他方法更好的准确性。该模型使用人工智能通过使用 DenseNet 169、InceptionNet V3 和 VGG19 等深度迁移学习模型自动进行读数检测。模型使用 1011 张带标签的图片、9 个类别和 0 到 8 的读数进行训练。VGG19 模型的训练精度较高，为 97.00%，但测试精度较低，为 75.00%，这表明存在过拟合的可能性。另一方面，InceptionNet V3 在两个数据集上都表现出一致的精度，但 DenseNet 169 在精度和泛化能力方面优于其他模型。
