PGC-Net: A Light Weight Convolutional Sequence Network for Digital Pressure Gauge Calibration

Abstract

Automatic digital pressure gauge calibration is challenging due to various unconstrained conditions. Although existing CNN-RNN based methods have been almost perfect on scene text recognition, they fail to perform well on digital pressure gauge calibration that requires to be extremely computationefficient and accurate. In this paper, we propose a light weight fully convolutional sequence recognition network for fast and accurate digital Pressure Gauge Calibration (PGC-Net). PGC-Net integrates feature extraction, sequence modelling and transcription into a unified framework. Experimental results show that PGC-Net runs 28 fps on CPU with 97.41% accuracy. Compared with previous methods, PGC-Net achieves better or comparable performance at lower inference time. Without bells and whistles, PGC-Net is capable of recognizing decimal points that usually appear in pressure gauge images, which evidently verifies the feasibility of PGC-Net. We collected a dataset that contains 17, 240 gauge images with annotated labels for automatic digital pressure gauge calibration. The dataset has been public for future research.

Generative Data Augmentation for Automatic Meter Reading Using CNNs

“…Then Tesseract [23], an open source OCR engine, have been widely used [6], [24], [25], though the recognition results are not quite satisfied. On the other hand, BLSTM [26], [27] and FCSRN [28] employed CNN architecture for sequence recognitions and achieved impressive recognition rates. However, their methods were evaluated with manually cropped counter images and hence its effectiveness for the real-world scenario is unclear.…”

Automatic Meter Reading Based on Bi-Fusion MSP Network and Carry-Out Rechecking

“…Instead of BLSTM, Yang et al [32] used a Recurrent Neural Network (RNN) for sequence modeling and then recognized the digits of water meters. For mobile applications, Li et al [33] proposed a PGC (Pressure Gauge Calibration) sequence network with three convolutional layers to recognize the digits of pressure gauge meters for fast and accurate gauge calibration. For performance evaluation, Laroca et al [23] introduced a public dataset, called the UFPR-AMR dataset, to evaluate different CNN-based approaches for AMR.…”