Detection and recognition method for pointer-type meter based on deep learning
Wenyuan Ding, Bin Zhang · 2021 IEEE 3rd International Conference on Civil Aviation Safety and Information Technology (ICCASIT) · 2021
In order to free up human productivity and hand over the tedious and potentially dangerous task of reading numbers to machines, many experts and scholars have been working on meter recognition since the beginning of the 21st century. With the advent of deep learning techniques, gauge recognition has been greatly improved, but there are still many problems. In order to solve one of these problems, which requires manual input of scale position and scale value, this paper proposes a deep learning-based method for detecting and recognizing pointer-type gauges, which can extract the scale by introducing text detection and text recognition. Experiments show that this method can meet the requirements in terms of response time and accuracy even if it is fully automated.