| dc.description.abstract | With the rapid development of artificial intelligence, nowadays many traditional industries gradually from labor-intensive industry into artificial intelligence. In the field of scientific technology, deep learning algorithm has been improved and applied in many fields, especially in image processing and pattern recognition. Currently, traditional image processing methods have many limitations in the automatic instrument recognition and most of the proposed methods were designed for recognizing only one type of specific instrument meter. Therefore, this study proposes a novel method to recognize different instrument meters and read the scales pointed in the meters.
In this study, the main purpose is that a kind of intelligent system based on deep learning and image processing is designed to recognize common instruments such as circular meters, square meters and digital scale meters in the factory. First of all, we use object detection network YOLOv3 to locate instruments of images which are captured from mobile phone and camera. Then we use image processing technology to remove interference information of the images. Secondly, according to the type of instrument, HoughCircles and findContours functions are used to confirm the central position of the instrument, and hough line transform and polar coordinate method are used to realize the pointer position. In addition, YOLOv3 is applied again to recognize the number in order to find the closest number and the second closest number to the pointer, finally, we can calculate the value of the instrument.
This thesis uses object detection network to locate the instrument position. In comparison with the traditional methods, the proposed method can rapidly locate various types and sizes of the instrument in different images and has strong anti-interference. The system can be adapted to the different range and uneven scale of the instrument, which greatly improves the application range, and really realize the intelligent instrument recognition.
| en_US |