Automatic identification system of aircraft cockpit indicators based on machine vision
Jiaqing Yao, Renwen Chen, Yijun Huang · 2022
Aiming at the problem that the test of civil aircraft is greatly affected by human factors in the batch manufacturing process, the automatic identification system of aircraft cockpit indicators based on machine vision is researched. Firstly, the slant screen images are automatically corrected and segmented by image processing technology. Secondly,different methods are used to identify different regions according to the specificity of different regions in the images. YOLOv5 algorithm is used for target detection of unconventional indicators; EasyOCR algorithm is used for character recognition, especially in decimal recognition, this research improved EasyOCR, in which using the projection of the legal decimal point position and cover at the data input end, modify the initial characteristics, to avoid the wrong identification interference of the decimal point. At the output end, the correct decimal point is reset between digits. The accuracy is improved by 27.65% and the average accuracy is 96.60%; Other general indicators recognition, using common image processing techniques, such as Hough transform, HSV color matching, etc. Experimental results show that the average error rate of identification results of various indicators is only 1.96%, the speed of machine recognition is 4.8 times that of manual test. Compared with manual test, it can effectively solve the problems of misjudgment, heavy workload and inefficient, and improve the degree of automation in the batch production process of civil aircraft.