Aviation cable coding visual identification technical method and device considering coding directivity

Abstract

The invention discloses an aviation cable coding visual identification method and device considering coding directivity, and the method comprises the steps: collecting a cable surface coding image, and carrying out the image preprocessing; acquiring upper and lower boundary points of the cable in the cable surface coding image, fitting a boundary and performing inclination correction, and correcting the cable to be in a horizontal direction; coding in the cable surface coding image is segmented and optimized to obtain a plurality of rectangular areas, and the plurality of rectangular areas are rotated to obtain a plurality of coding characters to be identified; inputting the plurality of to-be-recognized coded characters into a plurality of pre-trained classifiers used for respectively coding directions, and obtaining the coding directions and a coding recognition result through the plurality of classifiers. According to the method, the large classifier is divided into a plurality of small classifiers, so that classification categories are reduced, and the accuracy of code recognition is improved.

Description

technical field [0001] The present application relates to the technical field of visual inspection in automation equipment and manufacturing, and in particular to a method and device for visual recognition of aviation cable codes considering the directionality of codes. Background technique [0002] In the production process of aviation aircraft, a large number of cables need to be docked according to the functions of the cables. In order to avoid confusing the cables, a laser marking machine will be used to print a code on the cable in advance, and a pairing table between the codes will be established. Manually read the code and consult the pairing table for cable docking. However, the wire diameter of the aviation cable is very thin (2-5mm), and the coded characters are very small, and employees who identify the cable for a long time will cause a certain degree of damage to the eyes. Many studies consider that visual inspection has the characteristics of good non-contact,...

AI Technical Summary

Problems solved by technology

[0003] At present, there is some research on the use of vision for cable code recognition. The specific methods include two types: (1) Using CRNN convolutional neural network to directly recognize character sequences. The advantage of this method is that it can be directly processed without pre-processing Recognize the character sequence without considering the character direction of the cable and other information. The disadvantage is that a large amount of training data (tens of thousands) needs to be obtained manually; (2) obtained by preprocessing the image (character segmentation, standardization, etc.) Images of coded characters to be recognized, and then use machine learning methods such as BP neural network and SVM to recognize characters one by one. This method increases the similarity of each type of characters and reduces the difficulty of character recognition, so it does not require a large amount of data for training. But the disadvantage is that it is difficult to ensure the accuracy of character segmentation, and due to the character-by-character recognition and the uncertain direction of cable placement (the direction of each character segmented from left to right and right to left should be opposite), it may be Misrecognition of characters occurs (such as 6 and 9, M and W are centrally symmetrical, and the recognition may fail)

Images