Part code spraying detection method based on a convolutional neural network

Abstract

The invention discloses a part code spraying detection method based on a convolutional neural network. The part code spraying detection method comprises the following steps: S1, collecting an image; S2, extracting a binary image of the code spraying area; S3, segmenting a code spraying area; S4, training the convolutional neural network; S5: code spraying detection. According to the method, a morphological method is used for extracting the code spraying area, inclination correction of the code spraying area is completed through affine transformation, the code spraying area can be effectively extracted, orthodontics can be completed, noise around the code spraying area and interference caused by code spraying inclination are eliminated, and good robustness is achieved; The projection algorithm is improved, single character segmentation is completed according to the information of the target image, priori information such as the number of characters and the width of characters is not needed, and the limitation that priori knowledge such as the number of characters needs to be given in advance in a traditional algorithm is effectively solved.

Description

technical field [0001] The invention relates to the technical fields of machine learning and computer vision, in particular to a method for detecting codes of parts and components based on a convolutional neural network. Background technique [0002] Computer vision and machine learning are hot technologies that have developed rapidly in recent years, and have brought tremendous changes to people's production and life. As computer vision and machine learning become more and more integrated into people's daily lives, people are also starting to think about their applications in industry. The problem of inkjet detection of parts in industrial production is an important application direction. [0003] Coding detection and identification is an important means to classify and track products in the production process, and is the basis for determining the subsequent processing plan of the production line. In the past few decades, computer vision technology has made great breakthr...

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is to provide a computer vision technology that can effectively solve the problems of character adhesion and inkjet discreteness when the current computer vision technology is not effective or needs to rely on prior knowledge to complete the detection. The problem of recognition can effectively remove noise interference, complete text orthodontics, and achieve the effect of high-precision recognition of inkjet characters

Images