Guitar finished product detection method and detection system based on machine vision

Abstract

The invention discloses a guitar finished product detection method and system based on machine vision, and the method comprises the following steps: collecting guitar images, including a standard guitar image and a to-be-detected guitar image; performing image preprocessing on the acquired standard guitar image and the to-be-detected guitar image; establishing a guitar positioning template by using the collected standard guitar image; matching the guitar positioning template with the to-be-detected guitar image by adopting a template matching algorithm so as to judge whether a part of the to-be-detected guitar is installed and whether the installation position is qualified; recognizing characters on the to-be-detected guitar image by adopting ORC character recognition so as to judge whether the sequence of the characters on the to-be-detected guitar is qualified or not; and identifying the printing strokes on the to-be-detected guitar image by adopting machine learning MLP so as to judge whether the printing strokes on the to-be-detected guitar are incomplete or not. The guitar product detection method and device solve the problems that guitar products are detected manually in the prior art, so that the detection efficiency is low, and the omission ratio is high.

Description

technical field [0001] The present application relates to the technical field of guitar production, in particular, to a machine vision-based finished guitar inspection method and inspection system. Background technique [0002] The finished guitars produced by guitar manufacturers usually have dozens to hundreds of styles. Since each guitar is composed of many accessories, different styles of guitars use different accessories. Manual assembly will inevitably lead to errors. Therefore, it is necessary to inspect the guitar after the guitar is produced. The inspection content includes whether the accessories are installed, whether the installation position of the accessories is correct, and whether the characters and printing strokes on the guitar are correct, etc. In the related art, the detection of guitar products is still carried out manually, resulting in low detection efficiency and high missed detection rate. [0003] Aiming at the problems in the related art that the...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of this application is to provide a machine vision-based guitar product detection method and detection system to solve the problem in the related art that the detection of guitar products is still carried out manually, resulting in low detection efficiency and high missed detection rate.

Images