Battery silk-screen quality detection method combining block template matching with morphological processing

Abstract

The invention discloses a battery silk-screen quality detection method combining block template matching with morphological processing. The method comprises the following steps: establishing a character part template based on a morphological template matching method; extracting a battery area by applying threshold segmentation and morphological corrosion; determining an inclination angle in a mode of solving a minimum circumscribed rectangle of a battery area, searching the minimum circumscribed rectangle as a final result by adopting an equal interval rotation search algorithm, and performing reverse rotation on a deflection angle by utilizing affine transformation to perform battery correction and cutting; identifying the defects of the illustration part by adopting a difference image method; sequentially shielding picture insertion, character segmentation, character extraction and correction, character recombination and to-be-detected character skeleton extraction, identifying character part defects by adopting a difference image method, and carrying out defect detection by adopting suspicious area translation difference detection and suspicious area micro-rotation difference detection. The method is high in accuracy and low in cost, and has a certain degree of promotion effect in the field of domestic battery screen printing quality automatic detection.

Description

technical field [0001] The invention belongs to the technical field of machine vision automatic surface detection, and in particular relates to a method for detecting the quality of battery silk screen printing by block template matching combined with morphological processing. Background technique [0002] The content of battery screen printing includes illustrations, Chinese, English, Korean, numbers and barcodes and other complex patterns, covering a large number of important information including origin, model, specification, warnings and contraindications. The above content is generally printed by screen printing. The surface of the battery, so the quality of silk screen printing is extremely important. Due to the influence of equipment, technology, personnel and other factors, silk screen printing defects will be caused. The main defects are defects, skew, blur, ghosting, dirt, color difference and abnormal position. The traditional appearance inspection method mainly ...

AI Technical Summary

Problems solved by technology

[0004] 1) The algorithm is too complicated and the detection takes a long time, so it is not suitable for the factory to apply to the production line for detection;

[0005] 2) The characteristics of the application object are relatively single, and the versatility of the method and the ability to detect complex objects need to be strengthened

Good results cannot be achieved by using previous classical methods

Images