Tile defect detection method and tile defect detection system

Abstract

The invention relates to a tile defect detection method and a tile defect detection system. The tile defect detection system comprises a camera device and a detection device; the detection device comprises a memory and a processor; the camera device is electrically connected to the detection device; the camera device is used for acquiring the image of an original tile sample set and then transmitting the image data into the memory of the detection device, and the processor extracts the image data from the memory, processes the image data, learns the image data, and finally identifies a detected tile. Because a defective tile learning sample is divided into a plurality of sub-samples and each sub-sample needs to include a defect pattern, the quantity of needed samples is greatly reduced, and the efficiency of detection is improved.

Description

technical field [0001] The invention relates to the technical field of ceramic tile detection, in particular to a method and system for detecting tile defects. Background technique [0002] In today's society, ceramic tiles are the most important material for building decoration, and high-grade ceramic tiles are often used in expensive and high-grade housing construction. However, since the beginning of the 21st century, the ceramic industry has generally been under pressure from rising costs, environmental protection, anti-dumping, etc., especially the homogenization of industry products, which has intensified the competition among various brands in the industry. In this case, ceramic tile companies are paying more and more attention to product creation and intelligent production to attract more merchants to conduct transactions. [0003] Now more and more intelligent systems are applied to the ceramic tile industry, such as automatic laying line technology, robotic glaze ...

AI Technical Summary

Problems solved by technology

At present, intelligent detection has been successfully applied to detect defects such as color difference and contour of tiles, but in the process of production and processing of tile patterns, it is easy to produce pattern contour deformation, loss, color material overflow, drawing lines, dripping ink, color difference, etc. Pattern defects, if relying on manual detection, are prone to fatigue, low efficiency, and high missed detection rate. Therefore, it is necessary to develop a new type of tile pattern defect detection system based on machine vision

[0005] In the existing ceramic tile defect identification methods, it is necessary to set a large number of samples for the detection system to learn and remember, and then the detection system can determine whether the detected tile is a defective tile. Thousands of copies, which undoubtedly brings great difficulties to machine learning

Images