Online visual inspection device and method for surface dirt of group origin eggs

Abstract

The invention discloses an online visual inspection device and an online visual inspection method for surface dirt of group origin eggs, relating to the technical field of egg processing and grading. The method comprises the following steps: (1) acquiring an egg image; (2) preprocessing the egg image; (3) extracting the color characteristic parameters, and dividing the eggs into green-shell eggs and white-shell eggs according to the shell color; (4) extracting the egg surface dirt characteristic parameters comprising the ratio of the dirt area to the whole egg area and the number of dirt blocks; (5) finding the characteristic parameter range for distinguishing the clean eggs and dirty eggs; and (6) establishing an automatic identification model, and discriminating the dirt on the eggs. Detection is performed by utilizing machine vision, and the method has the non-critical property on the application environment and has good popularization and application prospects; and moreover, high efficiency and high intelligence are realized, and nondestructive testing can be realized.

Description

technical field [0001] The invention relates to the technical field of poultry egg processing and grading, in particular to an online visual detection device and method for poultry egg surface dirt in a group production area. [0002] Specifically, the present invention uses machine vision technology to collect color images of poultry eggs, divides the dynamic image of poultry egg groups into individual poultry egg images, and performs image preprocessing on them, then extracts color feature parameters, and divides poultry eggs according to shell color Divided into green-shell eggs and white-shell eggs, and then extract the ratio of the dirty area to the whole egg area and the number of dirty blocks in the image as characteristic parameters, find out the characteristic parameter range of clean eggs and dirty eggs, and establish an automatic recognition model , so as to achieve the purpose of detecting and grading the surface dirt of poultry eggs in the group origin. Backgrou...

AI Technical Summary

Problems solved by technology

[0006] 1. The research on the surface dirt of poultry eggs is mainly static, and it is difficult to realize batch detection;

[0007] 2. The detection of poultry egg surface dirt is greatly affected by the color of poultry egg shells, so only eggs with one shell color are often selected for research;

[0008] 3. The surface dirt of poultry eggs is divided into dirty spots, blood spots, etc., which reduces the accuracy of detection, and in practical applications, it is generally necessary to divide poultry eggs into clean poultry eggs or dirty poultry eggs.

Images