Citrus surface defect detecting method based on surface fitting correction, and computer program

Abstract

The invention belongs to the technical field of computer software and discloses a citrus surface defect detecting method based on surface fitting correction and a computer program. The method comprises the steps of image acquisition, background removal, mask extraction, citrus image extraction, surface fitting, abnormal point removal, surface fitting once again, image correction, and defect extraction. The method and the computer program in the invention aim at the effects of fruit shape, illumination, and the like on the gray scale of a defect region on the irregular globoid citrus surface and the complex situations of being intersected with brightness of a normal region and being discontinuous, fully consider the change of surface shape of the fruit and adaptively complete image gray scale regression and correction; and the citrus surface defects can be detected by adopting a global threshold segmentation method. The method in the invention is simple and practical, and has application prospects in machine vision detection of surface defects of citrus and other globoid fruits.

Description

technical field [0001] The invention belongs to the technical field of computer software, and in particular relates to a citrus surface defect detection method based on surface fitting correction and a computer program. Background technique [0002] Surface defects are one of the decisive factors for consumers to choose citrus, and also one of the decisive factors for the market value of citrus. Therefore, surface defects are an important indicator for citrus quality inspection and grading. Machine vision is a potential means to quickly detect surface defects of citrus. However, due to the large intersection of the gray level of the defect area and the gray level of the normal area of ​​the fruit surface, the adaptive segmentation and detection of the surface defect area of ​​​​citrus is still difficult. [0003] At present, the existing technologies commonly used in the industry are as follows: [0004] J.Blasco et al. used various technologies and equipments such as fusi...

AI Technical Summary

Problems solved by technology

[0005] In summary, the problems in the prior art are: Citrus fruits are irregular spheroids or ovoids, with different sizes and shapes. The middle gray level of the image is high, and the edge is low. There is a large intersection with the gray level of the normal area of ​​​​the fruit surface, which makes it difficult to detect fruit surface defects with machine vision

Images