Image segmentation method

Abstract

The invention discloses an image segmentation method, and the method comprises the steps: (1), extracting a to-be-segmented image, deleting the background, and carrying out the binarization processing; (2), carrying out the corrosion operation of a binary image, and forming connected regions; (3), carrying out the expansion operation of each connected region, and extracting edge curves; (4), taking a connection line between intersection points between the edge curves as a segmentation line, and forming initial segmented regions; (5), extracting the edge curve of each initial segmented region,carrying out the resampling of the discrete points on the edge curves, searching the boundary points of the adjacent articles on the edge curves, connecting the intersection points through a certain rule, and forming a secondary segmentation line. The article images with the smaller adhesion degree are segmented through corrosion expansion, thereby enabling the adhered articles to be reduced. Theintersection points of the edge curves of the adhered articles are searched, and the rule is set for continuing to segment the images, thereby achieving the complete segmentation, and solving a problem that a conventional method cannot achieve the effective segmentation of the adhered articles.

Description

technical field [0001] The invention relates to an image processing method, in particular to an image segmentation method. Background technique [0002] Image segmentation is the technology and process of dividing an image into several specific regions with unique properties and proposing objects of interest. It is a key step from image processing to image analysis. The objects extracted after image segmentation can be used in image semantic recognition, image search and other fields. [0003] At present, the main image segmentation methods include threshold segmentation, region segmentation, edge segmentation, etc. The research objects mainly focus on the segmentation of items with regular shapes and not easy to stick and squeeze, such as mechanical parts, fresh fruits, rice, etc. For example, Chinese patent CN101556693 discloses a watershed SAR image segmentation method for threshold method marker extraction, including the following steps: (1) Gaussian low-pass filtering...

AI Technical Summary

Problems solved by technology

[0004] However, there are relatively few studies on the segmentation of some irregular and deformable object samples, such as soft and deformable dried fruits such as raisins.

The shape and size of each of these samples are different, and the color is the same, and there will be mutual adhesion and extrusion deformation between two adjacent samples, which increases the difficulty of segmentation

Images