An Image Segmentation Method of Convex Polygon Contour Combining Concave Points and Concave Edges

Abstract

The invention discloses an image segmentation method of a convex polygonal contour combining concave points and concave edges. First, the inner and outer contours of an object are detected on a preprocessed picture; then, the concave points on the outer contour are found by means of vector cross multiplication; and then Find the convex hull of the outer contour. The shortest distance from each point on the outer contour to the edge of the convex hull is defined as the convex defect of the point. The adjacent points whose convex defect value exceeds the set threshold form a concave edge, thus obtaining several Concave edge; then group the concave edge and the concave point, and divide the concave points on the same concave edge into the same group; then traverse the concave point sequence, and find matching points in the concave point sequence under the remaining concave edge and the inner contour; according to the matching Contour segmentation is performed on good concave point pairs to obtain the final multiple convex contours. The image segmentation method of the convex polygon outline of the present invention has the advantages of simple principle and fast segmentation rate.

Description

technical field [0001] The invention relates to the field of image segmentation of a two-dimensional convex polygonal object outline, in particular to an image segmentation method of a convex polygonal outline combining concave points and concave edges. Background technique [0002] In the fields of biology and medicine, there are often multiple targets close together in images of similar shapes such as cells and colonies, which brings great difficulties to the analysis of image information. To solve this problem, the contour segmentation technology in the field of image processing is very effective. The contour segmentation technology based on concave point matching is a contour segmentation technology that finds concave points, matches concave points, and separates the contour from concave point pairs. It has the advantages of high operating efficiency, wide application scenarios, good segmentation effect, and simple operation. The contour segmentation technology based on...

AI Technical Summary

Problems solved by technology

The method of directly matching pairs of concave points in the sequence of concave points does not work well for complex situations where multiple objects are close together to form an inner contour, and does not consider whether the concave points are under the same concave edge, and it is easy to combine two objects on the same concave edge. Dimples form matching pairs causing segmentation errors

Images