Corner point detection method and apparatus
View Patent ↗A corner point detection method and apparatus, which may improve the efficiency of corner point detection is disclosed. The corner point detection method includes: obtaining a plurality of corner points of a target object in an image to be detected, where the plurality of corner points are corner points on a contour of a first object in the image to be detected, and the contour of the first object includes a contour of the target object; obtaining a region proportion corresponding to each of the plurality of corner points, where the region proportion is a proportion of a region of the first object in a predetermined region centered on the corner point; and determining a target corner point of the target object from the plurality of corner points based on the region proportion.
1 . A processor implemented corner point detection method, comprising:
obtaining a plurality of corner points of a target object in an image to be processed, wherein the plurality of corner points are corner points on a contour of a first object in the image to be processed, and the contour of the first object comprises a contour of the target object;
wherein the obtaining a plurality of corner points of a target object in an image to be processed comprises: obtaining the plurality of corner points in a region of interest in the image to be processed;
obtaining a region proportion for each of the plurality of corner points, wherein the region proportion is a proportion of a region of the first object in a predetermined region of the image to be processed, centered on the corner point; and
determining a target corner point of the target object from the plurality of corner points based on the region proportion;
wherein the determining a target corner point of the target obiect from the plurality of corner points based on the region proportion comprises:
obtaining at least one candidate corner point whose region proportion is greater than a predetermined value from the plurality of corner points; and
obtaining the target corner point from the at least one candidate corner point;
wherein the obtaining the target corner point from the at least one candidate corner point comprises:
determining there are a plurality of candidate corner points, and subsequently determining the target corner point based on a location relationship between each of the plurality of candidate corner points and a center point of the target object.
2 . The method according to claim 1 , wherein the determining the target corner point based on a location relationship between each of the plurality of candidate corner points and a center point of the target object comprises: determining, as the target corner point, a candidate corner point of the plurality of candidate corner points that is at a maximum vertical distance from a location of the center point of the target object.
3 . The method according to claim 1 , further comprising:
determining at least one region of interest in the image to be processed.
4 . The method according to claim 1 , wherein the obtaining a plurality of corner points of a target object in an image to be processed comprises: obtaining the contour of the first object in the region of interest to obtain a target contour, wherein the target contour comprises the contour of the target object;
and obtaining corner points on the target contour to obtain the plurality of corner points.
5 . The method according to claim 4 , wherein the obtaining corner points on the target contour to obtain the plurality of corner points comprises:
obtaining a polygon corresponding to the target contour by using a polygon approximation method; and
obtaining vertices of the polygon to obtain the plurality of corner points.
6 . The method according to claim 4 , wherein before obtaining the contour of the first object in the region of interest, the method further comprises: performing binarization on the image to be processed, to obtain a binary image of the image to be processed; and obtaining the contour of the first object based on an edge of the binary image.
7 . The method according to claim 1 , wherein the predetermined region is in the shape of a circle.
8 . The method according to claim 7 , wherein a radius of the circle is ten pixels.
9 . The method according to claim 1 , wherein the predetermined value is 0.6.
10 . The method according to claim 1 , wherein the target object is a tab.
11 . A corner point detection apparatus, comprising a processor and a memory, wherein the memory is configured to store a program, and the processor is configured to invoke the program from the memory and execute the program to perform a corner point detection method according to claim 1 .
12 . A non-transitory computer-readable storage medium, comprising a computer program that, when executed on a computer, causes the computer to perform a corner point detection method according to claim 1 .