A two-dimensional shape retrieval method and system based on contour feature point matching

Abstract

The present invention provides a two-dimensional shape retrieval method and system based on contour feature point matching, which can realize the following steps: extract the contour feature points of the target two-dimensional image, and use the extracted contour feature points to construct two feature point sets V 1 and V 2 ; respectively based on the above feature point set V 1 and V 2 , and through the use of edge compatibility matrix and area compatibility matrix, obtain the similarity between the target two-dimensional image and each two-dimensional image in the data set used for shape retrieval; compare the obtained similarities , to obtain the two-dimensional image in the data set corresponding to the maximum similarity, and the obtained two-dimensional image in the data set is the retrieval result. The invention is used to realize the optimization of the two-dimensional shape retrieval problem.

Description

technical field [0001] The invention relates to the fields of computer vision and pattern recognition, in particular to a two-dimensional shape retrieval method and system based on contour feature point matching. Background technique [0002] With the improvement of informatization in today's world, digital images are widely used in many fields. From the perspective of the visual features of the image, the shape feature information of the image is a kind of advanced visual information, which contains rich semantic information of the image, and is one of the most important features of the image. By studying the shape features of images, it can be applied to two-dimensional shape retrieval. [0003] The 2D shape retrieval process is the process of identifying images in a large database that are similar to the image of the shape to be retrieved. 2D shape retrieval has become a research hotspot in the fields of computer vision and pattern recognition. [0004] The key point o...

AI Technical Summary

Problems solved by technology

Among them, the early contour-based two-dimensional shape representation methods mainly used features such as area and roundness as two-dimensional shape representations, but the area and roundness of different shapes may also be similar or equal, resulting in the robustness of two-dimensional shape retrieval. Relatively poor performance, resulting in unsatisfactory application effect

Later, in order to overcome the above problems, Wang et al. proposed the height function method (height function), which is to take points on the image contour to form a sample set, and the orderly arrangement of the tangent distances from the points on the sample set to all other sample points Constitute a vector, and the vector formed by all sample points forms a matrix as a two-dimensional shape representation. Although the shape representation has certain robustness, it requires the order of the contour sample points on the contour, which increases the construction of the shape representation. the complexity

Images