Image contour characteristic extraction method and device

Abstract

The invention provides an image contour characteristic extraction method and device, and the method comprises the steps: obtaining absolute values of the gray value differences of all pixels of an input image and the peripheral adjacent pixels in at least two directions; calculating the mean gray scale difference of all pixels; determining a pixel set of contour characteristic points of the input image according to a preset rule, thereby obtaining contour characteristic information of the input image. The method can extract the layered feature information of the input image, prevents the binarization processing of the pixels from causing the leakage of characteristic information of the pixels in an extraction process of the contour information of the image. The method for extracting the contour characteristic information based on the surrounding mean gray scale difference of the pixels can effectively solve a problem of the extraction leakage of the contour characteristic information of various types of images and more complex images with more layers, overcomes a difficulty that a conventional image contour characteristic information extraction method is liable to lose the layered characteristic information of the image, and improves the description quality of the contour characteristic information.

Description

technical field [0001] The present invention relates to the technical field of image processing, and in particular, to a method for extracting contour features of an image, and a device for extracting contour features of an image. Background technique [0002] Accurate extraction of image contour features is the need to improve the quality of image recognition feature information in the field of image recognition. How to complete and accurately perform image edge detection is one of the difficult problems in image edge detection. Its solution is of great significance to our high-level feature description, identification and understanding. At the same time, because edge detection has very important application value in many aspects, people have been devoted to researching and solving the problem of how to construct edge detection operators with good properties. [0003] The contour of the image exists both in the irregular structure and unstable edges of the image, and also ...

AI Technical Summary

Problems solved by technology

[0005] 1. Although the contour detection algorithm based on differential operation can detect the contour feature information of the edge image, the threshold selection is based on the global average gray level, which only reflects the average degree of brightness or color depth of the image, and cannot Fully reflect the hierarchical feature information of the image; although the threshold selection of some methods is based on the gray average value of the local area, it still cannot fully reflect the hierarchical feature information of the image

[0006] 2. Using the average value of any gray level will definitely affect the binarization processing of pixels with other gray levels, resulting in the omission of pixel feature information

[0007] The traditional image extraction contour feature information method will lose the hierarchical feature information of the image in the process of image binarization

When there is a small difference in the gray value of the image itself but a large difference in the gray value of other images and a large number of gray levels, it is difficult for the traditional processing method to find out the target pixel of the image that the user is interested in and the contour formed by it. feature

Images