Natural scene target contour extraction method and system based on bionics

A technology for target contour extraction and natural scenes, applied in instruments, character and pattern recognition, computer components, etc., can solve the problems of complex scenes, low accuracy of target contours, and many interference factors, so as to improve accuracy and robustness sexual effect

Pending Publication Date: 2021-03-09
常州码库数据科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, from the perspective of practical application effects, contour detection and extraction is still an open research topic, and it faces many difficulties in different application scenarios.
Especially for target contour extraction in natural scenes, due to the complex scene and many interference factors, the accuracy of target contour extraction is not high

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Natural scene target contour extraction method and system based on bionics
  • Natural scene target contour extraction method and system based on bionics
  • Natural scene target contour extraction method and system based on bionics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] Such as figure 1 As shown, a bionics-based natural scene object contour extraction method includes: obtaining the Gaussian gradient and gradient magnitude of the image; obtaining the outer area suppression amount of the image based on the gradient magnitude of the image; Outer zone suppression generates contour responses; contour responses at different suppression levels are binarized to obtain a preliminary binary edge map; based on the edge saliency and collinearity of visual preference, the preliminary binary edge map is calculated The prior contour probability of the edge contour; based on the prior contour probability, the Bayesian probability framework is used to calculate the posterior contour probability of the edge point belonging to the contour edge; based on the posterior contour probability, under a given threshold, the contour of the output image .

[0038] 1) Obtain the Gaussian gradient and gradient magnitude of the image

[0039] Let I(x,y) represent a...

Embodiment 2

[0087] Based on the bionics-based natural scene target contour extraction method described in Embodiment 1, this embodiment provides a bionics-based natural scene target contour extraction system, including:

[0088] The first module is used to obtain the Gaussian gradient and gradient magnitude of the image;

[0089] The second module is used to obtain the outer area suppression amount of the image based on the gradient magnitude of the image;

[0090] The third module is used to generate a contour response based on the gradient magnitude of the image and the amount of outer zone suppression;

[0091] The fourth module is used to perform binary processing on the contour responses under different suppression levels to obtain a preliminary binary edge map;

[0092] The fifth module is used to calculate the prior profile probability of the edge profile in the preliminary binary edge map;

[0093] The sixth module uses the Bayesian probability framework to calculate the posteri...

Embodiment 3

[0096] Based on the bionics-based natural scene object contour extraction method described in Embodiment 1, this embodiment provides a computer-readable storage medium, the computer-readable storage medium includes a stored computer program, wherein, in the computer program When run by the processor, the device where the storage medium is located is controlled to execute the bionics-based natural scene object contour extraction method described in Embodiment 1.

[0097] Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk st...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a natural scene target contour extraction method and system based on bionics, and belongs to the technical field of computer vision. The accuracy and robustness of target contour extraction in a natural scene are improved. The method comprises the steps of obtaining a Gaussian gradient and a gradient amplitude of an image; based on the gradient amplitude of the image, obtaining an outer area suppression amount of the image; generating a contour response based on the gradient amplitude of the image and the outer region suppression amount; respectively carrying out binarization processing on the contour responses under different suppression levels to obtain a preliminary binary edge graph; calculating the prior contour probability of the edge contour in the preliminary binary edge graph based on the edge significance and colinearity of the visual preference; based on the prior contour probability, adopting a Bayesian probability framework to calculate the posterior contour probability that the edge point belongs to the contour edge; and based on the posterior contour probability, outputting the contour of the image under a given threshold.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a bionics-based natural scene object contour extraction method and system. Background technique [0002] Object contour extraction is a hot issue in the field of computer vision, and has a very broad application prospect. So far, a large number of solutions to this problem have been proposed. Traditional detection algorithms integrate linear filtering and local directional analysis, such as methods based on image data and methods based on local energy of images. However, these methods do not differentiate edge types, such as texture edges or region boundaries. Some other studies consider the context information of image edges, such as methods based on anisotropic fusion and edge gray information. This type of method no longer pays attention to all the grayscale changes in the image, but selectively detects and enhances the region of interest. Examples incl...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/46G06K9/38G06K9/40G06K9/62
CPCG06V10/28G06V10/30G06V10/44G06F18/24155
Inventor 冯全桑强
Owner 常州码库数据科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap