Image segmentation method and system

An image segmentation and image technology, which is applied in the field of image processing, can solve problems such as inaccurate image segmentation, and achieve the effects of improving efficiency and accuracy, improving accuracy, and high computing efficiency and accuracy

Active Publication Date: 2017-11-07
福建乐基科技有限公司
View PDF9 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] The technical problem to be solved by the present invention is to provide an image segmentation method and its system, which can solve the problem of inaccurate image segmentation with complex background information and weak boundaries in the prior art

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
  • Image segmentation method and system
  • Image segmentation method and system
  • Image segmentation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0093] Please refer to figure 1 , Embodiment 1 of the present invention is: an image segmentation method, said method is based on salient region detection and level set, comprising the following steps:

[0094] S1: Detect the salient area of ​​the target image, and obtain the initialization boundary curve of the target area; the target area in this embodiment is the salient area in the target image, and the target area is also the target to be segmented.

[0095] S2: Generate a new energy function according to the energy function of the LIF model and the energy function of the DRLSE model;

[0096] S3: Evolving the initialization boundary curve according to the new energy function and a preset number of iterations to obtain an evolved boundary curve;

[0097] S4: Carry out image segmentation according to the evolved boundary curve.

[0098] In step S1, the salient region is the pixel that attracts the most visual attention in the picture, and the criteria for the salient det...

Embodiment 2

[0181] This embodiment is a specific application scenario of the foregoing embodiments.

[0182]First, set the parameters of the new level set evolution equation, η=0.1, ρ=0.9, time step Δt=1, μ=0.2, λ=5, α=1.5, and the number of iterations is 11. Obtain the saliency map M of the target image according to the cellular automaton t+1 , which is the saliency region, and find the saliency map M t+1 mean M mean , using the mean value as a threshold value, divide the target image into two parts according to the threshold value, and use the divided curve as the initial contour curve, that is, initialize the boundary curve. According to the eleventh formula and the sixteenth formula, calculate m 1 and m 2 , L(φ) and A(φ), and then evolve the level set function every Δt=1s according to the new level set evolution equation and its finite difference equation. If the number of evolutions does not meet the number of iterations, continue to evolve the curve until the number of iteratio...

Embodiment 3

[0184] Please refer to image 3 , this embodiment is an image segmentation system corresponding to the above-mentioned embodiments, including:

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 an image segmentation method and system. The image segmentation method comprises the steps of detecting a salient region of a target image to obtain an initialized boundary curve of a target region; generating a new energy functional according to an energy functional of an LIF (Local Image Fitting) model and an energy function of a DRLSE (Distance Regularized Level Set Evolution) model; performing evolution on the initialized boundary curve according to the new energy functional and a preset number of iterations to acquire an evolved boundary curve; and carrying out image segmentation according to the evolved boundary curve. According to the invention, the initial curve is enabled to the started near the edge of the target region through performing saliency detection, so that the time of evolution is greatly saved, and the segmentation accuracy is improved; and image with complicated background information and weak boundaries can be effectively segmented according to a level set method combining local information and gradient information.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image segmentation method and system thereof. Background technique [0002] In the research and application of images, people are often interested in some parts of the image, and these interested parts generally correspond to specific and special areas in the image (can correspond to a single area or multiple areas), Call it the object or the foreground; while the other part is called the background of the image. In order to identify and analyze the target, it is necessary to isolate the target from an image, which is the problem to be studied in image segmentation. Image segmentation is the technology and process of dividing an image into several specific regions with unique properties and proposing objects of interest. Image segmentation is a crucial preprocessing for image recognition and computer vision. Correct recognition is impossible without correct...

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
IPC IPC(8): G06T7/11G06T7/136G06T7/194
CPCG06T7/11G06T7/136G06T7/194
Inventor 叶锋李婉茹陈家祯郑子华许力林晖洪斯婷
Owner 福建乐基科技有限公司
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