Unlock instant, AI-driven research and patent intelligence for your innovation.

An Interactive Intelligent Image Segmentation Method

An intelligent image and interactive technology, applied in the field of interactive intelligent image segmentation, can solve the problem of lack of adaptive selection features

Active Publication Date: 2015-11-25
浙江海宁经编产业园区开发有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, many scholars have also proposed many image segmentation methods based on human-computer interaction, but most of these methods lack the ability to adaptively select features

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
  • An Interactive Intelligent Image Segmentation Method
  • An Interactive Intelligent Image Segmentation Method
  • An Interactive Intelligent Image Segmentation Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further described below in conjunction with accompanying drawing.

[0037] The inventive method specifically comprises the following steps:

[0038] Step (1) Determine and calculate the candidate features of each pixel of the image: select the color value of the pixel and the diffusionmap as the candidate features, where the calculation of the diffusionmap is as follows, which is described in Document 1:

[0039] note image First The brightness value of a pixel is , defining the image The incidence matrix :

[0040]

[0041] in Used to control how much the correlation value between two pixels is attenuated relative to their distance. right normalized to get :

[0042]

[0043] in is a diagonal matrix with elements on the diagonal . If the image has pixels, then Is an matrix, which has eigenvalues , where the maximum eigenvalue is 1. Let's assume that the eigenvalues ​​are sorted: . remember is th...

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 interactive intelligent image partition method. Existing methods mostly lack self-adaption selection character functions. The method comprises the following steps of firstly confirming optional characters of pixels of an image to be calculated; then conducting man-machine interaction, achieving classification of the all pixels of the image, and utilizing a classification result to conduct character optimization; finally obtaining a multi-channel image which is formed by combining of a plurality of characters, serving the image as input, and executing a smooth iteration algorithm; and after fully iteration, obtaining a subsection constant image. The method only needs a little man-machine interaction and enables a user to obtain a wanted partition result.

Description

technical field [0001] The invention belongs to the technical fields of image editing and machine vision, and relates to an interactive intelligent image segmentation method. Background technique [0002] Image segmentation is the basis for many image editing operations and computer vision tasks. At present, most of the research on image segmentation focuses on fully automatic image segmentation methods, but in fact, fully automatic image segmentation is an ill-posed problem. Therefore, many scholars have also proposed many image segmentation methods based on human-computer interaction, but most of these methods lack the ability to adaptively select features. Contents of the invention [0003] The purpose of the present invention is to provide a globally optimized interactive image segmentation method capable of adaptively selecting features. [0004] The concrete steps of the inventive method are: [0005] Step (1) Determine and calculate the candidate features of each...

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 Patents(China)
IPC IPC(8): G06F3/0484G06T7/00
Inventor 金剑秋李丹王勋杨柏林江照意
Owner 浙江海宁经编产业园区开发有限公司