Semi-automatic image cutting method based on nuclear transfer

An image segmentation and kernel transfer technology, applied in the field of image processing, can solve problems such as inability to maintain the consistency of superpixel data points, unclear edges of objects of interest, and unlearned image data, etc., to achieve consistency and false match rates Low, the effect of improving accuracy

CN102663757AInactive Publication Date: 2012-09-12XIDIAN UNIV
2 Cites 31 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2012-09-12
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a semi-automatic image cutting method based on nuclear transfer, which mainly solves the problems that the existing interactive image cutting method can not keep data consistency, the cutting result is not stable, and edges are not clear. The method is realized through the following steps: inputting an image to be cut, obtaining a superpixel set of the input image through a mean shift method, calculating a superpixel color column diagram feature set, building a similarity matrix W through a Bhattacharyya coefficient formula, performing interactive operation on the precut image by a user to obtain a seed superpixel set, building a must-link constrain set M and a cannot-link constrain set C, transferring constrain information M and C to the whole nuclear space through a nuclear transfer method, so as to obtain a nuclear matrix R, clustering the nuclear matrix R through a k mean clustering method, so as to obtain a clustering mark vector, and outputting and displaying a cutting result. The method has the advantages of good data consistency, stable cutting result, simplicity of operation and clear edges, and can be applied to image retrieval, the technology of converting 2D to 3D, target detection and tracking, and medical image analysis.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of image processing, in particular to a semi-automatic image segmentation method based on kernel transfer, which can be used for target extraction and target detection. Background technique

[0002] Image segmentation is one of the most basic problems in computer vision and digital image processing, and it is the basis for further analysis, recognition, tracking and understanding of images. Image segmentation divides the pixels in the image into different subsets according to different visual features or semantics. Specifically, image segmentation is the process of assigning a label to each pixel in the image, the purpose of which is to make pixels with similar visual features or the same semantics have the same label. At the same time, it is of great significance to study image segmentation, which can be widely used in many fields such as semi-automatic image retrieval, video conferencing, 2D to 3D technology, targe...

Examples

Embodiment Construction

[0030] The specific realization and effect of the present invention are described in further detail below with reference to the accompanying drawings:

[0031] refer to figure 1 , the implementation steps of the present invention are as follows:

[0032] Step 1. Input an image and pre-segment it into a set S of superpixels.

[0033] First, input an image, and use the mean shift algorithm to pre-segment the image to obtain the label of each pixel;

[0034] Then, a set of pixels with the same label is called a superpixel, and a set of n superpixels is obtained, which are respectively identified as s i , i=1, 2, ..., n, to obtain the superpixel set of the pre-segmented image

[0035] where s i is the i-th region obtained by pre-segmenting the input image by the mean shift method, and n represents the number of superpixels contained in S.

[0036] The mean shift method can be found in literature: D. Comaniciu, P. Meer, "Mean shift: a robust approach toward feature space analy...