Graph model based saliency target detection method

A technology of object detection and graph model, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as inconsistency of saliency values, inability to fully highlight saliency objects, and neglect of superpixel correlations, etc.

Active Publication Date: 2016-09-28
重庆诺思达医疗器械有限公司
View PDF6 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method ignores the correlation between superpixels, which can easily lead to inability to

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
  • Graph model based saliency target detection method
  • Graph model based saliency target detection method
  • Graph model based saliency target detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0064] The implementation is as follows:

[0065] Step 1: Image smoothing based on MRF global potential energy minimization

[0066] a) Given an input image I m×n , m, n represent the length and width of the image, set the number of iterations N 1 ;

[0067] b) For image I m×n Each pixel of I ij , record the gray value of the pixel as P ij , i∈[1,m], j∈[1,n], the eight neighbors of the pixel are regarded as a group x ij . use Q i'j' represents the group x ij The gray value of each pixel in , where the symbols used are i', j' to indicate that the values ​​of i', j' cannot be equal to i, j at the same time, because the group x ij does not include pixel I ij .

[0068] c) Record each group x ij The gray values ​​corresponding to the 8 pixels in are Q 1 ,Q 2 ...Q 8 , calculate the group potential energy Z(k) generated by each pixel in turn:

[0069] ...

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 relates to a graph model based saliency target detection method. First, the method includes improving the clustering effect of an HAIC (Hexagon Arrangement Iteration Clustering) algorithm by using MRF overall potential energy minimization image smoothing; dynamically setting a threshold value so as to enable areas similar in color while communicating with each other in space to be divided into the same area by utilizing an improvement-based graph model for image division; combining areas with rich borders and improving excess division of image borders by using an attractor propagation clustering method. Second, the method includes optimizing a saliency graph by adopting a manifold ranking algorithm according to a manifold structure among super pixels so as to highlight the whole saliency area in the final saliency graph further.

Description

technical field [0001] The invention belongs to computer data image processing, in particular to a method for detecting a salient object based on a graph model. Background technique [0002] With the explosive growth of image data, how to quickly and effectively interpret image content has become an increasingly important part of image processing. As an important preprocessing step in the field of computer vision to reduce computational complexity, salient object detection can quickly Lock the target area in the image, realize the efficient analysis of the image content, help the computer reasonably allocate the resources required for image processing, and at the same time deepen our cognition and understanding of human visual characteristics. [0003] Existing salient object detection methods fall into two categories: one is bottom-up object-driven models, which are usually based on low-level visual information and thus can effectively detect detailed information rather tha...

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): G06T7/00
CPCG06T2207/20182G06F18/23
Inventor 李映崔凡马力
Owner 重庆诺思达医疗器械有限公司
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