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

A Similar Object Segmentation Method Based on Weighted Similar Active Contour Model

An active contour model and target segmentation technology, applied in image analysis, image data processing, instruments, etc., can solve the problem of inaccurate image segmentation results, achieve ideal segmentation effect, fast processing speed, and remove background noise.

Inactive Publication Date: 2017-09-08
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to realize the automatic segmentation of similar targets in natural scenes, and solve the problem of inaccurate image segmentation results caused by noise interference and complex background in existing target segmentation methods, and overcome the need for target traits in existing methods Due to the limitation of prior information and training set, an unsupervised similar object segmentation method based on the weight group similar active contour model is proposed, which can realize the automatic segmentation of multiple similar objects in natural scenes, improve the accuracy of object segmentation, and be able to preserve It plays an important role in the fields of image processing and pattern recognition by removing noise interference while removing target details and shapes.

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
  • A Similar Object Segmentation Method Based on Weighted Similar Active Contour Model
  • A Similar Object Segmentation Method Based on Weighted Similar Active Contour Model
  • A Similar Object Segmentation Method Based on Weighted Similar Active Contour Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0046] See figure 1 , a similar object segmentation method based on the weight group similar active contour model, including:

[0047] Step 1, input N images containing similar objects.

[0048] The input N images (N greater than or equal to 2) can be color images or grayscale images, and each image contains the target to be segmented. Also, similar objects mean two objects having similar shapes.

[0049] Step 2, using the saliency detection algorithm to extract the saliency regions of the N images.

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 the fields of image processing, pattern recognition and computer application, in particular to a method for segmenting similar objects based on weight group similar active contour models. The present invention extracts a plurality of salient regions that people are interested in from a source image group containing a plurality of similar targets; estimates the similarity and corresponding weight of each salient region with the common traits of a plurality of similar targets; The salient area establishes an active contour model and energy function based on similar weight groups; finally, a stable segmentation result is obtained by optimizing the energy function, thereby achieving similar target segmentation in multiple images. In the segmentation process, the present invention can remove the influence of noise while retaining the target detail features and group similarity characteristics, and has the advantages of accurate segmentation results, fast processing speed, little influence by noise and strong robustness, and can be applied to similar object segmentation, Vehicle detection and 3D multi-target extraction systems.

Description

technical field [0001] The invention relates to the fields of image processing, pattern recognition and computer application, in particular to a method for segmenting similar objects based on weight group similar active contour models. Background technique [0002] Image object segmentation is a very challenging task in the field of image processing and computer vision, and has a wide range of applications in many fields. For example, in the medical field, MR image segmentation of human organs; in the military field, infrared detection target imaging and terrain detection segmentation; in the urban traffic field, license plate segmentation, license plate number recognition, and pedestrian detection segmentation; in the intelligent Internet field Among them, face recognition and segmentation, gesture and posture segmentation, etc. In addition, in image segmentation, the segmentation technology of similar targets in multiple images also has important applications, such as aut...

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): G06T7/149
Inventor 赵清杰吕鹏
Owner BEIJING INSTITUTE OF TECHNOLOGYGY