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

A Complete Salient Object Detection Method Using Contour Detection

A technology of contour detection and object detection, which is applied in the field of image recognition and can solve problems such as inability to fully highlight salient areas of images

Active Publication Date: 2021-08-24
STATE GRID LIAONING ELECTRIC POWER RES INST +3
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Current salient object detection methods partially based on background priors cannot fully highlight salient regions of images

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 Complete Salient Object Detection Method Using Contour Detection
  • A Complete Salient Object Detection Method Using Contour Detection
  • A Complete Salient Object Detection Method Using Contour Detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0059] Such as figure 1 As shown, a complete salient object detection method using contour detection includes the following steps:

[0060] Step 1. Segment the image with superpixel segmentation and build it into a graph pattern.

[0061] The subsequent steps are all based on the image of the graphic mode, the process of constructing the graphic mode: read the image data information, adaptively set the threshold to eliminate the noise contour, and construct the graphic mode.

[0062] The threshold formula for removing noise contours is:

[0063]

[0064] Among them, ξ is the threshold to eliminate the noise contour, ξ i is the gradient value of the i-th contour line in the image, and N is t...

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 a method for detecting a complete salient object using contour detection, which includes segmenting an image with a superpixel segmentation method and constructing it into a graphic pattern; obtaining a saliency map based on contour extraction; obtaining a binary image based on a background template. value segmentation map; based on the saliency map and the binary segmentation map, the final saliency map is obtained. The invention can not only further highlight the salient area of ​​the image, but also well suppress the background area, and can be applied to scenes such as image retrieval, image segmentation, image classification, and object recognition.

Description

technical field [0001] The invention relates to a method for detecting a complete salient object using contour detection, and belongs to the technical field of image recognition. Background technique [0002] With the development of smart devices and social networks, we are immersed in a large amount of digital media data. How to use limited time and energy to extract useful information from a large amount of data and prepare for subsequent processing has become an important issue. Just as the human visual system can only focus on the most salient bits of information in the scene we see, often only some of the salient objects in an image catch our attention. Saliency detection refers to the identification of the most attractive areas in an image. It has become a hot topic in recent years due to its wide application in the fields of image processing and computer vision, such as image retrieval, image segmentation, image classification and target recognition. research field....

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): G06K9/34G06K9/46G06K9/40
CPCG06V10/30G06V10/267G06V10/462
Inventor 刚毅凝杜红军赵永彬李巍金成明郝跃冬刘嘉华康睿
Owner STATE GRID LIAONING ELECTRIC POWER RES INST