Image segmentation method and system based on frequency-tuned global saliency and deep learning

A deep learning and image segmentation technology, applied in the field of image processing and computer vision, it can solve the problems of being susceptible to noise interference and greatly affected by image segmentation results, achieve good enhancement effect, maintain texture detail information, and overcome susceptibility to noise. Effects and the effect of image distortion

Active Publication Date: 2021-02-12
BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the saliency enhancement obtained by these methods is easily disturbed by noise, and can only be saliency enhanced for simple images. Once faced with complex images, large-scale distortion will occur, which has a great impact on the results of image segmentation.

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
  • Image segmentation method and system based on frequency-tuned global saliency and deep learning
  • Image segmentation method and system based on frequency-tuned global saliency and deep learning
  • Image segmentation method and system based on frequency-tuned global saliency and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0034] The following describes the image segmentation method and system based on frequency-tuned global saliency and deep learning according to the embodiments of the present invention with reference to the accompanying drawings. First, the frequency-tuned global saliency and deep learning based on the embodiments of the present invention will be described with reference to the accompanying drawings. image segmentation method.

[0035] figure 1 It is a flowchart of an image segmentation method based on frequency-tuned global sal...

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 present invention provides an image segmentation method and system based on frequency tuning global saliency and deep learning, wherein the method includes the following steps: reading a target image, and smoothing the target image through Gaussian kernel filtering to obtain the smoothed image Saliency; establish a saliency enhancement formula according to the saliency of the smooth image, and enhance the target image according to the saliency enhancement formula; expand the target image after the saliency enhancement, and use the wide residual pyramid pooling The network deep learning method segments the augmented image to obtain the segmentation result. The image saliency enhancement obtained by this method has a more eye-catching visual effect, and the effect of image processing and analysis is also greatly improved. The edge of the segmentation area is clear, thereby effectively distinguishing different objects in the image.

Description

technical field [0001] The invention relates to the technical fields of image processing and computer vision, in particular to an image segmentation method and system based on frequency tuning global saliency and deep learning. Background technique [0002] Image segmentation is a crucial part in the field of image recognition and computer vision. The basis for segmentation includes the brightness and color of pixels in the image. When the segmentation is automatically processed by the computer, various difficulties will be encountered, such as uneven illumination, The influence of noise, the existence of unclear parts in the image, and shadows, etc., these difficulties often cause segmentation errors. Therefore, image segmentation is one of the technologies that need to be continuously studied. People hope to introduce some artificial knowledge-oriented and artificial intelligence methods to correct some errors in segmentation. This is a promising method, but at the same t...

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 & AuthorityPatents(China)
IPC IPC(8): G06K9/34G06K9/32G06N3/04
CPCG06V10/25G06V10/267G06N3/045
Inventor王瑜马泽源
OwnerBEIJING TECHNOLOGY AND BUSINESS UNIVERSITY