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

Image Smoothing Method Based on Salient Structure Metric Model

An image smoothing and structure tensor technology, applied in the field of image processing

Inactive Publication Date: 2016-08-24
BEIJING INSTITUTE OF TECHNOLOGYGY +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the traditional image smoothing method is difficult to maintain the salient visual structure in the smoothing process independently of contrast and scale, and at the same time ensure high efficiency and strong robustness, and propose an image based on the salient structure metric model smoothing method

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 Smoothing Method Based on Salient Structure Metric Model
  • Image Smoothing Method Based on Salient Structure Metric Model
  • Image Smoothing Method Based on Salient Structure Metric Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The implementation of the method of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0045] figure 1 is a flow chart of the method of the present invention. like figure 1 Shown, the present invention mainly is divided into three parts, 9 steps:

[0046] 1. Based on the conclusion in cognitive psychology that periodically repeated textures can inhibit human cognition, while structures with better directionality can enhance cognition, a saliency structure measurement model for images is proposed.

[0047] Step 1: Input the source image to be filtered. According to the input image, first calculate the metric M of the salient structure in it p , including Step 2, Step 3, and Step 4.

[0048] The law of human visual cognition in cognitive psychology shows that [1] : "Human understanding of structural information is cognitively driven, motivated by visual events, salience in change and direction, and possibly inhib...

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 an image smoothing method based on a significant structure metric model. The method includes the following steps that on the basis of the non-periodic and partial directivity characteristics of an edge structure of visual salience, a self-adaptation image significant structure metric is defined; on the basis of the metric model, an optimization strategy is put forward for image limit point distribution estimation; according to obtained limit points, an anisotropic shock filter algorithm is put forward to calculate a mid-value envelope, a smoothed basic image is generated, and image smoothing is finished. By means of the method, the image smoothing effect that intensity contrast is irrelevant to a scale is achieved, a significant visual structure in the image is completely maintained and even enhanced, and the effect of the method is remarkably improved compared with that of the latest international smoothing algorithm.

Description

Technical field: [0001] The invention relates to an image smoothing method, in particular to an image smoothing method based on a salient structure metric model, belonging to the field of image processing. Background technique [0002] With the continuous development of image filtering technology, various new image smoothing methods provide very useful help for various aspects of image processing, such as digital entertainment, detection and recognition, editing and synthesis. Therefore, continuously improving the performance of image smoothing methods and expanding their application fields have been extensively studied by foreign scholars. [0003] Traditional image smoothing methods lack the guidance of cognitive theory, so it is difficult to maintain a significant visual structure in a contrast-independent and scale-independent manner during the smoothing process, while ensuring high-efficiency and robust algorithm performance. In response to the above problems, accordin...

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): G06T5/00
Inventor 黄华臧彧张磊
Owner BEIJING INSTITUTE OF TECHNOLOGYGY