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

Image guided filter-based color image fusion algorithm

A technology for guiding filters and color images, applied in the field of image processing, can solve problems such as increasing computational complexity

Active Publication Date: 2017-05-31
WUXI SIMVISION TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, compared with grayscale images, since color images contain more complex and rich information, to obtain accurate image processing results, it is necessary to increase the computational complexity and sacrifice the real-time performance of image processing algorithms.

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 guided filter-based color image fusion algorithm
  • Image guided filter-based color image fusion algorithm
  • Image guided filter-based color image fusion algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention is aimed at color image processing of RGB three channels. The principle of the three-channel color image processing method is based on a two-dimensional image, that is, a grayscale image processing method.

[0025] The establishment method of the two-dimensional image-guided filter is as follows:

[0026] The input signal of the two-dimensional image-guided filter is the guide image set R and the input image set I, and the output signal of the two-dimensional image-guided filter is:

[0027]

[0028] In formula (1), i represents an image pixel; is a fixed-size template window, for example, in a specific embodiment, it can be a 3×3 window; k is Pixels within, A k , B k is the minimum mean square error between the guide image R and the input image I, and its calculation methods are as follows:

[0029]

[0030]

[0031] In formula (2) and formula (3), μ k ,δ k Respectively is the boot image R in the window mean and variance within...

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 an image guided filter-based color image fusion algorithm. The algorithm comprises the following steps of performing calculation on a to-be-processed source color image by utilizing a saliency detection algorithm to obtain a saliency mapping image; establishing a three-dimensional image guided filter; outputting a guided-filtered image by the three-dimensional image guided filter; performing mean filtering on the to-be-processed source color image to obtain a mean-filtered image; performing difference operation on the source color image and the mean-filtered image to obtain a difference image; performing weighted mean filtering on the guided-filtered image and the mean-filtered image; performing weighted mean filtering on the guided-filtered image and the difference image; and superposing results of the last two steps to obtain a grayscale-level image. According to the algorithm, a main body part of the image can be more highlighted on the grayscale-level image obtained by final processing, and the change of an image structure feature capable of being perceived by human eyes can be more emphasized.

Description

technical field [0001] The invention relates to an image processing method, in particular to an image-guided filter-based color image fusion algorithm. Background technique [0002] Images are one of the direct sources for human beings to understand the world. At the same time, since the 1970s, as computers have been able to simulate and present colors in the objective world according to different color spaces, color images have become more and more important in the field of machine vision and image processing, and have become a research hotspot for scholars. [0003] However, compared with grayscale images, since color images contain more complex and rich information, to obtain accurate image processing results, it is necessary to increase the computational complexity and sacrifice the real-time performance of image processing algorithms. In order to maintain the image features in the color image fusion process without generating false features, while retaining the color i...

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): G06T5/50
CPCG06T5/50G06T2207/10024
Inventor 邹逸
Owner WUXI SIMVISION TECH CO LTD