Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Apple image fusion method based on scale-invariant feature transformation

A scale-invariant feature and image fusion technology, which is applied in image enhancement, image analysis, image data processing, etc., can solve the problems of inconspicuous subsurface defects and unclear fruit surfaces in fused images, achieving high definition and eliminating artifacts. Gibbs phenomenon, information-rich effect

Inactive Publication Date: 2017-06-27
JIANGNAN UNIV
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art, and propose an apple image fusion method with scale-invariant feature transformation, to solve the fuzzy fruit surface and subsurface defects of the fusion image obtained by the existing infrared and visible light apple image fusion technology non-obvious problem

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
  • Apple image fusion method based on scale-invariant feature transformation
  • Apple image fusion method based on scale-invariant feature transformation
  • Apple image fusion method based on scale-invariant feature transformation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The following two embodiments of the present invention will be described in detail with reference to the accompanying drawings. This embodiment is performed on the premise of the technical solution of the present invention, such as figure 1 As shown, the detailed implementation and specific operation steps are as follows:

[0052] Step 1. Use the non-downsampled contourlet transform NSCT to decompose the to-be-fused visible and infrared apple image with a size of M×N (256×256) into low-frequency subband coefficients LC A (x, y) and LC B (x, y) and subband coefficients of different scales and directions with Where LC A (x, y) and LC B (x, y) represent the values ​​at the low-frequency subband (x, y) points of infrared image A and visible light image B, respectively, with Respectively represent the value at the high frequency subband (x, y) point in the t-th direction in the s-th scale of the infrared image A and the visible light image B. Among them, the NSCT filter selec...

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 fusion method based on scale-invariant feature transformation. The method is mainly used for realizing apple quality nondestructive testing. The method comprises the implementation steps that (1) to-be-fused images are disintegrated into low-frequency sub-bands and high-frequency sub-bands by use of non-subsampled contourlet transformation (NSCT); (2) feature descriptors of the low-frequency sub-bands are found by use of scale-invariant feature transformation (SIFT), the position of each feature descriptor in each low-frequency sub-band is recorded, and the feature descriptors are utilized to construct a content matching degree indicator; (3) a hybrid fusion policy based on the content matching degree is utilized to fuse the low-frequency sub-bands, and a bigger absolute value taking fusion policy is utilized to realize fusion of high-frequency sub-band coefficients; and (4) a fusion image is generated by use of non-subsampled contourlet inverse transformation. Through the method, useful information of infrared and visible light apple images can be fully fused, source image details are effectively protected, and the visual effect is improved; compared with a traditional fusion method, the quality of the fusion image is greatly improved, and nondestructive quality testing of apples can be effectively carried out.

Description

Technical field [0001] The invention relates to an apple image fusion method based on scale-invariant feature transformation, which is a fusion method in the technical field of fruit quality non-destructive testing, and is widely used in fruit quality testing. Background technique [0002] Because the information contained in a single image is limited, it is often unable to meet practical applications. In order to obtain better information, image fusion technology was proposed in the 1970s. Image fusion is a technology in which images of the same scene collected by multiple sensors are processed by a fusion algorithm to synthesize an image. The fused image can effectively combine the advantages of multiple images to be fused, which is more suitable for humans. Visual perception. In recent years, image fusion has been widely used in military reconnaissance, medical diagnosis, and remote sensing. [0003] As a big country producing apples, my country is very important for efficien...

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 Applications(China)
IPC IPC(8): G06T7/00G06T7/33
CPCG06T7/0004G06T2207/30128
Inventor 罗晓清张战成王鹏飞董静王骏檀华廷
Owner JIANGNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com