Ghosting reflection removal method based on image gradient sparsity

An image gradient and sparsity technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of missing information and inapplicability, and achieve the effect of good comprehensive performance and shortened processing time.

Active Publication Date: 2019-07-05
HUNAN NORMAL UNIVERSITY
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above methods build models and construct algorithms with different emphases. While performing reflection separation, they retain some unrecognizable reflections to varying degrees and lose the information they need.
At the same time, such methods are not suitable for common double-layer ghost reflections

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
  • Ghosting reflection removal method based on image gradient sparsity
  • Ghosting reflection removal method based on image gradient sparsity
  • Ghosting reflection removal method based on image gradient sparsity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Such as figure 1 Shown is a schematic flow chart of the method of the present invention: the ghost reflection removal method based on image gradient sparsity provided by the present invention includes the following steps:

[0037] S1. Build a ghost reflection model;

[0038] In daily life, when shooting a scene through a layer of transparent glass, usually the captured picture has glass reflection, and there will be a problem of translation and attenuation of the second layer of reflection on the basis of the first layer of reflection; assuming the translation distance And the amount of attenuation is known, so the desired dereflection image can be obtained through optimization;

[0039] According to the uniqueness of this type of reflection, the following reflection model can be obtained

[0040]

[0041] where g∈R M×N , u∈R M×N , s ∈ R M×N , h represents a double-layer reflective convolution kernel. In the actual processing process, the above formula can be d...

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 ghosting reflection removal method based on image gradient sparsity. The ghosting reflection removal method comprises the following steps of constructing a ghosting reflection model; converting the ghosting reflection model into a ghosting reflection variation model; solving the ghosting reflection variation model; and outputting the model result in a picture mode to obtain a final image with ghosting reflection removed. According to the method, the image reflection is removed, meanwhile, the processing time of the algorithm can be shortened to a great extent, the detail information, such as the structure and the texture of the image, etc., is reserved as much as possible, and the better comprehensive performance is obtained.

Description

technical field [0001] The invention specifically relates to a ghost reflection removal method based on image gradient sparsity. Background technique [0002] The reflection ghost image is produced by the light of the object on the same side as the image sensor reflecting through the glass and entering the image sensor. It is common in daily life to shoot glass windows, and use a camera indoors to shoot outdoor scenes through the glass. From a physical point of view, when light passes from one medium to another, some light must be reflected. How to use the knowledge of mathematics and physics to describe this part of the reflected light in the reflection ghost image and separate the reflection image from the transmission image has become an urgent problem in the field of computer vision. [0003] Image restoration is a basic topic of image processing and computer vision, and a large number of researchers have conducted in-depth research on this issue. In the captured refle...

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): G06T5/00
CPCG06T2207/10004G06T5/73
Inventor 文有为熊求兴杨蕾
Owner HUNAN NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap