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

Method for synthesizing high dynamic range image based on PatchMatch algorithm and rank minimization algorithm

A technology with high dynamic image and minimum rank, applied in image enhancement, image analysis, image data processing, etc., can solve image artifacts, blurring and other problems

Active Publication Date: 2017-03-15
SUN YAT SEN UNIV +2
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the shaking of the camera or the movement of objects in the scene, artifacts or blurring will often appear in the fused image.

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
  • Method for synthesizing high dynamic range image based on PatchMatch algorithm and rank minimization algorithm
  • Method for synthesizing high dynamic range image based on PatchMatch algorithm and rank minimization algorithm
  • Method for synthesizing high dynamic range image based on PatchMatch algorithm and rank minimization algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The present invention will be further explained below in conjunction with the drawings.

[0071] Such as figure 1 As shown, the method for synthesizing highly dynamic images based on PatchMatch and rank minimization algorithm of the present invention includes: 1) normalizing an input image set, and using PatchMatch algorithm to achieve image registration; 2) registering an image set Use the gamma curve to calibrate the image set; 3) use the rank minimization algorithm on the registered image set to obtain batches of aligned images; 4) synthesize the aligned image set to obtain the target high dynamic image.

[0072] The steps are described in detail below:

[0073] 1) Such as Figure 4 Shown as input (a) (b) (c) (d) (e) five images, and normalize all images, then use PatchMatch algorithm to process a set of dynamic scene image sets, in the reconstruction process, pass Extract the brightness of the image and its gradient information to obtain a set of registered image stacks,...

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 method for synthesizing a high dynamic range image based on a PatchMatch algorithm and a rank minimization algorithm. The method comprises the steps of firstly normalizing an input image set, and implementing image registration on the image set by using the PatchMatch algorithm; then performing radiometric calibration on the registered image set by using a gamma curve, and then acquiring batched aligned images by using the rank minimization algorithm; and finally synthesizing an aligned image set into a high dynamic range (HDR) image. The method disclosed by the invention utilizes latest research results of the rank minimization algorithm and the PatchMatch algorithm, and can effectively solve a problem of removing artifacts and fuzz in the fused HDR image.

Description

Technical field [0001] The invention relates to a method for synthesizing low-dynamic images into high-dynamic images. Specifically, it relates to a method that uses radiation calibration, PatchMatch and rank minimization algorithms to complete the registration and alignment of low-dynamic images, and finally generates high-dynamic images Image method. Background technique [0002] High dynamic range imaging has begun to become a commercial product, such as today's smart phones. In the same real scene, the limited dynamic range of most imaging sensors often fails to capture the irradiance range visible to the human eye. However, a relatively simple and inexpensive way to solve this limitation is to capture several pairs of the same scene. The photos of the exposure time are then merged into an image, which effectively expands the dynamic range of the image. However, due to the shaking of the camera or the movement of objects in the scene, artifacts or blurring of the fused imag...

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): G06T5/00G06T7/00
CPCG06T2207/20208G06T5/00G06T5/90
Inventor 谭洪舟邹兵兵朱雄泳陈荣军李智文黄登
Owner SUN YAT SEN UNIV
PatSnap Eureka logo

PatSnap Eureka turns technology decisions into work you can execute. Powered by our Innovation Knowledge Graph, it runs expert workflows across engineering, life sciences, materials and intellectual property. Get your review-ready output in minutes.

X (Twitter)LinkedInYouTubeSubstack

© 2026 PatSnap. All rights reserved. 

Terms of Service

 | 

Privacy policy

 | 

Modern Slavery Act Transparency Statement