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

Deep learning image restoration method for automatically identifying blurring type

A deep learning and automatic recognition technology, applied in the field of image restoration, can solve problems such as the inability to quickly batch process a large number of images of different blur types, the inability to identify image blur types, etc.

Inactive Publication Date: 2018-11-16
湖南丹尼尔智能科技有限公司
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the shortcomings of the above situation, the present invention aims to provide a deep learning image restoration method that automatically recognizes the blur type, so as to solve the problem that the existing image restoration method cannot identify the image blur type, and cannot quickly batch process a large number of images of different blur types

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
  • Deep learning image restoration method for automatically identifying blurring type
  • Deep learning image restoration method for automatically identifying blurring type
  • Deep learning image restoration method for automatically identifying blurring type

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0025] Such as figure 1 As shown, a deep learning image restoration method for automatically identifying blur types provided in this embodiment includes the following steps:

[0026] Step 1: Build a deep learning classification model for identifying ambiguous types, such as figure 2 As shown, the specific structure includes 14 layers. The input layer is a blurred image with a size of 256×256. The output layer is the blur type corresponding to t...

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 deep learning image restoration method for automatically identifying a blurring type. For lots of blurred image with unknown blurring types, the blurring types are identifiedautomatically by a trained deep learning classification model; and on the basis of the blurring types, deep learning image restoration algorithms for the blurring types are invoked and thus end-to-end image restoration processing is carried out quickly. According to the invention, images with different blurring types can be processed quickly in batches; and the method can be applied in practice conveniently.

Description

technical field [0001] The invention relates to the field of image restoration, and specifically refers to a deep learning image restoration method for automatically identifying blur types. Background technique [0002] In the process of image acquisition, transmission and storage, due to various factors, such as the turbulence effect of the atmosphere, the aberration of the optical system, the relative motion between the imaging device and the object, the nonlinearity of the sensor characteristics, etc., the image will be blurred. As a result, image quality is degraded, and corresponding image restoration algorithms need to be used for deblurring, thereby improving image quality. [0003] According to the causes of blurred images, there are many types of blurred images, such as motion blur, defocus blur, and shaking blur. At present, many image restoration algorithms have been proposed for each type of blurred image to obtain a good image. Recovery effect. However, in rea...

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): G06T5/00G06N3/04G06N3/08
CPCG06N3/08G06T2207/20084G06T2207/20081G06N3/045G06T5/73
Inventor 徐国祥
Owner 湖南丹尼尔智能科技有限公司