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

Deep learning-based high-precision image fuzzy detection method

A technology of blur detection and deep learning, used in image enhancement, image analysis, image data processing, etc.

Inactive Publication Date: 2017-05-31
TIANJIN UNIV
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in terms of image blur detection, we need to learn blur-related features while ignoring the large differences due to different image contents

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-based high-precision image fuzzy detection method
  • Deep learning-based high-precision image fuzzy detection method
  • Deep learning-based high-precision image fuzzy detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Below in conjunction with accompanying drawing, the present invention is described in detail:

[0034] The invention proposes a high-precision image blur detection method based on deep learning. Different from the existing method of extracting low-order features to optimize energy functions, the present invention extracts high-order features of images extracted by CNN from multiple scales for classification, and can realize high-precision image blur detection. This technology combines deep convolutional neural networks (ConvolutionalNeural Networks

[0035] Such as figure 1 Shown, the present invention adopts following technical scheme:

[0036] Step 1 (110, 120, 130) establishes a deep convolutional neural network model CNN and initialization, and inputs a detection image to it;

[0037] Among them, the overall architecture of the deep convolutional neural network is as follows: figure 2 As shown, the overall framework of blur detection at multiple scales is demo...

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 provides a deep learning-based high-precision image fuzzy detection method, which comprises the following steps: (1) building a deep convolution neural network model CNN and carrying out initialization and inputting a detected image into the deep convolution neural network model CNN; (2) selecting different s scales for a to-be-detected image by the deep convolution neural network model to obtain image blocks of different scales; (3) carrying out feature extraction on the image blocks in the step (2) by the deep convolution neural network model to obtain single-scale fuzzy graphs according to six convolution layers; and (4) carrying out fusion processing on the different single-scale fuzzy graphs by the deep convolution neural network model for multiple times to obtain the fuzzy graphs. According to the method, a deep convolution neural network is applied to the problem image fuzzy detection, so that a fuzzy area in the image is accurately detected as the target.

Description

technical field [0001] The invention belongs to the field of image blur detection and relates to a high-precision image blur detection technology based on deep learning. Background technique [0002] The background technology involved in the present invention has: [0003] (1) Image blur detection (Blur detection): For image blur detection, previous work mainly focused on the manual selection of features and the optimization of energy functions. Selecting appropriate features or energy functions, different methods can be used to directly model the subject, such as the use of multi-directional gradient statistics methods to establish energy functions for fuzzy segmentation, local gradient statistics methods are also used to estimate the blur caused by object motion . Commonly used features are local energy spectrum slope, gradient histogram span, maximum saturation, and local autocorrelation consistency. There are some works to identify the type of blur and measure the con...

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): G06T7/00
CPCG06T7/0002G06T2207/20081G06T2207/20084
Inventor 冯伟孙济洲万亮黄睿范铭源
Owner TIANJIN 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