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

Image processing method and device based on fuzzy detection

An image processing device and blur detection technology, applied in the field of image processing, can solve the problems of inability to completely solve the problem of blur image processing, inability to distinguish between blurred parts and clear parts, lack of blur image processing, etc., and achieve high image processing efficiency and simple algorithm , to avoid the effect of misidentification

Pending Publication Date: 2021-08-03
NEW VISION MICROELECTRONICS INC
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Although it classifies and detects blurred images through a classification model based on neural networks, it lacks the processing of blurred images, and when detecting blurred images, it can only distinguish between blurred and clear images, but it cannot target the blurred images in a single image. Distinguishing between blurred and clear parts
Therefore, it is still impossible to completely solve the processing problem of blurred images.

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
  • Image processing method and device based on fuzzy detection
  • Image processing method and device based on fuzzy detection
  • Image processing method and device based on fuzzy detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Such as figure 1 shown

[0036] An image processing method based on blur detection, the method performs the following steps:

[0037] Step 1: When the image capture device captures image information, it first uses the first image recognition model to perform image recognition on the subject to obtain the first image recognition result, and adds the first image recognition result to the captured image information to obtain For complete image information, go to step 2;

[0038] Step 2: Perform image blur judgment on the complete image information, specifically including: using the second image recognition model to perform image recognition on the image information in the complete image information to obtain the second image recognition result, and compare the second image recognition result with the complete image The first image recognition result in the information is compared to obtain a similarity value; if the similarity value between the first image recognition re...

Embodiment 2

[0042] On the basis of the previous embodiment, the method for the first image recognition model in the step 1 to perform image recognition on the captured image includes: determining a target candidate area from the photographed object, and performing a target candidate area in the target candidate area Feature extraction to obtain extracted image features; use the extracted image features to perform target detection based on a deep convolutional multilayer neural network target detection model to obtain candidate targets; use the extracted image features to perform target detection based on a deep convolutional multilayer neural network The neural network target classification model identifies the candidate targets to obtain a first image recognition result.

[0043] Specifically, Convolutional Neural Networks (CNN) is a type of Feedforward Neural Networks (Feedforward Neural Networks) that includes convolution calculations and has a deep structure, and is one of the represen...

Embodiment 3

[0046] On the basis of the previous embodiment, the method for the second image recognition model in step 2 to perform image recognition on the image information in the complete image information includes: extracting the multi-dimensional local features of the image information, and extracting the Deep learning features of image information; splicing the multi-dimensional local features and the deep learning features to form a multi-dimensional vector of the image information, and performing dimensionality reduction on the spliced ​​multi-dimensional vector through a metric learning dimensionality reduction matrix processing to obtain metric learning features, wherein the metric learning dimensionality reduction matrix includes a first metric learning dimensionality reduction matrix and a second metric learning dimensionality reduction matrix; the image is identified according to the metric learning features to obtain the second Image recognition results.

[0047] Specifically...

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 belongs to the technical field of image processing, and particularly relates to an image processing method and device based on fuzzy detection. According to the method, the efficiency is improved by discriminating whether the image information is a blurred image or not, and compared with direct blurring processing on the image information in the prior art, the clear image can be screened out in advance, and system resources are reduced; meanwhile, when the image information is processed, the fuzzy area in the fuzzy image is determined firstly, only the fuzzy part in the image information can be processed in a targeted mode when the fuzzy processing is carried out, and the efficiency is further improved. Besides, when the fuzzy processing is carried out, the image is restored by using the fuzzy equation solution based on the Markov chain, so that the image can be restored from multiple levels, and the image restoring quality is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image processing method and device based on blur detection. Background technique [0002] When shooting an object with a camera, there may be relative movement or shaking between the camera and the object during the exposure process, so the obtained image will appear blurred. For example, the forward propulsion of the aircraft and the vibration of the loading platform during the aerial photography of the ground, the shaking of the ordinary digital camera when the object is held in hand and the door is released and opened, etc., many shooting environments will cause motion blur. Under certain image acquisition conditions, how to use the obtained information to obtain a clearer image has become a particularly important step in the imaging process, and it is also a hot spot in the field of modern image processing. It is used in astronomical photography, aeria...

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): G06T5/00G06T7/00G06T7/13G06K9/62G06N3/04G06N3/08
CPCG06T7/0002G06T7/13G06N3/08G06T2207/10004G06N3/045G06F18/213G06F18/22G06F18/2431G06F18/295G06T5/73
Inventor 肖宏
Owner NEW VISION MICROELECTRONICS INC
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