Supercharge Your Innovation With Domain-Expert AI Agents!

Image screening method and device and electronic equipment

A screening method and image technology, applied in the field of image processing, can solve problems such as time-consuming and labor-intensive, and achieve the effects of improving experience, solving time-consuming and labor-intensive, and improving screening efficiency.

Inactive Publication Date: 2019-06-04
BEIJING UNIV OF TECH
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the object of the present invention is to provide an image screening method, device and electronic equipment to solve the time-consuming and labor-intensive technical problem of image feature extraction existing in the prior art

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 screening method and device and electronic equipment
  • Image screening method and device and electronic equipment
  • Image screening method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] The embodiment of the present invention provides an image screening method, such as figure 1 As shown, the method includes:

[0037] Step S102: Obtain image data to be processed.

[0038] Specifically, the image to be processed is the initial image data that meets the preset pixel and picture format, such as: the preset picture format is ".jpg", the preset picture pixel is 96*96, and the picture needs to be extracted from the initial image data The image format is .jpg, and the image format is .jpg is processed to obtain an image format of .jpg with a picture pixel of 96*96, which is the image data to be processed.

[0039] Step S104: Use the first network model to filter out the image data to be processed that is lower than the preset score value to obtain the first image data and the image detection data value corresponding to the first image data.

[0040] It should be noted that the first network model is a convolutional neural network (Convolutional Neural Network, referre...

Embodiment 2

[0050] The embodiment of the present invention provides an image screening method, such as figure 2 As shown, the method includes:

[0051] Step S202: Acquire initial image data through the imaging device.

[0052] Specifically, the user collects the initial image data through a mobile phone, a tablet computer, and a camera, and stores the initial image data. The initial image data can be stored in a local server for recall.

[0053] Step S204: Extract image data that meets the preset image attributes from the initial image data to obtain the image data to be processed, where the preset image attributes include: the file format of the image and the pixel information of the image.

[0054] It should be noted that the image formats include: ".jpg", ".jepg", ".png", ".gif", ".bmp". The image formats selected in the present invention are ".jpg" and ".jepg" ", the pixel information of the selected image is 96*96.

[0055] Step S206: Use the first network model to filter out the image data ...

Embodiment 3

[0080] The embodiment of the present invention provides an image screening device, such as Image 6 As shown, the device includes: an acquisition module 61, a filtering module 62, a grouping module 63, an extraction module 64, and a screening module 65.

[0081] It should be noted that the acquisition module 61 is used to acquire image data to be processed. The filtering module 62 is configured to use the first network model to filter the to-be-processed image data lower than the preset score value to obtain the first image data and the image detection data value corresponding to the first image data. The grouping module 63 is configured to use a hash algorithm to group images in the first image data whose similarity is greater than a preset value, and filter the grouped first image data according to the image detection data to obtain second image data. The extraction module 64 is configured to input the second image data into the second network model, and extract the third image...

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 an image screening method and device and electronic equipment, and relates to the technical field of image processing, which comprises the following steps: obtaining to-be-processed image data; Filtering to-be-processed image data lower than a preset score value by using the first network model to obtain first image data and an image detection data value corresponding to thefirst image data; Grouping the images with the similarity greater than a preset value in the first image data by using a Hash algorithm, and screening the grouped first image data according to the image detection data to obtain second image data; Inputting the second image data into a second network model, and extracting third image data corresponding to the preset scene from the second network model; According to the method, the third image data is screened according to the input of the user to obtain the target image data, the image screening efficiency is improved, the images meeting the requirements of the user can be screened according to the input of the user, and good experience is brought to the user.

Description

Technical field [0001] The present invention relates to the field of image processing technology, in particular to an image screening method, device and electronic equipment. Background technique [0002] With the development of science and technology, life has become rich and colorful. People often use mobile phones or cameras to record their lives, and then choose some pictures to share on social platforms such as websites, Weibo, and WeChat. However, due to the image beauty, the complexity of shooting scenes and the explosive growth of the number of images, it is difficult to edit and manage images. [0003] The prior art usually constructs image feature extraction algorithms based on image characteristics, aesthetic theories, etc., manually extracts image features, and uses machine learning methods, such as support vector machine (SVM) and support vector regression (support vector regression). , Referred to as SVR), etc., to classify image beauty or to score image beauty. This...

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): G06K9/62G06T7/00
Inventor 冯文颖姜楠高雅妮纪卓骁
Owner BEIJING UNIV OF TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com