Supercharge Your Innovation With Domain-Expert AI Agents!

Portrait clustering processing method and device

A processing method and clustering technology, applied in the field of image processing, can solve problems such as poor clustering effect of portraits, achieve the effect of reducing influence and improving accuracy

Pending Publication Date: 2022-05-27
ZHEJIANG DAHUA TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a portrait clustering processing method and device, to at least solve the problem of screening captured images according to fixed thresholds of some indicators in the related art for portrait clustering, and some low-quality images participate in portrait clustering, resulting in portrait clustering underperforming problems

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
  • Portrait clustering processing method and device
  • Portrait clustering processing method and device
  • Portrait clustering processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] The method embodiment provided in Embodiment 1 of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Take running on a mobile terminal as an example, figure 1 is the hardware structure block diagram of the mobile terminal of the portrait clustering processing method according to the embodiment of the present invention, such as figure 1 As shown, the mobile terminal may include one or more ( figure 1 Only one is shown) processor 102 (processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data, optionally, the above-mentioned mobile terminal may also Transmission devices 106 and input and output devices 108 may be included for communication functions. Those of ordinary skill in the art can understand that, figure 1 The shown structure is for illustration only, and it does not limit the structu...

Embodiment 2

[0092] According to another embodiment of the present invention, there is also provided a portrait clustering processing device, Image 6 is a block diagram of a portrait clustering processing device according to an embodiment of the present invention, such as Image 6 shown, including:

[0093] The parsing module 62 is used for parsing the captured image of the target to obtain the target image data;

[0094] The input module 64 is used to input the target image data into the pre-trained image evaluation model to obtain the target image classification result corresponding to the target image data output by the trained image evaluation model;

[0095] The output module 66 is used for outputting the target image data to the archive message queue if the target image classification result is an image to be gathered;

[0096] The clustering module 68 is configured to perform portrait clustering processing based on the message queue for gathering files.

[0097] Optionally, the ...

Embodiment 3

[0113] Embodiments of the present invention further provide a computer-readable storage medium, where a computer program is stored in the storage medium, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

[0114] Optionally, in this embodiment, the above-mentioned storage medium may be configured to store a computer program for executing the following steps:

[0115] S1, parse the target snapshot image to obtain target image data;

[0116] S2, inputting the target image data into a pre-trained image evaluation model to obtain a target image classification result corresponding to the target image data output by the trained image evaluation model;

[0117] S3, if the classification result of the target image is an image to be grouped, outputting the target image data to the grouping message queue;

[0118] S4, perform portrait clustering processing based on the message queue for gathering files.

[0119] Option...

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 portrait clustering processing method and device, and the method comprises the steps: analyzing a target snapshot image, and obtaining target image data; inputting the target image data into a pre-trained image evaluation model to obtain a target image classification result corresponding to the target image data output by the trained image evaluation model; if the target image classification result is an image to be subjected to file gathering, outputting the target image data to a file gathering message queue; and carrying out portrait clustering processing on the basis of the file clustering message queue, so that the problem of poor portrait clustering effect caused by the fact that part of low-quality images participate in portrait clustering when snapshot images are screened out for portrait clustering according to fixed threshold values of part of indexes in related technologies can be solved; the accuracy of the image classification result is improved through the trained image evaluation model, high-quality images can be screened out more accurately to participate in clustering, and the influence of low-quality images on the clustering result is reduced.

Description

technical field [0001] The present invention relates to the field of image processing, and in particular, to a method and device for clustering processing of portraits. Background technique [0002] Due to the complexity of the real environment and the randomness of point snapshots, some low-quality images (that is, blurred images, abnormal exposure, noise, etc.) often appear in the collection of personnel images. For example, if there are people moving at a high speed in front of the capture point, the captured image is often blurred; at certain angles at noon, the captured image of the person is often overexposed, resulting in reduced image recognition; when the light is insufficient, the captured image is Images can produce severe image noise. [0003] Most of the current solutions are to select several effective evaluation indicators and assign them a fixed threshold. When the captured image does not meet the threshold of a certain indicator, it is directly discarded an...

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): G06K9/62G06F9/54G06V10/762G06V10/764G06V10/774
CPCG06F9/546G06F18/23G06F18/214G06F18/241
Inventor 邱莹袁虎标李辉董素素
Owner ZHEJIANG DAHUA TECH CO LTD
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