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

Multi-task face attribute classification method and system based on adaptive feature fusion

A technology of feature fusion and attribute classification, which is applied in the fields of computer vision and machine learning, can solve problems such as not being able to express images well, and achieve the effect of significant classification accuracy and improved classification accuracy

Active Publication Date: 2022-07-15
SHANDONG UNIV OF FINANCE & ECONOMICS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The features after feature fusion cannot express the characteristics of the image well

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
  • Multi-task face attribute classification method and system based on adaptive feature fusion
  • Multi-task face attribute classification method and system based on adaptive feature fusion
  • Multi-task face attribute classification method and system based on adaptive feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] Embodiment 1, this embodiment provides a multi-task face attribute classification method based on adaptive feature fusion;

[0034] like figure 1 As shown, the multi-task face attribute classification method based on adaptive feature fusion includes:

[0035] S1: Obtain the face image to be classified;

[0036] S2: Preprocessing the face image to be classified;

[0037] S3: Input the preprocessed face image to be classified into the multi-task face attribute classification model based on adaptive feature fusion, obtain the probability of different categories of the image on each face attribute, and select the category with the highest probability as the Classification results on corresponding attributes.

[0038] As one or more embodiments, the preprocessing operation specifically includes:

[0039] First, scale all images to 224×224 pixels;

[0040] Then, the average pixel value of the images in the training set is calculated, and the normalization operation is pe...

Embodiment 2

[0115] Embodiment 2, this embodiment provides a multi-task face attribute classification system based on adaptive feature fusion;

[0116] A multi-task face attribute classification system based on adaptive feature fusion, including:

[0117] an acquisition module, which is configured to: acquire a face image to be classified;

[0118] a preprocessing module, which is configured to: perform a preprocessing operation on the face image to be classified;

[0119] A classification module, which is configured to: input the preprocessed face image to be classified into a multi-task face attribute classification model based on adaptive feature fusion, and obtain the probability of different categories of the image on each face attribute, The category with the highest probability is selected as the classification result on the corresponding attribute.

Embodiment 3

[0120] Embodiment 3, this embodiment also provides an electronic device, including a memory, a processor, and computer instructions stored in the memory and run on the processor, and when the computer instructions are run by the processor, the first embodiment is completed. method described.

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 multi-task face attribute classification method and system based on self-adaptive feature fusion, comprising: acquiring a face image to be classified; performing a preprocessing operation on the face image to be classified; The face image is input into the multi-task face attribute classification model based on adaptive feature fusion, and the probability of different categories of the image on each face attribute is obtained, and the category with the highest probability is selected as the classification result on the corresponding attribute. The present disclosure constructs an adaptive feature fusion layer to connect network branches of different tasks to form a unified multi-task deep convolutional neural network, so that information can be effectively shared between different tasks, and the classification accuracy effect is significantly improved.

Description

technical field [0001] The present disclosure relates to the technical fields of computer vision and machine learning, and in particular, to a multi-task face attribute classification method and system based on adaptive feature fusion. Background technique [0002] The statements in this section merely mention background related to the present disclosure and do not necessarily constitute prior art. [0003] In recent years, deep convolutional neural networks have achieved breakthrough results in many computer vision tasks, such as object detection, semantic segmentation, depth prediction, etc. The multi-task deep convolutional neural network is designed to jointly process multiple related tasks. While improving the learning efficiency, it can improve the prediction accuracy and generalization performance through the feature interaction between tasks and prevent overfitting. [0004] When implementing multi-task deep convolutional neural networks, the most common scheme is t...

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 Patents(China)
IPC IPC(8): G06V40/16G06V10/764G06V10/80G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/179G06V40/178G06V40/168G06V40/172G06N3/047G06N3/045G06F18/2415G06F18/253
Inventor 崔超然申朕黄瑾
Owner SHANDONG UNIV OF FINANCE & ECONOMICS
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