Unlock instant, AI-driven research and patent intelligence for your innovation.

AI face style identification method based on attribute feature extraction

A technology of attribute characteristics and recognition methods, applied in the field of face images, can solve the problems of not being able to recognize the style of the face, affecting the visual effect of wearing different clothes, etc.

Inactive Publication Date: 2020-09-01
杭州智珺智能科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the theory of face aesthetics, except for the distinctions of yellow, white, and black faces, any person has an inner id style, and the inner id style of the face is to a large extent , affecting the visual effects of wearing different clothes, and the existing face recognition technology cannot recognize the inner self-style of the face

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
  • AI face style identification method based on attribute feature extraction
  • AI face style identification method based on attribute feature extraction
  • AI face style identification method based on attribute feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Specific embodiments of the present invention will be described below in conjunction with the accompanying drawings, so that those skilled in the art can better understand the present invention. It should be noted that the specific embodiments described here are only used to explain the present invention, and do not limit the present invention.

[0023] In this embodiment, an AI face style recognition method based on attribute feature extraction is disclosed. The overall process is as follows figure 1 Shown:

[0024] Obtain a face picture through any device to ensure that there is an unobstructed face in the picture.

[0025] Based on the mtCNN face detection model, the face is located and recognized, and the positions of five key points of the face are obtained at the same time, which are two eyes, a nose, and the left and right ends of the mouth, such as figure 2 shown. According to the recognized eye position, the image is rotated until the two key points of the ...

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 relates to an AI face style identification method based on attribute feature extraction. The method comprises the steps of firstly obtaining a picture containing an unshielded face; detecting, positioning and correcting the human face in the picture; putting the corrected human face image into a pre-trained human face attribute recognition model; identifying face attributes such as gender, age, faceid, key points of the face, skin quality, skin color, face shape, five sense organ distribution, five sense organ size, five sense organ outline, five sense organ type and the like ofthe face; and finally, taking the recognized face attribute as an input, inputting the input into a pre-trained face style recognition model combined with an aesthetic expert theory, and finally outputting a face style.

Description

technical field [0001] The present invention relates to the technical field of face images, in particular to an AI face style recognition method based on attribute feature extraction. Background technique [0002] With the development of technology and the continuous improvement of productivity, face recognition has become a hot computer research field. [0003] Existing face recognition technology is mainly based on the input of pictures or videos of faces. First, it detects whether there is a face. It also includes attributes such as gender, age, and face shape of the face. [0004] However, in the theory of face aesthetics, except for the distinctions of yellow, white, and black faces, any person has an inner id style, and the inner id style of the face is to a large extent , affecting the visual effects of wearing different clothes, and the existing face recognition technology cannot recognize the inner self-style of the face. Contents of the invention [0005] The ...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/168G06V40/172G06N3/045G06F18/2411
Inventor 张力超董静雅郑泽宇桂珺付殿峥高原杨天吉
Owner 杭州智珺智能科技有限公司
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