Three-dimensional measurement method of non-contact cheongsam customized human body based on deep learning

A non-contact, deep learning technology, applied in the field of clothing manufacturing, can solve problems such as high background complexity requirements and poor customization of cheongsam

Active Publication Date: 2022-02-22
HANGZHOU DIANZI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] This invention mainly aims at the problems that the current field of cheongsam customization at home and abroad has high demand for remote non-contact measurement, and similar inventions in the past are not very pertinent to cheongsam customization and have high requirements for background complexity. A non-contact human body three-dimensional size measurement method for cheongsam customization based on deep learning and higher accuracy

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
  • Three-dimensional measurement method of non-contact cheongsam customized human body based on deep learning
  • Three-dimensional measurement method of non-contact cheongsam customized human body based on deep learning
  • Three-dimensional measurement method of non-contact cheongsam customized human body based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be described in detail below in conjunction with the accompanying drawings. It should be noted that the described embodiments are only intended to facilitate the understanding of the present invention, rather than limiting it in any way.

[0032] The present invention aims to take into account the accuracy, efficiency and cost, fully consider the user's privacy needs when using it, and use image processing technology and deep learning technology to extract The outline of the human body and the target points of the human body, and automatically calculate the corresponding precise size data. Through the present invention, users at home and abroad can obtain accurate human body measurements only by uploading a few photos. The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0033] figure 1 It is a flow chart of the measurement method of the present invention, showing the whole ...

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 a non-contact cheongsam customized human body three-dimensional size measurement method based on deep learning. The present invention first trains on the COCO data set to obtain a network model capable of separating the human body from complex backgrounds. Secondly, obtain the back and side images of the object. Position the human body coordinates and mask according to the model, and extract the binary image centered on the human body object. Then, according to the performance characteristics of each part of the human body, the coordinates of each feature point are located to obtain the first size group. Then, according to the feature point coordinates and the first size group, the body shape of the target human body is divided into multiple categories, and different calculation formulas are used to obtain the three-dimensional circumference size of the human body, that is, the second size group. The invention proposes a novel positioning method for armpit points, neck points, and waist height points for clothing customization, and proposes non-contact measurement methods for front waist joints, back waist joints, front chest width, and back width for cheongsam customization. Fine-tune the positioning of feature points and the calculation of circumference for body features.

Description

technical field [0001] The invention belongs to the field of clothing manufacturing, and relates to a non-contact human body three-dimensional dimension measurement method based on deep learning for cheongsam customization. Background technique [0002] With the development of computers, computers have brought various conveniences to people's lives, and various intelligent devices have also appeared. At the same time, deep learning technology has been widely used in the field of digital image processing in recent years and has achieved remarkable results, both in scientific research and project implementation. [0003] Cheongsam is famous for highlighting the graceful figure of women, and is deeply loved by ladies at home and abroad. When making cheongsam, people of different body types have different body parts, and cheongsam needs to fit all parts of a woman's body, requiring very accurate human body measurements. And compared with general clothing, cheongsam customizati...

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): A41H1/00G06K9/62
CPCA41H1/00G06F18/214
Inventor 付晓峰胡卓群付晓鹃
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products