Human body shape recognition method based on shape context is suitable for garment customization

A clothing customization and context technology, applied in the field of clothing, can solve the problems of high professional experience requirements of physiotherapists, difficult to form standardized methods, and difficult to quantify, and achieve scientific and feasible results.

Inactive Publication Date: 2019-03-01
HUNAN WANGBULIAO GARMENTS +1
View PDF7 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method requires high professional experience of body sizers. For the same body type, different body sizers may have different judgment results. It is difficult to form a standardized method and cannot meet the speed and accuracy requirements of large-scale personalized clothing customization.
Its shortcoming: When a body measurer evaluates the body shape, it is a comprehensive investigation of the body shape characteristics, which is difficult to quantify through specific anthropometric indicators

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] The method consists of three parts:

[0073] Part A: Establishing a body shape feature library;

[0074] Part B: Automatic recognition of human body shape;

[0075] Part C: clothing customization;

[0076] The specific steps of "establishing a body shape feature library" are as follows:

[0077] Step A1: Summarize the shoulders, back, chest and buttocks of the human body into different body shapes and their characteristic parameters in at least two levels;

[0078] Shoulder: determine the slope range value of flat shoulder, normal shoulder and slip shoulder;

[0079] Back: determine the mutation sites and mutation range values ​​of hunchback, flat back, normal back and reverse arched back;

[0080] Breast: Determine the mutation sites and mutation range values ​​of chicken breast, normal breast, flat chest and concave breast;

[0081] Buttocks: Determine the mutation sites and mutation range values ​​of the buttocks, flat buttocks and concave buttocks.

[0082] St...

Embodiment 2

[0093] Basically the same as Example 1, the difference is:

[0094] The "obtaining the customer's front or / and back and side images" in the step B1 uses a digital camera or a mobile phone camera or a three-dimensional scanner.

[0095] The "reading the image and extracting the contour graphic data of the human body" in the step B2 adopts one or a combination of image preprocessing, binarization, and Canny contour extraction methods.

Embodiment 3，4

[0097] Respectively with embodiment 1,2 are basically the same, the difference is:

[0098] The specific method of "calculating the shape context descriptors of the feature contours of the normal body and the special body in various parts in the step A1" in the step A2 is;

[0099] Step A2-1: randomly sampling a certain number of measurement samples according to the various body shape parameters divided in step A1;

[0100] Step A2-2: Calculating the average shape of the local contours of the samples characterizing each type of body shape;

[0101] Step A2-3: Perform a certain amount of uniform sampling on the average shape of the contour to obtain a set of point sets describing the shape of the contour;

[0102] Step A2-4: Calculate the shape context description histogram of each point according to the coordinates of the point set, and the histogram sequence of all contour points constitutes the shape context descriptor of the contour.

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 human body shape identification method based on shape context suitable for garment customization. The method includes: step A1 the shoulder, back, chest and buttocks of the human body are induced into different body shapes and their characteristic parameters; A2) calculatING that shape context descriptor of the feature contour of each part to establish a body shape feature database; Step B1, acquiring a face image of a customer; B2, read that contour figure data of the human body extracted from the image, and calculate a shape context descriptor of the actual characteristic contour of the designated part; B3, compare that obtained somatotype result; C1, obtaining that actual size; C2, formulating a modification rule; C3, adjusting and modifying that specific partof the standard garment template; C4: making pattern design and outputting. The invention has the following advantages: the method is scientific and feasible, the image can be obtained remotely, the figure identification is intelligently completed, the actual size is measured, and the pattern output of the customized garment is completed.

Description

technical field [0001] The invention relates to the field of clothing, in particular to a body shape recognition method based on shape context suitable for clothing customization. Background technique [0002] When customizing clothing, it is necessary to measure the size of certain parts of the human body, and judge the particularity of the individual body shape, such as a chest-high body, a normal body, a hunchback body, etc., and make corresponding adjustments to the clothing version according to the judgment results. Adapt to special body characteristics and improve the fit of clothing. Traditional anthropometric measurements and judgments of special body shapes are done manually by body sizers, and the judgment of special body types mainly depends on the professional experience of body sizers. This method requires high professional experience of body sizers. For the same body type, different body sizers may have different judgment results. It is difficult to form a sta...

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): G06K9/00G06K9/46G06K9/40
CPCG06V40/103G06V10/30G06V10/44
Inventor 夏明
Owner HUNAN WANGBULIAO GARMENTS
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap