Body type classification method based on contour features and matched rotary shooting device thereof

A technology of contour features and classification methods, which is applied in biometrics recognition, character and pattern recognition, instruments, etc., can solve problems such as uncombined and complicated processes, achieve small angle deviation, improve enterprise quality and market competitiveness, and promote The effect of the development of clothing customization technology

Active Publication Date: 2020-03-24
ZHEJIANG SCI-TECH UNIV
View PDF12 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] However, there are some problems in this type of method: (1) only rely on three-dimensional or two-dimensional information, that is, size data or cross-sectional shape for body type classification, and do not combine the two
(2) Relying on human body size information length, circumference size difference or angle value data for classification, the process is complicated and requires detailed size information of the tester

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
  • Body type classification method based on contour features and matched rotary shooting device thereof
  • Body type classification method based on contour features and matched rotary shooting device thereof
  • Body type classification method based on contour features and matched rotary shooting device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0058] Taking the classification of young women's legs as an example, firstly, the photos of the testers are taken by the measuring device, and then the size of the testers is measured. Image measurement sites such as Figure 3 to Figure 5 shown. Among them, O1 is the midpoint of the thigh, O2 is the midpoint of the knee, and O3 is the midpoint of the ankle. A total of 25 initial data variables were extracted (see Table 1).

[0059] Table 1 Initial data variables

[0060]

[0061]

[0062] Next, preprocess the data to ensure the accuracy of the experimental data. From the initial data variables, 12 variables that have a greater impact on the legs are selected, combined with the 8 related variables obtained through calculation, and finally 20 variables (as shown in Table 2) are selected for the research and analysis of leg shape segmentation.

[0063] Table 2 Variable table of leg body shape

[0064]

[0065] After analysis, the leg shape of young women can be divid...

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 body type classification method based on contour features and a matched rotary shooting device thereof. The body type classification method comprises the following steps: (1)human body photo shooting; (2) human body size extraction: determining feature points on the edge of the human body image to obtain the size of a human body feature part; respectively researching andclassifying the parts of the human body to obtain characteristic parameters which have great influence on the human body form; and (3) body type classification: according to the characteristic parameters obtained by the five parts of the human body, concluding the main body type of each part, respectively subdividing the five parts of the young female body, and carrying out morphological analysison the body type of each part. Starting from local characteristics of a human body, a three-dimensional human body measurement technology, and related theories and experimental technologies of three-dimensional human body modeling are researched and combined. A matched shooting device is researched and developed, images of the front face and the side face of the human body can be accurately measured by means of the rotary shooting device, and the angle deviation is extremely small; and the shooting device can realize shooting at different angles without configuring a plurality of cameras.

Description

technical field [0001] The invention belongs to the field of ergonomics technology and clothing measurement, and in particular relates to a body type classification method based on contour features and a supporting rotary shooting device. Background technique [0002] With the rapid development of computer network and information technology, the traditional clothing industry has entered the course of computer informatization and digitization. At the same time, people's requirements for clothing have also changed from the previous aesthetics and firmness to fit and comfort. At the same time, it has also promoted the reform of the traditional clothing industry, constantly adjusting the industrial model of clothing to meet the changing needs of consumers. Among them, fit is an inseparable part of the process of inspecting clothing quality, and it is also an indicator that most significantly affects consumer satisfaction today. Therefore, how to produce products that meet cons...

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): G06K9/00G06K9/20G06K9/46G06K9/62
CPCG06V40/10G06V10/10G06V10/44G06F18/24
Inventor 顾冰菲蔡晓裕陈希雅王婷钟泽君赵颖徐凯忆徐平华
Owner ZHEJIANG SCI-TECH 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