Garment aesthetics quality evaluation system based on deep convolutional neural network

A quality evaluation, neural network technology, applied in the field of clothing aesthetics quality evaluation system based on deep convolutional neural network, can solve the problem of inconvenient clothing aesthetic quality distinction and evaluation, to improve aesthetic ability, improve accuracy, and improve recognition. the effect of knowing

Inactive Publication Date: 2022-03-18
长春大学旅游学院
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The above-mentioned evaluation system has the advantages of objectification, automation and systematization of clothing visual effect evaluation; but

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
  • Garment aesthetics quality evaluation system based on deep convolutional neural network
  • Garment aesthetics quality evaluation system based on deep convolutional neural network
  • Garment aesthetics quality evaluation system based on deep convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0034] Example 1

[0035] See Figure 1 - Figure 3 The present invention provides a clothing aesthetic quality evaluation system based on deep convolutional neural network, wherein the technical solutions are as follows:

[0036] Including clothing image acquisition module, clothing image division module, clothing image classification module, clothing image analysis module, convolutional neural network module, aesthetic quality evaluation module;

[0037] The clothing image acquisition module is used to capture overall image data for the collection of clothing;

[0038] The clothing image segmentation module is used to segment the image data collected in the clothing image acquisition module in accordance with the different structures of the clothing to obtain several local clothing image data;

[0039] Clothing Image Classification Module The number of partial fashion image data in multiple clothing is classified according to the structure of the garment, and collectively collate ...

Example Embodiment

[0057] Example 2

[0058] See Figure 1 - Figure 3 The present invention provides a clothing aesthetic quality evaluation system based on deep convolutional neural network, wherein the technical solutions are as follows:

[0059] Including clothing image acquisition module, clothing image division module, clothing image classification module, clothing image analysis module, convolutional neural network module, aesthetic quality evaluation module;

[0060] The clothing image acquisition module is used to capture overall image data for the collection of clothing;

[0061] The clothing image segmentation module is used to segment the image data collected in the clothing image acquisition module in accordance with the different structures of the clothing to obtain several local clothing image data;

[0062] Clothing Image Classification Module The number of partial fashion image data in multiple clothing is classified according to the structure of the garment, and collectively collate ...

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 clothing aesthetic quality evaluation system based on a deep convolutional neural network. According to the technical scheme, the clothing aesthetic quality evaluation system is characterized by comprising a clothing image acquisition module, a clothing image segmentation module, a clothing image classification module, a clothing image analysis module, a convolutional neural network module and an aesthetic quality evaluation module; the clothes image acquisition module is used for acquiring overall image data of the collected clothes; the clothing image segmentation module is used for sequentially segmenting the image data acquired in the clothing image acquisition module according to different structures of clothing to obtain a plurality of local clothing image data; the clothing image classification module classifies a plurality of local clothing image data of a plurality of garments according to the structures of the garments and collects the local clothing image data together for classification; the cognition of people on the aesthetic quality of the clothes is improved, and the aesthetic ability of the clothes is improved.

Description

technical field [0001] The invention relates to the field of clothing aesthetic quality evaluation, in particular to a clothing aesthetic quality evaluation system based on a deep convolutional neural network. Background technique [0002] Clothing aesthetics is a subject that studies the beauty, aesthetics and laws of clothing. It is one of the most important courses in clothing art courses. It belongs to the general aesthetic category and follows the special laws of clothing art and clothing aesthetics. The main research content It is the comprehensive aesthetic effect of clothing, wearer and environment. Clothing aesthetics has the philosophical nature of theoretical speculation, but it has its own independent discipline system and professional field, and has special laws of clothing art and clothing aesthetics. As the condensate of human culture, clothing is a must for human life. [0003] For example, the Chinese patent whose authorized announcement number is CN 104268...

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): G06Q10/06G06N3/04G06K9/62G06V10/26G06V10/764G06V10/82G06V10/74
CPCG06Q10/06393G06N3/045G06F18/22G06F18/24
Inventor 刘凌孙明阳
Owner 长春大学旅游学院
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