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

Color and shape recognition method for garment fabric cut-parts and related device

A recognition method and fabric technology, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve the problem that recognition technology cannot take into account the fast and accurate recognition performance at the same time, so as to improve the speed, improve the recognition effect, improve effect of training

Pending Publication Date: 2021-02-26
GUANGDONG UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a color and shape recognition method and related devices for clothing fabric pieces, which are used to solve the technical problem that the existing clothing fabric piece recognition technology cannot take into account fast and accurate recognition performance at the same time

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
  • Color and shape recognition method for garment fabric cut-parts and related device
  • Color and shape recognition method for garment fabric cut-parts and related device
  • Color and shape recognition method for garment fabric cut-parts and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] see figure 1 , Embodiment 1 of a color and shape recognition method for garment fabric pieces provided in the embodiment of the present application, including:

[0043] Step 101, collecting image datasets of clothing fabric pieces, labeling and saving the image datasets through the LabelImg tool.

[0044] It should be noted that those skilled in the art can use the camera imaging system to collect images of clothing fabric pieces as image data sets of clothing fabric pieces; and label and save the image data sets through the LabelImg tool. Markings include: the shape and color of clothing fabric pieces. The shape mainly includes: the front panel, back panel, sleeve head, sleeves and trouser legs of clothing fabric pieces; the colors mainly include black, white, red, orange, yellow, Blue, green, purple. For image collection and labeling, those skilled in the art can select according to the actual situation, which is not limited here.

[0045] Step 102, enhancing the i...

Embodiment 2

[0056] see figure 2 , Embodiment 2 of a color and shape recognition method for garment fabric pieces provided in the embodiment of the present application, including:

[0057] Step 201. Set the collection background color to white and the image size to 1280×960, and collect the image data set of the clothing fabric pieces.

[0058] It should be noted that, in order to reduce the interference of the data set of clothing fabric pieces on the recognition speed and accuracy, in this embodiment, when collecting the image data set of clothing fabric pieces, the background color of the collection is white, and the image size is set to for 1280×960.

[0059] Step 202. Name each image in the image data set according to the color and shape of the images in the image data set.

[0060] It should be noted that, in order to facilitate the classification of the recognized clothing fabric pieces, this embodiment also names each image in the image data set. The naming method can be manuall...

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 color and shape recognition method for garment fabric cut-parts and a related device, and the method comprises the steps: collecting an image data set of the garment fabric cut-parts, and carrying out the labeling and storage of the image data set through a LabelImg tool; enhancing the image data set to obtain an image expansion data set, wherein the image expansion dataset comprises a training set and a test set; setting a feature extraction layer of the RetinaNet network structure model to be ResNet-50; setting evaluation indexes of the RetinaNet network structuremodel, freezing a first convolution layer and a second convolution layer of the RetinaNet network structure model, inputting the training set into the RetinaNet network structure model for training, and obtaining a RetinaNet network structure recognition model when a preset number of training times is reached; and inputting the test set into the RetinaNet network structure identification model, and outputting an identification result of the garment fabric cut-parts, thereby solving the technical problem that the existing garment fabric cut-part identification technology cannot give consideration to rapid and accurate identification performance at the same time.

Description

technical field [0001] The present application relates to the technical field of target detection, and in particular to a method and device for recognizing the color and shape of clothing fabric pieces. Background technique [0002] With the rapid development of modern science and technology in our country, traditional industries will also be impacted to a certain extent. Enterprises need to integrate modern science and technology as soon as possible, and develop in the direction of automation and intelligence. Using the research results in the field of computer vision to replace a large number of repetitive and stylized production processes manually can provide a new solution for the production industry to improve production efficiency and product quality. [0003] In the production process of clothing products, the identification of clothing fabric pieces is a very important process. The recognition and classification of the shape and color of clothing fabric pieces requ...

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): G06K9/32G06K9/00G06K9/46G06K9/62G06N3/04
CPCG06V10/95G06V10/255G06V10/56G06N3/045G06F18/214
Inventor 柴文光陈香远
Owner GUANGDONG UNIV OF TECH