A fine-grained classification method for women's fashion images based on part detection and visual features

A technology of visual features and classification methods, applied in computer parts, character and pattern recognition, instruments, etc., can solve the problem of not making good use of local information, and achieve the effect of improving accuracy and high classification accuracy.

Active Publication Date: 2022-04-12
KUNMING UNIV OF SCI & TECH
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In terms of feature extraction and classification, the known methods are mostly based on the underlying features such as color and texture to achieve feature extraction, which cannot make good use of local information, and there are certain limitations in the feature extraction of subtle style differences between fashion clothing categories and within categories. characteristics, only coarse-grained classification of fashion clothing can be achieved

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
  • A fine-grained classification method for women's fashion images based on part detection and visual features
  • A fine-grained classification method for women's fashion images based on part detection and visual features
  • A fine-grained classification method for women's fashion images based on part detection and visual features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Embodiment 1: as Figure 1-2 As shown, a fine-grained classification method for fashion women's clothing images based on part detection and visual features, firstly detects the parts of body parts on the input fashion women's clothing images to be classified and fashion women's clothing images in the fashion women's training set; secondly, extracts parts respectively The detected fashion women's clothing image and the HOG, LBP, color histogram and edge operator four underlying features of the fashion women's clothing image are trained to obtain the image after feature extraction; then, the defined visual feature descriptor is combined with the extracted four The underlying features are matched, and the fine-grained classifier model is trained using random forest and multi-class SVM supervised learning; finally, through the trained fine-grained classifier, the fine-grained classification of the fashion women's clothing images extracted from the feature is realized, and th...

Embodiment 2

[0036] Embodiment 2: wherein the improved DPM model is made up of a root model and some part models, and the object model of n parts is represented as a (n+2) tuple (F 0 ,P 1 ,...P i ,...P n ,b), where F 0 is the root filter, P i is the model of the i-th component, b is a deviation loss coefficient, at l 0 scale layer, with (x 0 ,y 0 ) for the anchor's response score is:

[0037]

[0038] in, is the response score of the root model, v i Is a two-dimensional vector, used to specify the coordinates of the i-th filter's anchor point position (ie, the standard position when no deformation occurs) relative to the root position, is the response score of the n part model, λ is the number of levels of the feature map computed at twice the resolution in the feature pyramid;

[0039] After calculating the response score, transform the response of the component filter and take into account the spatial uncertainty, the response transformation calculation formula is as follo...

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 fine-grained classification method for fashion women's clothing images based on component detection and visual features, and belongs to the field of computer vision and image applications. The present invention first detects body parts on the input images of fashion women's clothing to be classified and images in the training set; secondly, extracts the detected fashion women's clothing images respectively, and trains the HOG, LBP, color histogram and edge operator of the fashion women's clothing images 4 kinds of underlying features to obtain the image after feature extraction; then, match the defined visual feature descriptors with the extracted 4 underlying features, and use multi-class SVM supervised learning to train the fine-grained classifier model; finally, after training The fine-grained classifier for feature extraction realizes fine-grained classification of fashion women's clothing images, and outputs the classification results of fashion women's clothing images. The detection and classification method adopted in the present invention has a higher accuracy rate.

Description

technical field [0001] The invention relates to a fine-grained classification method for fashion women's clothing images based on component detection and visual features, and belongs to the field of computer vision and image applications. Background technique [0002] Online shopping has been greatly welcomed by people, showing the development trend of popularization, globalization, and mobility, which makes fashion clothing classification become an increasingly hot topic, and fashion clothing classification is widely used in e-commerce and other fields. Therefore, there are many improved methods for fashion clothing classification, including the most classic bag of words model, fashion clothing classification method based on deep learning, and random forest, SVM (Support Vector Machine, SVM for short), CNN (Convolutional Neural Network, Convolutional Neural Network, referred to as CNN) and other methods. Most of the known methods are aimed at the coarse-grained classificat...

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 & AuthorityPatents(China)
IPC IPC(8): G06V10/764G06V10/44
CPCG06V10/44G06F18/2411
Inventor刘骊吴苗苗付晓东黄青松刘利军
OwnerKUNMING UNIV OF SCI & TECH