Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A fashion compatibility prediction method based on low-rank regularization feature enhancement representation

A technology of feature enhancement and prediction method, applied in the field of clothing analysis in a multimedia environment

Active Publication Date: 2019-04-05
TIANJIN UNIV
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a fashion compatibility prediction method based on low-rank regularized feature enhancement characterization. The present invention is dedicated to solving the problem of clothing collocation evaluation, and proposes a fashion compatibility scoring method. See the following description for details:

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 fashion compatibility prediction method based on low-rank regularization feature enhancement representation
  • A fashion compatibility prediction method based on low-rank regularization feature enhancement representation
  • A fashion compatibility prediction method based on low-rank regularization feature enhancement representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] An embodiment of the present invention provides a method for predicting fashion compatibility based on low-rank regularized feature-enhanced representation, see figure 1 , the method includes the following steps:

[0037] 101: Decompose the feature matrix into a first objective function consisting of main features of multiple perspectives and a sparse error matrix;

[0038] 102: Use hypergraph items to standardize the features learned in low-rank subspaces, and obtain the second objective function of the relationship between fashion items:

[0039] 103: Introduce the Grassmannian manifold to obtain the third objective function with the largest distance between the dictionary base matrices under different perspectives;

[0040] 104: Establish the relationship between the characteristics of the multi-view low-rank subspace and the output collocation score, add a sparse regularization term to the least squares loss part, and obtain the typical Lasso regression, which is t...

Embodiment 2

[0048] The scheme in embodiment 1 is further introduced below in conjunction with calculation formula and examples, see the following description for details:

[0049] 201: Using the penultimate fully connected layer of VGGNet19 to extract 1000-D high-level semantic features, plus extracting four kinds of visual features, using the l2 norm to normalize each type of feature, and then concatenating them to form a 1634- The feature representation of D, and finally, the 1634-D feature is normalized to obtain the feature matrix X;

[0050] Among them, the four visual features are: 1) 225-D block color moment, 2) 73-D edge direction histogram, 3) 128-D wavelet texture, 4) 64-D color histogram and 144-D color auto Related graphs.

[0051] 202: Decompose the feature matrix X into main feature parts of multiple perspectives and a sparse error matrix, see the following formula (1);

[0052] Through the processing of step 202, the learned feature matrix has the lowest rank, and the dic...

Embodiment 3

[0078] Provide the test experiment of a kind of fashion compatibility scoring method of the embodiment of the present invention below:

[0079] The detection performance of the embodiment of the present invention is measured by the normalized mean square error (nMSE) and the standard mean square error (rMSE) between the predicted scoring and the real value, defined as follows:

[0080]

[0081]

[0082] in, is the prediction score obtained by the model on the test set, y i is the true value on the test set, and N is the number of samples in the test set.

[0083] In order to evaluate the algorithm performance of this method, the embodiment of the present invention uses 21,889 sets of clothing collocations from the online fashion website Polyvore as a data set, which contains a total of 164,379 fashion items. 17116 outfits are taken for training and 3076 for testing. Take up to 5 pictures for each outfit, such as tops, pants, shoes and accessories. The ratio of the n...

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 fashion compatibility prediction method based on low-rank regularization feature enhancement representation. The method comprises the steps that a feature matrix is decomposed into a first objective function composed of main features of multiple visual angles and a sparse error matrix; The features learned in the low-rank subspace are standardized through hypergraph items, and a second objective function of the relation between the fashionable single products is obtained; a Grassmannian manifold is introduced to obtain a third objective function of the maximum distance between dictionary base matrixes under different visual angles; Establishing a relation between the characteristics of the multi-view low-rank subspace and the output matching score, adding a sparseregularization item to the least square loss part, and obtaining a typical Lasso regression, namely a fourth objective function; Obtaining a fifth objective function taking the affinity matrix as a label matrix, establishing a relationship between the affinity matrix and the learned characteristics, and minimizing an error between the affinity matrix and the learned characteristics; And obtaininga total objective function according to the weighting of the first to fifth objective functions, optimizing the total objective function by utilizing an alternating direction multiplier method, introducing a Lagrangian multiplier, and sequentially iteratively updating parameters at each view angle until the value of the objective function is converged to obtain a final prediction score.

Description

technical field [0001] The invention relates to the field of clothing analysis in a multimedia environment, in particular to a fashion compatibility prediction method based on low-rank regularization feature enhancement representation. Background technique [0002] With the improvement of social productivity, people's consumption level is also gradually rising, and people pay more and more attention to the pursuit of fashion and the improvement of personal image. Fashion collocation mainly refers to the coordination of tops, bottoms, shoes, accessories, etc. in terms of style, color and material, in order to achieve an overall trendy and generous feeling. However, not everyone focuses on clothing collocation to match clothing with tedious daily life, because it involves style definition, color analysis, dressing coordination and other aspects. At present, the Chinese market needs at least 6 million professional clothing collaborators, and the talent gap is about 4.8 million...

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): G06K9/62
CPCG06F18/2136G06F18/213G06F18/28Y02P90/30
Inventor 张静叶澍井佩光苏育挺
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com