A fine-grained classification method for fashion women's wear images based on component 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.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0030] Example 1: as Figure 1-2 As shown, a fine-grained classification method for fashion women's clothing images based on component detection and visual features. First, the inputted fashion women's clothing images to be classified and the fashion women's clothing images in the fashion women's clothing training set are subjected to body part detection; secondly, the components are extracted respectively. The detected fashion women's clothing image and the four underlying features of HOG, LBP, color histogram and edge operator of the training fashion women's clothing image are obtained to obtain the image after feature extraction; then, the defined visual feature descriptor is compared with the extracted four kinds of The underlying features are matched, and random forest and multi-class SVM supervised learning are used to train the fine-grained classifier model; finally, through the trained fine-grained classifier, fine-grained classification is performed on the fashion wome...
Embodiment 2
[0036] Embodiment 2: wherein the improved DPM model is composed of a root model and several component models, and the object model of n components 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 for the ith component, b is a deviation loss coefficient, at l 0 scale layer, with (x 0 ,y 0 ) is the anchor point and the response score is:
[0037]
[0038] in, is the response score of the root model, v i is a two-dimensional vector that specifies the coordinates of the anchor point position of the ith filter (that is, the standard position without deformation) relative to the root position, is the response score of the n-part model, λ is the number of levels of feature maps computed at twice the resolution in the feature pyramid;
[0039] After calculating the response score, transform the response of the component filter and consider the spatial uncertainty, the response transformation calculation formul...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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