Manifold learning network and its computer vision image set classification method

A computer vision and manifold learning technology, applied in the field of manifold learning, can solve the problems of complex back-propagation calculation and many learning parameters, and achieve the effect of simple and effective training, avoiding matrix calculation, and reducing complexity.

Active Publication Date: 2021-02-26
聚时科技(上海)有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For this type of algorithm, the key point is to perform the backpropagation calculation of the Riemann matrix on the manifold. It can be seen that this type of algorithm can achieve higher classification results on complex data sets, but its backpropagation calculation is more complicated. , and the network needs to learn more parameters

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
  • Manifold learning network and its computer vision image set classification method
  • Manifold learning network and its computer vision image set classification method
  • Manifold learning network and its computer vision image set classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is carried out on the premise of the technical solution of the present invention, and detailed implementation and specific operation process are given, but the protection scope of the present invention is not limited to the following embodiments.

[0050] Such as figure 1 As shown, the present invention provides a manifold learning network, comprising: an input layer for obtaining a symmetric positive definite manifold corresponding to an image set to be classified; a fully connected layer for feature extraction of data received by the input layer; The correction layer is used to adjust the extracted feature values ​​to maintain the consistency of the sample space; the Riemann pooling layer is used to perform pooling operations on features to reduce network complexity; the second logarithmic mapping layer is used to convert the ...

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 present invention relates to a manifold learning network and a method for classifying computer vision image sets based on it. The manifold learning network includes an input layer, a fully connected layer, a correction layer, a Riemann pooling layer, a second logarithmic mapping layer and an output layer , which is mainly used to classify the collected video sequences, by building a simple learning network on the Riemannian manifold, and using bidirectional two-dimensional principal component analysis technology to optimize the weight parameters to complete the nonlinear feature extraction and Classification. Compared with the prior art, the present invention can effectively improve the object classification accuracy in complex scenes, and at the same time, the training time is shorter.

Description

technical field [0001] The invention relates to the field of manifold learning, in particular to a manifold learning network and a method for classifying computer vision image sets based on it. Background technique [0002] In the field of computer vision, the problem of classification of image sets has recently received extensive attention from researchers. The main reason is that compared with the traditional single-picture-based classification task, the image set can be more flexible and effective for feature representation. For the image set classification task, each image set contains multiple pictures belonging to the same category, and they have certain differences in illumination, pose, and resolution. In the era of big data, classification problems based on image sets have been widely and successfully applied in video-based face recognition, surveillance, identity authentication, and biometric information recognition, and in these applications, the method of manifo...

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 Patents(China)
IPC IPC(8): G06K9/62
CPCG06F18/24G06F18/214
Inventor 郑军王锐罗长志
Owner 聚时科技(上海)有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap