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

Classification and aggregation sparse representation face identification method based on nuclear space

A sparse representation and face recognition technology, which is applied in the field of face recognition with sparse representation of classification and aggregation, and can solve the problems of large fitting error and low accuracy.

Active Publication Date: 2016-07-13
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF3 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] Aiming at the above-mentioned shortcomings of the existing face recognition methods, such as large fitting error and low accuracy, the present invention provides a face recognition method based on classification and aggregation sparse representation of kernel space, which heats classification concentration constraints in the sparse expression constraints , so that the samples of the same type are more aggregated in the subspace, and samples of different types are relatively dispersed in the subspace, which is conducive to the clustering of samples in the high-dimensional subspace and improves the recognition effect

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
  • Classification and aggregation sparse representation face identification method based on nuclear space
  • Classification and aggregation sparse representation face identification method based on nuclear space
  • Classification and aggregation sparse representation face identification method based on nuclear space

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] The present invention will be further described below in conjunction with the accompanying drawings.

[0072] A face recognition method based on classification clustering sparse representation of kernel space, comprising the following steps:

[0073] Step 1: Use convolutional neural network to extract face features from face images. In this embodiment, the VGG model (Deepface recognition, O.M. Parkhiand A. Vedaldian and A. Zisserman, Deep Face Recognition, Proceeding of the British Machine Vision Conference (BMVC), 2015) is selected. First, change the size of the face image to 224×224, and then call the VGG model to obtain the features of the face image.

[0074] Step 2: Training classification aggregation dictionary, the training steps are:

[0075] (1) Input training sample, adopt the picture sample training classification dictionary that comprises C kinds, training sample space is represented by X, expresses as X=[X 1 ,X 2 ,...,X c ,...,X C ]∈R D×N , D represe...

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 classification and aggregation sparse representation face identification method based on a nuclear space. The method comprises the following steps: employing a convolutional neural network to extract facial features of a facial image, training a classification and aggregation dictionary, and identifying the image. The classification and aggregation sparse representation face identification method based on the nuclear space considers that the weighting of each training sample to the subspace construction is different and the train samples closed to a class center should have bigger weight to the subspace construction when the train samples are configured to perform sparse representation of test samples, a [Phi](Xc)Wc matrix is adopted to construct a new sparse representation dictionary, and classification concentration constraint terms are added in a sparse representation constraint. Compared with the prior, the classification and aggregation sparse representation face identification method based on the nuclear space is able to effectively reduce the fitting error of test samples in corresponding subspaces to allow samples with the same type to aggregate in the sparse representation so as to improve the face identification performance, enhance the capabilities of processing the non-linear structure and relation, effectively excavate hiding features of complex data and further improve the face identification performance.

Description

technical field [0001] The technical field of pattern recognition of the present invention, in particular, relates to a face recognition method based on classification aggregation sparse representation of kernel space. Background technique [0002] With the development of science and technology, many fields are faced with an increasingly large amount of data, such as seismic data, geophysical data, audio data, astronomical data, industrial control data, genetic data, etc. How to realize flexible and effective processing of these huge data And adaptive expression has gradually become one of the concerns of people. Image processing, information transmission, computer vision and many other fields have been seeking sparse and concise representations of signals and images. The advantage of this sparse representation is that non-zero coefficients reveal the internal structure and essential properties of signals and images. Nonzero coefficients have explicit physical meaning. [...

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): G06K9/00G06K9/62
CPCG06V40/172G06F18/2136G06F18/214
Inventor 刘宝弟王立韩丽莎王延江
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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