Unlock instant, AI-driven research and patent intelligence for your innovation.

Projection operator and wavelet transformation-base palmprint recognition method

A technology of wavelet transform and projection operator, applied in the field of palmprint recognition, can solve the problems affecting the practicality of the method

Inactive Publication Date: 2017-02-15
北京京航计算通讯研究所
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the feature extraction method based on subspace, the dimension of the feature generally needs to be set artificially, which affects the practicability of the method

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to make the purpose, content, and advantages of the present invention clearer, the specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0032] For solving the problem of prior art, the present invention provides a kind of palmprint recognition method based on projection operator and wavelet transform, and it comprises the steps:

[0033] Step S1: constructing a palmprint database;

[0034] Step S2: Carry out wavelet transform to the image in the palmprint database;

[0035] Step S3: Construct the null space of the projection operator with the palmprint data after wavelet transformation;

[0036] Step S4: use the method of singular value decomposition to obtain the discriminant projection of the space;

[0037] Step S5: Using the discriminant projection to perform feature extraction on the palmprint data to obtain a dimensionally reduced palmprint dat...

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 belongs to the field of palmprint recognition under illumination change and relates to a projection operator and wavelet transformation-base palmprint recognition method. The method of the invention is a subspace feature extraction-based method. According to the method, dimensionality reduction is performed on high-dimensionality palmprint data, and therefore, computation amount can be decreased, and at the same time, the storage space of the data is decreased; the intrinsic relationship of a projection operator and wavelet transformation is considered; the projection operator and the wavelet transformation are combined organically and ingeniously; the subspace decomposition feature of the projection operator is utilized, so that artificial setting of feature dimensionality is avoided; and a nearest neighbor classifier is selected according to the optimal approximation feature of subspace projection. The method of the invention has a certain robustness and is insensitive to the change of the illumination of a palmprint image and has a high recognition rate.

Description

technical field [0001] The invention belongs to the field of palmprint recognition with illumination changes, in particular to a palmprint recognition method based on projection operator and wavelet transform. Background technique [0002] At present, people's work and life are more and more inseparable from identification and identity verification. As a new identification technology, palmprint recognition technology has received more and more attention. How to represent palmprints is a difficult point and a hotspot in palmprint recognition. Effective representation of palmprint is the key to improve the performance of palmprint recognition technology, and the feature extraction method based on subspace is one of the effective methods to represent palmprint. It is supported by statistical theory and has achieved good results. However, in the feature extraction method based on subspace, the dimension of the feature generally needs to be set artificially, which affects the pr...

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): G06K9/00G06T11/00G06T3/00
CPCG06T11/003G06V40/1347G06V40/1365G06T3/067
Inventor 赵峰张冠英徐均张卫崔媛媛
Owner 北京京航计算通讯研究所