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

Convolutional neural network face recognition method for a fuzzy face image

A convolutional neural network, face image technology, applied in biological neural network models, character and pattern recognition, neural architecture, etc., can solve the problems of small calculation and classification speed, and achieve the effect of good recognition results

Inactive Publication Date: 2019-05-24
TIANJIN UNIV
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When using the LBP algorithm (texture extraction method of local binary pattern) for face recognition, the calculation process is simple, the calculation amount is small, and the classification speed is high, but the recognition is easily affected by factors such as illumination and image rotation.

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
  • Convolutional neural network face recognition method for a fuzzy face image
  • Convolutional neural network face recognition method for a fuzzy face image
  • Convolutional neural network face recognition method for a fuzzy face image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0022] like figure 1 Shown, the convolutional neural network face recognition method for fuzzy face image of the present invention comprises the following steps:

[0023] (1) Calculate the LTP and LPQ eigenvalue matrix of the original face image (image)

[0024] First, divide the original face image into S 0 ,S 1 ,S 2 ,...,S m-1 There are a total of m block areas, and the LTP and LPQ algorithms are calculated on the divided image. The LTP algorithm formula is as follows.

[0025]

[0026]

[0027] The algorithm starts with each pixel i c The eight neighborhoods are sampled, and each sampling point is i P (P=0,1,...,7), t is the algorithm threshold.

[0028] The LPQ alg...

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 convolutional neural network face recognition method for a fuzzy face image, and the method comprises the steps: carrying out the preprocessing of a fuzzy face image, calculating an LTP feature value through employing an LTP algorithm, and obtaining an LTP histogram; Processing and extracting an LPQ characteristic value by using an LPQ algorithm to obtain an LPQ histogram; Combining the LTP histogram with the LPQ histogram to form an LTP _ LPQ combined histogram, and inputting the LTP _ LPQ combined histogram into a convolutional neural network for training; And processing the test image, inputting the obtained LTP _ LPQ joint histogram into the trained convolutional neural network, carrying out feature vector extraction on the histogram, calculating similarity byadopting an Euclidean distance, and finally obtaining an identification result through a SoftMax classifier. According to the invention, a good identification result can be obtained.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a face recognition method of a convolutional neural network for fuzzy face images. Background technique [0002] Face recognition is currently a research hotspot in the field of pattern recognition and computer vision. At present, face recognition methods mainly include recognition methods based on local features, global features, and mixed features. Using LBP algorithm (texture extraction method of local binary pattern) for face recognition has simple calculation process, small calculation amount and high classification speed, but the recognition is easily affected by factors such as illumination and image rotation. Contents of the invention [0003] The purpose of the present invention is to provide a convolutional neural network face recognition method for fuzzy face images aiming at the technical defects existing in the prior art. [0004] The technical scheme a...

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): G06K9/00G06K9/46G06N3/04
Inventor 高静于子涵聂凯明徐江涛史再峰
Owner TIANJIN UNIV