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

A Convolutional Neural Network Face Recognition Method Based on Multi-scale Pooling

A convolutional neural and multi-scale technology, applied in the field of face recognition and deep learning, can solve the problems of destroying the original image scale and aspect ratio, loss of important information, etc.

Inactive Publication Date: 2019-06-14
ZHEJIANG UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, when the size of the input face image is different, it is often necessary to intercept and fix the size of the input image. This artificial change of the size of the input face image destroys the scale and aspect ratio of the original image, which will lead to the loss of some important information. lost

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
  • A Convolutional Neural Network Face Recognition Method Based on Multi-scale Pooling
  • A Convolutional Neural Network Face Recognition Method Based on Multi-scale Pooling
  • A Convolutional Neural Network Face Recognition Method Based on Multi-scale Pooling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be further described below in conjunction with accompanying drawings and implementation examples.

[0038] A kind of face recognition method of convolutional neural network based on multi-scale pooling of the present invention, comprises the following steps:

[0039] (1) Collect standard face grayscale images of 100 people, among which 50 pieces are collected for each person, and 5000 standard face grayscale images are obtained as training images; each training image corresponds to a 100×1-dimensional binary face category label vector y lable =[y 1 the y 2 the y 3 … y t ] T , where the category label vector y of the nth face image lable middle element y i The following conditions should be met:

[0040]

[0041] For example, the category label vector y of the first person lable =[1 0 0 ... 0] T , the first element is 1 and the rest are 0. The category label vectors for other face images are similar;

[0042] (2) Convolutional...

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 based on multi-scale pooling. This method uses a multi-scale pooled convolutional neural network to extract the features of face images for face recognition. In the process of constructing the convolutional neural network, the method of alternating convolution and maximum sampling is used to extract the features in depth. In addition, the strategy and steps of multi-scale pooling are adopted for each convolutional layer, and they are input to the full connection. layer so that it has multi-scale, fixed-size feature column vectors. The present invention does not need to intercept or adjust the size of the input face image, and images of different sizes can use the same network for training and recognition. The convolutional neural network based on multi-scale pooling not only solves the problem that the size of the input image can not be fixed, but also enables the network to extract multi-scale face features, and greatly improves the performance of the network, which will promote multi-scale pooling. Wide application of convolutional neural network in face recognition.

Description

technical field [0001] The invention belongs to the fields of deep learning and face recognition, and relates to a convolutional neural network face recognition method based on multi-scale pooling. Background technique [0002] Face recognition is a multidisciplinary biometric technology that integrates biology, psychology, and cognitive science. It uses various technologies such as pattern recognition, image processing, and computer vision. Communication and other fields have a wide range of market application prospects. At present, the technical research on face recognition at home and abroad mainly revolves around the two directions of feature extraction and classification algorithms. The face recognition technology based on the deep convolutional neural network is very mature, but the size of the input face image of the traditional convolutional neural network is fixed (for example: 256*256), this is because the BP backpropagation algorithm is used Updating weights and...

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): G06K9/00G06N3/08
CPCG06N3/084G06V40/168G06V40/172
Inventor 刘云海吴斯
Owner ZHEJIANG UNIV