Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A face recognition and feature analysis technology, applied in the field of face recognition, can solve problems such as poor robustness, achieve high accuracy, good robustness, and solve the effects of uneven illumination
Inactive Publication Date: 2018-11-27
CHENGDU KOALA URAN TECH CO LTD
View PDF2 Cites 6 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] The purpose of the present invention is to provide a face recognition method based on feature analysis, which solves the technical problem that the current face recognition algorithm has poor robustness in actual open set evaluation and recognition and is not suitable for use in industry
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment 1
[0085] A face recognition method based on feature analysis, comprising the following steps (such as figure 1 shown):
[0086] Step 1: Construct a neural network model for extracting features, use the face data set to train, and obtain a trained neural network model; the neural network model is composed of an Inception module and a ResNet module, and the neural network composed of these two modules The network model is an existing scheme;
[0087] When training the neural network model, the loss function used is:
[0088]
[0089] Among them, m represents the batch size (batchsize), i represents the sample label, and x i Indicates the i-th sample, y i Represents the label of the i-th sample, T represents the transpose operation, j represents the label label, n represents the total number of categories, and λ represents the hyperparameter, which is used to control The weight of , after experiments, the effect is best when λ is 0.01;
[0090] c represents the class cente...
specific Embodiment 2
[0124] Based on Embodiment 1, this embodiment provides a welcome and access control system.
[0125] The system (such as figure 2 Shown) includes a camera arranged at the entrance, the camera is connected to the Ethernet through a local area network, the switch at the entrance to control the opening and closing of the entrance is connected to the Ethernet, and the face recognition server, storage server and display are all connected to the Ethernet.
[0126] The workflow of this system is:
[0127] Step 1: The face recognition system loads the trained neural network model to extract image features;
[0128] Step 2: The face recognition system registers the people who need to use the system for verification (such as all the staff in a building), that is, use the trained neural network model to perform feature extraction on the face images of all the people who need to be verified , build a face feature library;
[0129] Step 3: The camera collects the face image at the entr...
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
Login to view more
Abstract
The invention discloses a face recognition method based on feature analysis, and belongs to the field of face recognition. A neural network model for feature extraction is constructed and trained by using a face data set so as to obtain the trained neural network model; constructing a face feature library; the face image to be recognized is filtered and the processed image is inputted into the trained neural network model to extract the features; and the similarity between the extracted features and the features in the face feature library is calculated, if the similarity is greater than the threshold, the linear discriminant is applied to improve the matching accuracy of the features of which the similarity is greater than the threshold and the recognition result is obtained, or the faceimage corresponding to the feature is discarded. The face recognition method is suitable for multiple actual environments such as the access control system, the bank system, etc. Compared with the mainstream face recognition SDK, the system algorithm has good robustness to the environment change.
Description
technical field [0001] The invention relates to the field of face recognition, in particular to a face recognition method based on feature analysis. Background technique [0002] In recent years, we have witnessed the great success of Convolutional Neural Network (CNNs) algorithms in Face Recognition (FR). Thanks to advanced deep network architectures such as DCNN, ResNet, GoogleNet and discriminative learning methods, deep CNNs improve the performance of FR to an unprecedented level. In general, face recognition can be classified into face recognition and face verification. The former approach is geared toward classifying specific identities, while the latter decides whether a pair of faces belong to the same identity. [0003] In terms of testing methods, face recognition can be evaluated in closed-set or open-set settings. For closed-set evaluation, all test identities are predefined in the training set. Naturally, face images can be classified into the given Identity,...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more