Network construction method, recognition method and system for face recognition
A construction method and artificial neural network technology, applied in the face recognition network construction method, recognition method and system field, can solve the problems that the performance cannot meet the needs of practical applications, etc., achieve good effect, strong learning ability, and strong generalization ability Effect
Active Publication Date: 2019-03-15
HENGFENG INFORMATION TECH CO LTD
View PDF5 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0008] The purpose of the present invention is to overcome the defect that the performance of the traditional method in the existing face analysis technology cannot meet the needs of practical applications, thereby proposing a network construction method for face recognition and a face recognition method based on the network construction. Identification method and system
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0062] The present invention will be further described now in conjunction with accompanying drawing.
[0063] The present invention provides a face analysis method based on multi-feature deep learning, including:
[0064] Step 1), face detection and preprocessing are performed on the picture.
[0065] Step 2), face analysis is carried out to the face picture obtained in step 1), and input to the deep network of human face gender recognition and the deep network of human face age estimation respectively.
[0066] Step 3), the gender of the predicted face picture output by the face gender recognition deep network, male or female; the age integer value of the estimated face picture output by the face age estimation deep network output, how many years old.
[0067] 1. Construction of face gender recognition network:
[0068] In the above-mentioned technical scheme, described step 2) provides a kind of face gender identification method, as figure 1 As shown, a deep network syst...
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 deeper layer network constructing method used for gender identification or age estimation based on human face. The method includes a step (101) dividing all training pictures into a plurality of groups; (102) extracting high layer features of a group of pictures based on a convolution neural network and thereby obtaining a first matrix composed of the high layer feature vectors, and extracting low layer and global features of the same group of the training images based on an artificial neural network and thereby obtaining a second matrix composed of the low layer feature vectors, obtaining a group of gender identification or age estimation results based on the extract first matrix, the second matrix and the defined judgment formula, wherein the values of a first weight matrix W1, a second weight matrix w2, an offset matrix b and an adjusting weight beta in the defined judgment formula are updated by utilizing an error back propagation algorithm and the final values of the parameters are obtained and the network construction is completed. Judgment of age and gender of a human face is performed based on the judgment formula determined according to the values of the parameters when the network construction is completed.
Description
technical field [0001] The present invention relates to the technical fields of computer vision and deep learning, in particular to a network construction method, recognition method and system for face recognition. Background technique [0002] As an object that is very difficult for computers to recognize and analyze, human face has attracted extensive attention of researchers since the 1990s. Successful and effective face analysis has great application prospects in the fields of intelligent surveillance, video indexing, and demographic information statistics. Face analysis mainly includes face gender recognition and face age estimation. The accuracy of gender classification and the average absolute error of age estimation are the key indicators of the two. [0003] The current related research in the field of face analysis is based on the "manual" determination of feature descriptors to represent faces, combined with classifier algorithms or regression algorithms. Manual...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/66G06N3/02
Inventor 李松斌蒋雨欣刘鹏戴琼兴邓浩江
Owner HENGFENG INFORMATION TECH CO LTD