A palmprint feature extraction method and a hand recognition method
A technology of feature extraction and palmprint, applied in character and pattern recognition, acquisition/organization of fingerprint/palmprint, matching and classification, etc., can solve problems such as long time, lack of resources, occupation of network resources, etc., to reduce the amount of calculation, The effect of reducing the number of parameters and small network models
Pending Publication Date: 2019-04-23
GUANGZHOU JIUBANG DIGITAL TECH
View PDF5 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Most of the palmistry software is mobile, and the computing power and resources of the mobile terminal are often relatively scarce. If it is run through the cloud, it will take up network resources and take a long time
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
[0044] In order to overcome the shortcomings of the existing technology, the palmprint feature extraction method based on the traditional network model and the deep convolutional neural network model has large models, many parameters, long running time, large computing resource requirements, and requires network resources to be occupied and cannot be calculated offline in real time. see figure 1 and figure 2 , the present invention provides a kind of palmprint feature extraction method, comprises the steps:
[0045] S10: Obtain the palmprint image of the user;
[0046] S30: Input the palmprint image into the pre-trained neural network model to obtain the palmprint feature image; wherein, the neural network model includes a convolutional layer, a pooling layer and a fully connected layer of the mobilenet network. Specifically include the following steps
[0047] S31: The palmprint image is input to the convolutional layer of the mobilenet network, and one of the layers of t...
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 relates to a palmprint feature extraction method. The method comprises the following steps of obtaining a palmprint image of a user; inputting the palmprint image into a pre-trained neural network model to obtain a palmprint feature image, wherein the neural network model comprises a convolutional layer, a pooling layer and a full connection layer of a modilenet network. The method specifically comprises the following steps of inputting a palm print image into a convolutional layer of a mobienet network, and selecting one layer of the convolutional layer of the mobienet network to output a palm print shallow-layer feature image; inputting the palmprint shallow feature image into a pooling layer for pooling, and extracting main features of the palmprint; inputting the palmprint main characteristics into a full connection layer, connecting all the palmprint main characteristics, and finally outputting a palmprint characteristic image. The palmprint feature extraction methodprovided by the invention has the advantages of small model, few calculation resources and short running time.
Description
technical field [0001] The invention relates to the technical field of biometric feature recognition, in particular to a palmprint feature extraction method and a palmistry recognition method. Background technique [0002] In the field of biometric identification technology, palmprint recognition technology has high recognition accuracy. Palmprint is unique and basically unchanged for life, and has a wealth of information that can be used for identification. Palmprint recognition technology has also been well applied in the fields of government, banking, social welfare, electronic morning and security defense. The research on palmprint recognition technology is of great significance. [0003] Palmprint feature extraction is a key step in palmprint recognition. At present, among similar technologies, there are mainly methods such as conventional image algorithm technology, image feature recognition based on deep convolutional network, and so on. However, the feature extract...
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 IPC IPC(8): G06K9/00G06N3/04
CPCG06V40/1347G06V40/1365G06N3/045
Inventor 邓裕强何晓芬廖吉平周少煌王飞
Owner GUANGZHOU JIUBANG DIGITAL TECH