A finger vein recognition method and system based on correlation semantic feature learning
A technology of finger veins and semantic features, applied in the field of computer vision, can solve the problems of binary codes without semantic information, reduce feature interpretability, and low interpretability, so as to achieve good promotion and application value, improve learning accuracy, and discriminating effect
Active Publication Date: 2022-04-12
SHANDONG INSPUR SCI RES INST CO LTD
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, most of the existing binary encodings have no semantic information, which reduces the interpretability of features
Therefore, how to effectively solve the problems of low interpretability and poor validity of existing features has important research significance and application value.
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
[0029] The finger vein recognition method based on correlation semantic feature learning of the present invention firstly defines codes with semantic information according to the characteristics of finger veins, and constructs a multi-code learning model according to the codes of the constructed semantic information, and the multi-code learning model is used for all codes at the same time Carry out learning, and obtain the correlation information of multiple codes during the learning process, and improve the learning accuracy of each code; by inputting the test image into the multi-code learning model, multiple code features of the test image are obtained, and the obtained multiple The coding features are compared with the coding features of the registered user, and based on the obtained similarity, it is judged whether the test image and the registered user are the same user.
[0030] The method specifically includes the following steps:
[0031] S1. Training phase: building ...
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 finger vein recognition method and system based on correlation semantic feature learning, belonging to the technical field of computer vision. The finger vein recognition method based on correlation semantic feature learning of the present invention defines codes with semantic information according to the characteristics of finger veins, constructs a multi-code learning model according to the codes of the constructed semantic information, and performs multi-code learning on all codes simultaneously. learning, and obtain the correlation information of multiple codes during the learning process to improve the learning accuracy of each code; by inputting the test image into the multi-code learning model, the multiple code features of the test image are obtained, and the multiple codes acquired The feature is compared with the encoded feature of the registered user to determine whether the test image and the registered user are the same user. The finger vein recognition method based on the correlation semantic feature learning of the invention can obtain the semantic information of the image, has better discrimination, and has good promotion and application value.
Description
technical field [0001] The invention relates to the technical field of computer vision, and specifically provides a finger vein recognition method and system based on correlation semantic feature learning. Background technique [0002] Feature extraction is an important step in image processing, pattern recognition and other fields. Compared with other types of features, binary encoding has the advantages of simplicity and less storage space. However, most of the existing binary encodings have no semantic information, which reduces the interpretability of features. Therefore, how to effectively solve the problems of low interpretability and poor validity of existing features has important research significance and application value. Contents of the invention [0003] The technical task of the present invention is to address the above-mentioned problems and provide a finger vein recognition method based on correlation semantic feature learning that can obtain semantic inf...
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): G06V40/145G06N20/00
CPCG06N20/00G06V40/1365
Inventor 袭肖明于治楼
Owner SHANDONG INSPUR SCI RES INST CO LTD