A Flash Search and Comparison Method for Large-Scale Distributed Palm Context Data
A distributed and large-scale technology, applied in network data retrieval, network data query, other database retrieval and other directions, can solve the problems of slow recognition speed, slow comparison speed, difficult to meet the needs of large traffic and high frequency use, etc. The effect of overcoming slow speed and breaking through development bottlenecks
Active Publication Date: 2021-12-07
广州麦仑信息科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
There are many limitations in traditional palm vein recognition. Although the recognition accuracy is high, the recognition speed is slow and it is difficult to meet the needs of high-volume and high-frequency use.
The present invention proposes a large-scale distributed full-palm venation data flash search comparison method, which not only utilizes the vascular venation distribution characteristics of the entire palm, but also adopts the method of combining the global feature vector index and local feature vector index of deep learning, Introduce the inverted index method widely used in network search engines to overcome the technical difficulties of traditional palm pulse recognition and break through the bottleneck of slow comparison speed
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
[0037] In order to make the purpose and technical solution of the present invention clearer, the present invention will be further clearly and completely described below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain the technical solutions of the present invention, and other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.
[0038] A flash search and comparison method for large-scale distributed full palm vein data, including three parts: feature extraction and calculation for the full palm vein image, construction of feature database and search comparison, refer to figure 1 As shown, the specific implementation steps are as follows:
[0039] S1. Perform feature extraction calculation on the whole palm vein image, specifically:
[0040] S1-1. Construct multi-scale vein feature space, let the or...
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 method for flash search and comparison of large-scale distributed full-palm vein data, which includes three parts: performing feature extraction and calculation on the full-palm vein image, constructing a feature database, and searching and comparing. The technical solution provided by the present invention draws on the idea of GIS and the method of webpage search, and is applied to the search and comparison of palm pulse data, which can realize the flash speed of massive palm pulse data in large-scale, large-flow and high-frequency application scenarios Comparison and recognition solves the technical problem that traditional palm vein recognition cannot be used in large-scale and high-flow applications due to its slow speed.
Description
technical field [0001] The invention belongs to the field of biological feature recognition, relates to the technical fields of computer image processing and pattern recognition, and particularly relates to a flash search and comparison method for large-scale distributed whole palm context data. Background technique [0002] With the development and application of deep learning and other artificial intelligence technologies, more and more biometric identification technologies have been developed and applied. At present, the application of face recognition has been very extensive, but due to the lack of differentiating features among individuals, no matter how powerful the algorithm is, it is difficult to distinguish two people with similar looks, such as twins. Therefore, face recognition technology is difficult to apply to the individual identification of super-large-scale crowds. Palm Vein Recognition is a technology that uses the distribution characteristics of blood ves...
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): G06F16/51G06F16/55G06F16/583G06F16/953G06K9/00
CPCG06F16/51G06F16/55G06F16/583G06F16/953G06V40/1347G06V40/1365G06V40/14G06V10/449G06V10/431G06V30/2504G06V30/19173G06V40/50
Inventor 余孟春谢清禄薛勇波
Owner 广州麦仑信息科技有限公司