Vein Fusion Recognition Method of Hand Shape and Arm Based on Cumulative Matching and Equal Error Rate

A technology of equal error rate and fusion recognition, applied in the field of information perception and recognition, it can solve the problems of noise of collected data and poor robustness, and achieve the effect of reducing accidental errors, high reliability and excellent fusion recognition performance.

CN109190460BActive Publication Date: 2022-02-11NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2022-02-11

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a hand shape / arm vein fusion recognition method based on cumulative matching and equal error rate curves, which belongs to the field of information perception and recognition technology. The method proposes two-level weights for the recognition performance of two biological features: first, using the CMC curve According to the characteristics of the above curve, the global weight of fractional fusion is calculated according to the area above the curve; then the optimal classification threshold is obtained through the ERR curve, and then the adaptive weight is calculated, and the two are multiplied as the total weight and fractional weighted fusion is performed. This method has It is conducive to highlighting the advantages of biological features, and multi-biological feature fusion can make up for the lack of single-modal biometric recognition by utilizing the independence and complementarity between features.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of information perception and recognition, and relates to a hand shape / arm vein fusion recognition method based on cumulative matching and equal error rate curves. Background technique

[0002] Biometric identification technology is the use of the human body's own inherent biological and behavioral characteristics for personal identification. With the development of computer science and technology, the role of identification technology based on biometric identification in social security is becoming increasingly important. Single-modal identification technology has problems such as poor reliability, poor robustness, and noise in collected data, which can no longer meet the current needs. Multi-biological feature fusion utilizes the independence and complementarity between features, performs fusion calculations on biological features from different dimensions, maximizes the use of its advantages, reduces the...

Examples

Embodiment Construction

[0088] In order to make the object, technical solution and effect of the present invention clearer and clearer, the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be pointed out that the specific implementations described here are only used to explain the present invention, not to limit the present invention.

[0089] Such as figure 1 as shown, figure 1 It is the overall framework diagram of the system of the hand-shaped arm vein fusion recognition method based on cumulative matching and equal error rate of the present invention, and the specific steps are as follows:

[0090] Step 1: Take pictures of hands and arms, and establish a database of users to be authenticated;

[0091] In order to obtain vein information, a near-infrared camera is used to capture images of the hand and forearm, such as figure 2 as shown, figure 2 For near-infrared hand image and contour extraction. where hand ima...