Recognition method for finger vein identification based on Multiple loss function

Abstract

The invention relates to a biological recognition technology, in particular to a recognition method for finger vein identification. The recognition method for finger vein identification based on a Multiple loss function comprises the following specific steps: acquiring finger vein sample images of at least two persons, and acquiring at least two images of each finger; dividing the acquired vein sample images into three groups: an anchor point group in which a finger vein image of an identification object is taken as an anchor point, a positive group in which another finger vein image of the same person is taken as the identification object as a positive sample group, and a negative group in which a finger vein image of a person different from the identification object is taken as a negative sample group; putting the three groups of data into a deep residual error network for training, and obtaining an embeddings vector by using Multiple loss; and calculating the Euclidean distance between every two embeddings, and the short distance indicates the same person, and the long distance indicates different persons. The personal identity can be quickly and accurately identified, and themethod is applied to a vein identification system and has the advantages of small size, friendly interface and proper price.

Description

technical field [0001] The invention relates to biometric identification technology, in particular to an identification method for verifying identity by finger veins. Background technique [0002] Traditional identification methods include identity identification items (such as keys, certificates, ATM cards, etc.) and identity identification (such as user names and passwords). It is easy to be impersonated or replaced by others. Biometric technology is more secure, confidential and convenient than traditional identification methods. Biometric identification technology has the advantages of not easy to forget, good anti-counterfeiting performance, not easy to forge or be stolen, "carry" with you, and available anytime and anywhere. Light propagation technology can ensure that high-contrast finger vein images can be captured without being affected by any defects and blemishes such as wrinkles, textures, roughness, dryness and humidity on the skin surface. Since the finger v...

AI Technical Summary

Problems solved by technology

[0007] For the above method, for the global population of 7.594 billion, it is impossible to collect finger vein pictures of all people and classify 7.594 billion

Second, there is no way to accurately determine the identities of 7.594 billion people through probability

Images