Method and device for extracting biological feature, biological identification method and system

Abstract

The invention provides a method and device for extracting a biological feature, a biological identification method and system. The method for extracting the biological feature comprises the following steps: utilizing a multi-scale multidirectional iteration filter to filter an ROI (region of interest) of an original palm print image and the ROI of an original palm pulse image, thereby extracting texture; performing competitive encoding according to the maximum response of the filter; and respectively taking the obtained encoded images as an identification feature of palm print and the identification feature of palm pulse. According to the method for extracting the biological feature provided by the invention, the calculation volume for extracting the biological feature in the biological identification technology is efficiently reduced, the time for extracting the biological feature is saved and the identification efficiency of the whole biological identification system is increased.

Description

technical field [0001] The invention relates to the technical field of digital image processing of biometric identification technology, in particular to a biometric feature extraction method and device, and a biometric identification method and system. Background technique [0002] The identification technology based on human biological characteristics is referred to as biometric technology, which is an interdisciplinary subject combining biological information technology and computer technology that has emerged in recent years. The so-called biometric technology refers to the use of the inherent physical characteristics of the human body, such as fingerprints, palm prints, irises, faces, etc., and behavioral characteristics, such as voice, handwritten signature, gait, etc., as personalized representations of people. A technique for identifying a person. Compared with traditional keys, passwords and ID cards and other identity representations, human biometrics have the adva...

AI Technical Summary

Problems solved by technology

[0003] Among the many human biological characteristics, various human characteristics have their own advantages and disadvantages: face recognition is an identification method that is most similar to people's daily behavior, but it is affected by the environment, lighting and expressions, and the recognition accuracy is low; Fingerprint recognition is one of the earliest biometric technologies that began to be studied, and it is also one of the more mature technologies. However, the recognition accuracy is low and it is easy to be forged, which has hindered the further development of fingerprint recognition; It is not comfortable enough, and the equipment is relatively expensive; behavioral characteristics such as signature and gait have great limitations in the application field due to the stability of the characteristics themselves; palm feature recognition uses the complex lines on the palm, palm shape and subcutaneous An emerging biometric recognition technology that recognizes features such as veins. Palm-based recognition technology has gradually become a hot spot in research and application. In terms of user comfort, palm features are second only to human faces. The flexibility of the arms makes The collection of various palm features is more convenient and user acceptance is higher

However, smoothing and filtering, edge detection or curve positioning of images by convolution or fast Fourier transform (FFT transform) requires a large amount of calculation, which makes the calculation speed of the filter not high and the efficiency of biometric recognition is low.

Images