A multi-spectral palmprint fine texture extraction and recognition method

Abstract

Disclosed are a multispectral palm-print fine-texture extraction and an identification method and an acquisition platform thereof, both of which belong to the field of identity identification. The invention aims at providing a multispectral palm-print fine-texture extraction and identification method which acquires palm-print images under radiation of a plurality of kinds of spectrums and obtains extremely accurate palm-print textures after processing the palm-print images acquired through multiple spectrums. The method includes the following steps: multispectral image acquisition, single-spectrum image fine-texture feature extraction, multispectral image fine-texture feature fusion, morphological processing and identification of cross textures and textures shaped like a Chinese character 'mi'. The method is not only capable of displaying clearly a main line on the palm, but also capable of extracting shallow and fine textures so that fine textures with special shapes, such as cross textures and textures shaped like a Chinese character 'mi' are identified.

Description

technical field [0001] The invention belongs to the field of identification. Background technique [0002] In recent years, more efforts have been invested in the research of biometric technology at home and abroad, especially in the United States, Europe and other places. At present, the main researched biometrics include human fingerprints, irises, palm prints, voice, handwriting, face and DNA, etc. Since these features have the uniqueness and stability inherent in the human body, they cannot be copied, stolen or forgotten. Palmprint recognition is a relatively new biometric recognition technology proposed in recent years. The factors that affect the accuracy of palmprint recognition mainly include hardware and software, namely the clarity of the image collected by the palmprint image collection device and the efficiency of the recognition algorithm. [0003] When traditional palmprint image acquisition equipment collects images, it generally puts the palm under the ligh...

AI Technical Summary

Problems solved by technology

[0006] The instrument was proposed. This special acquisition instrument uses a computer to control the switching of four spectral light sources: infrared, red, green, and blue. What is collected is the image of the entire palm. The details of the palmprint are not clear, and the fine lines on the palm cannot be extracted.

In 2012, a high-resolution multi-spectral acquisition system based on a mask and double Amici prisms was proposed. This multi-spectral acquisition system requires the use of a prism splitter to disperse the transmitted light into spectra at multiple wavelengths. Calibration is required, the structure of the device is complicated, and the collection process is cumbersome, which is not conducive to the promotion and use of the device

In 2013, a palmprint extraction and recognition method (application number CN201310137558) was proposed. This method works well when extracting deep and long main lines on the palm. For other small lines on the palm, this method will lose many details; although in The "growth" method is used to connect the intermittent main lines in the process of extracting ridges, but the extracted main lines still have a small number of break points, and the extracted ridges are not smooth

Images