Unlock instant, AI-driven research and patent intelligence for your innovation.

Hardware function for solidifying fingerprint identification algorithm

A fingerprint recognition and algorithm technology, applied in the field of biometric recognition algorithms, can solve the problems of customization and lack of biometric recognition algorithms, etc., and achieve the effect of increasing the number of recognition comparisons, improving the recognition pass rate, and increasing the calculation time

Inactive Publication Date: 2018-11-02
百帝安(北京)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

The operating efficiency of the algorithm depends on the mathematical logic structure and operational efficiency of the algorithm itself, as well as the main frequency of the MCU and the number of SRAMs. There are also DSP and floating-point operation logic and trigonometric function instruction sets inside the high-end MCU, which can be improved. The computational efficiency of the algorithm, but there is no IP core specially customized for the biometric algorithm

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Hardware function for solidifying fingerprint identification algorithm
  • Hardware function for solidifying fingerprint identification algorithm
  • Hardware function for solidifying fingerprint identification algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0004] 1. Function description

[0005] Function name: void MatchFeatures(lpFeatureVect pfile, lpFeatureVect psearch, lpPairVect ppairs)

[0006] Function function: Calculate the similarity between images.

[0007] Input parameters: lpFeatureVect pfile (fingerprint library feature vector), lpFeatureVect psearch (fingerprint feature vector participating in verification)

[0008] Output parameters: lpPairVect ppairs (number of matching feature points)

[0009] Result: success: 0<=number of matching feature points<=MAX_PAIR_NUM

[0010] Failed: Negative number or above MAX_PAIR_NUM.

[0011] 2. Code

[0012]

[0013]

[0014]

[0015]

[0016]

[0017]

[0018]

[0019]

[0020] The above code calculates the correlation coefficient between two matrices, and the two matrices are two images.

[0021] The formula for the correlation coefficient between two matrices X and Y is as follows:

[0022]

[0023] The code calculates the correlation coefficie...

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

No PUM Login to View More

Abstract

The present invention relates to a hardware IP core technology for solidifying a software program of a fingerprint identification algorithm into a hardware logic unit, and belongs to the field of biological identification algorithms. At present, an MCU used by a fingerprint identification algorithm in an embedded platform is a universal chip. Operation efficiency of the algorithm depends on a mathematical logical architecture and computation efficiency of the algorithm. Dominant frequency of the MCU, an SRAM and universal instruction sets are mainly used, and customized IP cores and instruction sets are not present. To increase the computation efficiency of the fingerprint identification algorithm in an embedded MCU, the present invention extracts a part which needs a large amount of computation in core software of the fingerprint identification algorithm, optimizes and logically simplifies the part and solidifies the part into the hardware logic unit to form a special IP core and instruction sets for fingerprint identification. With the instruction sets and the IP core, computation time of the algorithm can be improved, an identification pass rate of the algorithm can be increased, and the number of identification and comparison of the algorithm and other parameters of the algorithm can be improved.

Description

technical field [0001] The invention relates to a hardware IP core technology that solidifies a fingerprint recognition algorithm software program into a hardware logic unit, and belongs to the field of biometric recognition algorithms. Background technique [0002] At present, the fingerprint identification algorithm runs on the embedded platform in software mode, and the MCU used is mostly a general-purpose chip. The operating efficiency of the algorithm depends on the mathematical logic structure and operational efficiency of the algorithm itself, as well as the main frequency of the MCU and the number of SRAMs. There are also DSP and floating-point operation logic and trigonometric function instruction sets inside the high-end MCU, which can be improved. The computing efficiency of the algorithm, but there is no IP core specially customized for the biometric algorithm. Biometric products have been popularized in various fields, and there is a demand for products with em...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F8/30
CPCG06F8/31
Inventor 许建清
Owner 百帝安(北京)科技有限公司