Method for fingerprint image mark direction calculation and image segmentation based on BP neural network

Abstract

The invention discloses a fingerprint image grain direction calculating and image dividing method based on a BP neuronic network and the method comprises the following steps: (1), dividing a fingerprint image I with a width of m and a height of n into blocks W(i, j) which are not mutually overlapped with a size of Omega*Omega(15*15); (2) using a method based on gradient vectors to calculate the grain direction O(W(k, l)) of W(k, l); (3), using the method of the BP neuronic network to confirm the accuracy on the result of the direction O(W(k, l)) of each image block and carrying out the primary cutting on the image; if the direction of the image block W(i, j) is correct, then the image block is set to be a foreground and M(W(i, j)) is equal to 1; if the direction is wrong, then the image block is set to be a background and M(W(i, j)) is equal to 0. The method can better process the fingerprint image with low quality, is high in the accuracy rate of the characteristic extracting result, is low in calculating complexity and is accurate in image cutting.

Description

technical field [0001] The invention relates to a method for calculating the direction of fingerprint lines and segmenting images based on a BP neural network, which is used for low-quality images and has obvious effects. Background technique [0002] Fingerprint recognition technology has a wide range of applications. In daily life, we often encounter occasions that require identity authentication, such as logging in to the operating system, using certain software, going to the bank to withdraw money, identifying suspects, and entering important military locations. As a more convenient, safer and more reliable identity authentication method, fingerprint recognition technology can effectively avoid the defects of traditional identity authentication methods. However, the automatic fingerprint recognition technology still needs to be improved. The test results of the international fingerprint verification competition FVC (Finger-print Verification Competition) show that there ...

AI Technical Summary

Problems solved by technology

The method based on the direction field model uses heuristic knowledge to predict the general trend of the global texture according to the position of the singular point, so the predicted texture does not represent the real direction of the texture

However, the current fingerprint cutting algorithm does not segment from the perspective of whether the grain direction can be calculated correctly, but separates the areas without grains and the areas with unrecoverable grains from the perspective of visual observation. Such a segmentation method is incomplete and will Seriously affect the accuracy of recognition

[0004] The deficiencies in the existing fingerprint grain direction calculation and image cutting methods are: (1), the existing algorithm is inefficient for low-quality fingerprint images; (2), it is easy to interfere and make mistakes for images with large noise; (3), the current Some image cutting methods cannot accurately cut fingerprints

Images