Fingerprint feature extraction device, storage medium storing instructions to perform fingerprint feature extraction method, and method for training neural network to extract feature information of fingerprint

A non-transitory computer-readable storage medium storing computer executable instructions, wherein the instructions, when executed by a processor, cause the processor to perform a fingerprint feature extraction method, the method comprising:

• calculating a similarity based on feature information of the input fingerprint and feature information of a registered fingerprint stored in the fingerprint feature extraction device;
• when the similarity does not exceed a predetermined threshold, comparing the feature information of the input fingerprint with feature information of a matching fingerprint previously matched with the registered fingerprint;
• generating additional modification information based on a result of the comparison between the feature information of the input fingerprint and the feature information of the matching fingerprint;
• modifying the feature information of the registered fingerprint based on the additional modification information;
• pairing the modified feature information of the registered fingerprint with the input fingerprint;
• and
• inputting results of pairing to a pre-trained neural network to output the fingerprint feature extraction result.

A method of training a neural network for fingerprint feature extraction using a fingerprint feature extraction device, the method comprising:

• calculating a similarity based on feature information of the input fingerprint and feature information of a registered fingerprint stored in the fingerprint feature extraction device;
• when the similarity does not exceed a predetermined threshold, comparing the feature information of the input fingerprint with feature information of a matching fingerprint previously matched with the registered fingerprint;
• generating additional modification information based on a result of the comparison between the feature information of the input fingerprint and the feature information of the matching fingerprint;
• modifying the feature information of the registered fingerprint based on the additional modification information;
• pairing the modified feature information of the registered fingerprint with the input fingerprint;
• and
• training the neural network to output a fingerprint feature extraction result with respect to the input fingerprint by using results of pairing as training input data and the modified feature information of the registered fingerprint as training label data.