# US 2026/0073728 A1 · Fingerprint recognition method and fingerprint recognition device

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0073728 A1
- Document ID: US20260073728A1
- Status: Published application
- Kind: A1
- Application number: 18/925,616
- Filed: 2024-10-24
- Published: 2026-03-12
- Earliest claimed: 2024-09-10
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Hanhui Li; Xiaochun Yan; Chunmiao Jiang; Huaiwen Bai; Jiangbo Chen; Yanjun Chen
- Web page: https://patentgrep.com/patent/US20260073728A1

## CPC

- G06V 40/1353: {Extracting features related to minutiae or pores}
- G06V 10/82: using neural networks
- G06V 40/1365: {Matching; Classification}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A fingerprint recognition method includes receiving an input fingerprint image; dividing the input fingerprint image into M image blocks, wherein M is an integer greater than 1, calculating a score of N image blocks among the M image blocks by inputting successive ones of the M image blocks into a neural network for fingerprint recognition until the score of the N image blocks meets a preset condition, wherein the score is a sum score, and N is an integer less than or equal to M, and terminating calculating the scores of remaining image blocks among the M image blocks, and recognizing a legitimacy of a fingerprint in the input fingerprint image.

## Claims

### Claim 1

A fingerprint recognition method comprising:
receiving an input fingerprint image;
determining a plurality of minutiae appearing in the input fingerprint image, wherein the plurality of minutiae number M; and
recognizing a legitimacy of a fingerprint in the input fingerprint image by performing an iterative method comprising:
obtaining an image block from the input fingerprint image, wherein the image block corresponds to a next one of the plurality of minutiae;
calculating a score of the image block by inputting the image block into a neural network for fingerprint recognition;
adding the score of the image block to a sum score of each image block previously obtained, such that the sum score is calculated using a plurality of image blocks numbering N; and
recognizing the legitimacy of the fingerprint in the input fingerprint image upon the sum score satisfying a preset condition.

### Claim 2 (depends on 1)

The fingerprint recognition method according to claim 1, wherein the preset condition includes a first condition,
wherein the first condition indicates that a sum score is greater than or equal to a product of M and a preset threshold score, and
wherein the recognizing the legitimacy of the fingerprint in the input fingerprint image comprises:
recognizing the fingerprint in the input fingerprint image as true upon the sum score meeting the first condition.

### Claim 3 (depends on 1)

The fingerprint recognition method according to claim 1, wherein the preset condition includes a second condition,
wherein the second condition indicates that a sum of the sum score and a first value is less than a product of M and a preset threshold value, and the first value is equal to a product of a difference between M and N and a maximum score that the neural network may output, and
wherein the recognizing the legitimacy of the fingerprint in the input fingerprint image comprises:
recognizing the fingerprint in the input fingerprint image as false upon the sum score meeting the second condition.

### Claim 4 (depends on 1)

The fingerprint recognition method according to claim 1, further comprising:
determining a center coordinate of the input fingerprint image; and
determining a first number of image blocks corresponding to a first number of minutiae closest to the center coordinate among the plurality of image blocks and a second number of image blocks corresponding to a second number of minutiae farthest from the center coordinate among the plurality of image blocks as M image blocks, wherein a sum of the first number and the second number is equal to M.

### Claim 5 (depends on 4)

The fingerprint recognition method according to claim 4, wherein determining the plurality of minutiae appearing in the input fingerprint image comprises extracting the plurality of minutiae from the input fingerprint image using a feature extraction algorithm,
wherein each image block of the plurality of image blocks is centered on a different minutia of the plurality of minutiae.

### Claim 6

A fingerprint recognition method comprising:
receiving an input fingerprint image;
dividing the input fingerprint image into M image blocks, wherein M is an integer greater than 1;
calculating a score of N image blocks among the M image blocks by inputting successive ones of the M image blocks into a neural network for fingerprint recognition until the score of the N image blocks meets a preset condition, wherein the score is a sum score, and Nis an integer less than or equal to M; and
terminating calculating the scores of remaining image blocks among the M image blocks, and recognizing a legitimacy of a fingerprint in the input fingerprint image.

### Claim 7 (depends on 6)

The fingerprint recognition method according to claim 6, wherein the preset condition includes a first condition,
wherein the first condition indicates that a sum of the scores of the N image blocks is greater than or equal to a product of M and a preset threshold score, and
wherein the recognizing the legitimacy of the fingerprint in the input fingerprint image comprises:
recognizing the fingerprint in the input fingerprint image as true upon the scores of the N image blocks meeting the first condition.

### Claim 8 (depends on 6)

The fingerprint recognition method according to claim 6, wherein the preset condition includes a second condition,
wherein the second condition indicates that a sum of a sum of the scores of the N image blocks and a first value is less than a product of M and a preset threshold value, and the first value is equal to a product of a difference between M and N and a maximum score that the neural network may output, and
wherein the recognizing the legitimacy of the fingerprint in the input fingerprint image comprises:
recognizing the fingerprint in the input fingerprint image as false upon the scores of the N image blocks meeting the second condition.

### Claim 9 (depends on 6)

The fingerprint recognition method according to claim 6, wherein the neural network comprises a depthwise separable convolutional network, and a number of output channels of point convolutions of the depthwise separable convolutional network is consistent with multiplication and accumulation operations supported by a fingerprint recognition device performing the fingerprint recognition method.

### Claim 10 (depends on 9)

The fingerprint recognition method according to claim 9, wherein the depthwise separable convolutional network includes a separable convolutional structure of which the number of output channels is a predetermined number,
wherein the separable convolutional structure includes depth-wise convolutional layers and point-wise convolutional layers, and
wherein a convolution operation of the depth-wise convolution layers is accelerated using a convolution hardware accelerator of the fingerprint recognition device, and a convolution operation of the point-wise convolution layers is accelerated using a multiplication and accumulation hardware accelerator of the fingerprint recognition device.

### Claim 11 (depends on 6)

The fingerprint recognition method according to claim 6, wherein the dividing of the input fingerprint image into the M image blocks comprises:
obtaining a plurality of image blocks by dividing the input fingerprint image;
determining a center coordinate of the input fingerprint image; and
determining a first number of image blocks closest to the center coordinate among the plurality of image blocks and a second number of image blocks farthest from the center coordinate among the plurality of image blocks as the M image blocks, wherein a sum of the first number and the second number is equal to M.

### Claim 12 (depends on 11)

The fingerprint recognition method according to claim 11, wherein the obtaining the plurality of image blocks by dividing the input fingerprint image comprises:
extracting a plurality of minutiae from the input fingerprint image using a feature extraction algorithm,
wherein each image block of the plurality of image blocks is centered on a different minutia of the plurality of minutiae.

### Claim 13

A fingerprint recognition device comprising:
a receiving module configured to receive an input fingerprint image;
an obtaining module configured to obtain M image blocks by dividing the input fingerprint image, wherein M is an integer greater than 1; and
a recognition module configured to calculate a score of N image blocks among the M image blocks by inputting successive ones of the M image blocks into a neural network for fingerprint recognition until the score of the N image blocks meets a preset condition, wherein the score is a sum score, and Nis an integer less than or equal to M, terminate calculating the scores of remaining image blocks among the M image blocks, and recognize a legitimacy of a fingerprint in the input fingerprint image, wherein N is an integer less than or equal to M.

### Claim 14 (depends on 13)

The fingerprint recognition device according to claim 13, wherein the preset condition includes a first condition,
wherein the first condition indicates that a sum of the scores of the N image blocks is greater than or equal to a product of M and a preset threshold score, and
wherein the recognition module is configured to:
recognize the legitimacy of the fingerprint in the input fingerprint image as true upon the scores of the N image blocks meeting the first condition.

### Claim 15 (depends on 13)

The fingerprint recognition device according to claim 13, wherein the preset condition includes a second condition,
wherein the second condition indicates that a sum of a sum of the scores of the N image blocks and a first value is less than a product of M and a preset threshold value, and the first value is equal to a product of a difference between M and N and a maximum score that the neural network may output, and
wherein the recognition module is configured to:
recognize the legitimacy of the fingerprint in the input fingerprint image as false upon the scores of the N image blocks meeting the second condition.

### Claim 16 (depends on 13)

The fingerprint recognition device according to claim 13, wherein the neural network comprises a depthwise separable convolutional network, and a number of output channels of point convolutions of the depthwise separable convolutional network is consistent with multiplication and accumulation operations supported by the fingerprint recognition device.

### Claim 17 (depends on 16)

The fingerprint recognition device according to claim 16, wherein the depthwise separable convolutional network includes a separable convolutional structure of which the number of output channels is a predetermined number,
wherein the separable convolutional structure includes depth-wise convolutional layers and point-wise convolutional layers, and
wherein a convolution operation of the depth-wise convolution layers is accelerated using a convolution hardware accelerator of the fingerprint recognition device, and a convolution operation of the point-wise convolution layers is accelerated using a multiplication and accumulation hardware accelerator of the fingerprint recognition device.

### Claim 18 (depends on 13)

The fingerprint recognition device according to claim 13, wherein the obtaining module is configured to:
obtain a plurality of image blocks by dividing the input fingerprint image;
determine a center coordinate of the input fingerprint image; and
determine a first number of image blocks closest to the center coordinate among the plurality of image blocks and a second number of image blocks farthest from the center coordinate among the plurality of image blocks as the M image blocks, wherein a sum of the first number and the second number is equal to M.

### Claim 19 (depends on 18)

The fingerprint recognition device according to claim 18, wherein the obtaining module is configured to:
extract a plurality of minutiae from the input fingerprint image using a feature extraction algorithm,
wherein each image block of the plurality of image blocks is centered on a different minutia of the plurality of minutiae.

### Claim 20 (depends on 13)

The fingerprint recognition device according to claim 13, further comprising:
a processor; and
a computer-readable storage medium storing a computer program, which, when executed by the processor, implements a method of the recognition module.
