# US 2022/0012541 A1 · Fingerprint image processing methods and apparatuses

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

- Number: US 2022/0012541 A1
- Document ID: US20220012541A1
- Status: Published application
- Kind: A1
- Application number: 17/362,213
- Filed: 2021-06-29
- Published: 2022-01-13
- Earliest claimed: 2020-07-13
- Assignees: Alipay (Hangzhou) Information Technology Co., Ltd.
- Applicants: Alipay (Hangzhou) Information Technology Co., Ltd.
- Inventors: Kai Zhu; Jianxu Zheng
- Web page: https://patentgrep.com/patent/US20220012541A1

## CPC

- G06V 40/1347: {Preprocessing; Feature extraction}
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06V 10/82: using neural networks
- G06V 40/13: Sensors therefor
- G06V 40/1365: {Matching; Classification}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Methods, systems, and apparatus for operations for processing fingerprint images. An example system includes obtaining an original fingerprint trace image of a fingerprint trace left by a user on a target object; inputting the original fingerprint trace image to a pre-trained fingerprint image processing model that is configured to process the original fingerprint trace image in accordance with pre-trained parameters of the pre-trained fingerprint image processing model; obtaining as output a target fingerprint trace image from the fingerprint image processing model; and using the target fingerprint trace image as a test fingerprint image for performing a test on a fingerprint recognition device, wherein a degree of matching between a fingerprint in the target fingerprint trace image and a real fingerprint that corresponds to a same finger is greater than or equal to a predetermined threshold.

## Claims

### Claim 1

A computer-implemented method for processing fingerprint images, comprising:
obtaining an original fingerprint trace image of a fingerprint trace left by a user on a target object;
inputting the original fingerprint trace image to a pre-trained fingerprint image processing model that is configured to process the original fingerprint trace image in accordance with pre-trained parameters of the pre-trained fingerprint image processing model;
obtaining as output a target fingerprint trace image from the fingerprint image processing model; and
using the target fingerprint trace image as a test fingerprint image for performing a test on a fingerprint recognition device, wherein
the fingerprint image processing model is obtained through training based on a set of fingerprint trace image samples and a set of real fingerprint image samples corresponding to a plurality of different fingers, and a degree of matching between a fingerprint in the target fingerprint trace image and a real fingerprint that corresponds to a same finger is greater than or equal to a predetermined threshold.

### Claim 2 (depends on 1)

The computer-implemented method according to claim 1, wherein inputting the original fingerprint trace image to the pre-trained fingerprint image processing model comprises:
mirror-flipping the original fingerprint trace image to generate a mirror-flipped fingerprint trace image;
inputting the mirror-flipped fingerprint trace image to the fingerprint image processing model; and
restoring texture information of a fingerprint trace in the mirror-flipped fingerprint trace image by using the fingerprint image processing model, or reducing a value of color difference between the fingerprint trace in the original fingerprint trace image and the target object by adjusting a color value of the fingerprint trace in the mirror-flipped fingerprint trace image by using the fingerprint image processing model.

### Claim 3 (depends on 2)

The computer-implemented method according to claim 2, wherein inputting the original fingerprint trace image to the pre-trained fingerprint image processing model further comprises:
inputting the original fingerprint trace image to the fingerprint image processing model;
mirror-flipping the original fingerprint trace image by using the fingerprint image processing model to generate the mirror-flipped fingerprint trace image; and
restoring texture information of the fingerprint trace in the mirror-flipped fingerprint trace image by using the fingerprint image processing model, or reducing the value of color difference between the fingerprint trace in the original fingerprint trace image and the target object by adjusting the color value of the fingerprint trace in the mirror-flipped fingerprint trace image.

### Claim 4 (depends on 1)

The computer-implemented method according to claim 1, wherein before inputting the original fingerprint trace image to the pre-trained fingerprint image processing model, the method further comprises:
obtaining a plurality of fingerprint trace images corresponding to the plurality of different fingers;
mirror-flipping the plurality of fingerprint trace images to generate the set of fingerprint trace image samples corresponding to the plurality of different fingers;
obtaining the set of real fingerprint image samples corresponding to the plurality of different fingers by using a fingerprint sensor; and
training the fingerprint image processing model by using the set of fingerprint trace image samples and the set of real fingerprint image samples corresponding to the plurality of different fingers.

### Claim 5 (depends on 4)

The computer-implemented method according to claim 4, wherein before inputting the original fingerprint trace image to the pre-trained fingerprint image processing model, the method further comprises:
inputting a fingerprint trace image sample from the set of fingerprint trace image samples to the fingerprint image processing model for processing;
obtaining as output a processed fingerprint trace image sample from the fingerprint image processing model;
determining a matching result based on matching a fingerprint in the processed fingerprint trace image sample with a real fingerprint that corresponds to a same finger; and
optimizing the fingerprint image processing model based on the matching result.

### Claim 6 (depends on 1)

The computer-implemented method according to claim 1, wherein obtaining the original fingerprint trace image of the fingerprint trace left by the user on the target object comprises:
scanning a surface region on the target object that has the fingerprint trace by using an image scanning device.

### Claim 7 (depends on 1)

The computer-implemented method according to claim 1, wherein the fingerprint image processing model is a self-attention generative adversarial network (SAGAN) model.

### Claim 8

A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations for processing fingerprint images, wherein the operations comprise:
obtaining an original fingerprint trace image of a fingerprint trace left by a user on a target object;
inputting the original fingerprint trace image to a pre-trained fingerprint image processing model that is configured to process the original fingerprint trace image in accordance with pre-trained parameters of the pre-trained fingerprint image processing model;
obtaining as output a target fingerprint trace image from the fingerprint image processing model; and
using the target fingerprint trace image as a test fingerprint image for performing a test on a fingerprint recognition device, wherein
the fingerprint image processing model is obtained through training based on a set of fingerprint trace image samples and a set of real fingerprint image samples corresponding to a plurality of different fingers, and a degree of matching between a fingerprint in the target fingerprint trace image and a real fingerprint that corresponds to a same finger is greater than or equal to a predetermined threshold.

### Claim 9 (depends on 8)

The non-transitory, computer-readable medium according to claim 8, wherein inputting the original fingerprint trace image to the pre-trained fingerprint image processing model comprises:
mirror-flipping the original fingerprint trace image to generate a mirror-flipped fingerprint trace image;
inputting the mirror-flipped fingerprint trace image to the fingerprint image processing model; and
restoring texture information of a fingerprint trace in the mirror-flipped fingerprint trace image by using the fingerprint image processing model, or reducing a value of color difference between the fingerprint trace in the original fingerprint trace image and the target object by adjusting a color value of the fingerprint trace in the mirror-flipped fingerprint trace image by using the fingerprint image processing model.

### Claim 10 (depends on 9)

The non-transitory, computer-readable medium according to claim 9, wherein inputting the original fingerprint trace image to the pre-trained fingerprint image processing model further comprises:
inputting the original fingerprint trace image to the fingerprint image processing model;
mirror-flipping the original fingerprint trace image by using the fingerprint image processing model to generate the mirror-flipped fingerprint trace image; and
restoring texture information of the fingerprint trace in the mirror-flipped fingerprint trace image by using the fingerprint image processing model, or reducing the value of color difference between the fingerprint trace in the original fingerprint trace image and the target object by adjusting the color value of the fingerprint trace in the mirror-flipped fingerprint trace image.

### Claim 11 (depends on 8)

The non-transitory, computer-readable medium according to claim 8, wherein before inputting the original fingerprint trace image to the pre-trained fingerprint image processing model, and wherein the operations further comprise:
obtaining a plurality of fingerprint trace images corresponding to the plurality of different fingers;
mirror-flipping the plurality of fingerprint trace images to generate the set of fingerprint trace image samples corresponding to the plurality of different fingers;
obtaining the set of real fingerprint image samples corresponding to the plurality of different fingers by using a fingerprint sensor; and
training the fingerprint image processing model by using the set of fingerprint trace image samples and the set of real fingerprint image samples corresponding to the plurality of different fingers.

### Claim 12 (depends on 11)

The non-transitory, computer-readable medium according to claim 11, wherein before inputting the original fingerprint trace image to the pre-trained fingerprint image processing model, and wherein the operations further comprise:
inputting a fingerprint trace image sample from the set of fingerprint trace image samples to the fingerprint image processing model for processing;
obtaining as output a processed fingerprint trace image sample from the fingerprint image processing model;
determining a matching result based on matching a fingerprint in the processed fingerprint trace image sample with a real fingerprint that corresponds to a same finger; and
optimizing the fingerprint image processing model based on the matching result.

### Claim 13 (depends on 8)

The non-transitory, computer-readable medium according to claim 8, wherein obtaining the original fingerprint trace image of the fingerprint trace left by the user on the target object comprises:
scanning a surface region on the target object that has the fingerprint trace by using an image scanning device.

### Claim 14

A computer-implemented system, comprising:
one or more computers; and
one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform operations for processing fingerprint images, wherein the operations comprise:
obtaining an original fingerprint trace image of a fingerprint trace left by a user on a target object;
inputting the original fingerprint trace image to a pre-trained fingerprint image processing model that is configured to process the original fingerprint trace image in accordance with pre-trained parameters of the pre-trained fingerprint image processing model;
obtaining as output a target fingerprint trace image from the fingerprint image processing model; and
using the target fingerprint trace image as a test fingerprint image for performing a test on a fingerprint recognition device, wherein
the fingerprint image processing model is obtained through training based on a set of fingerprint trace image samples and a set of real fingerprint image samples corresponding to a plurality of different fingers, and a degree of matching between a fingerprint in the target fingerprint trace image and a real fingerprint that corresponds to a same finger is greater than or equal to a predetermined threshold.

### Claim 15 (depends on 14)

The computer-implemented system according to claim 14, wherein inputting the original fingerprint trace image to the pre-trained fingerprint image processing model comprises:
mirror-flipping the original fingerprint trace image to generate a mirror-flipped fingerprint trace image;
inputting the mirror-flipped fingerprint trace image to the fingerprint image processing model; and
restoring texture information of a fingerprint trace in the mirror-flipped fingerprint trace image by using the fingerprint image processing model, or reducing a value of color difference between the fingerprint trace in the original fingerprint trace image and the target object by adjusting a color value of the fingerprint trace in the mirror-flipped fingerprint trace image by using the fingerprint image processing model.

### Claim 16 (depends on 15)

The computer-implemented system according to claim 15, wherein inputting the original fingerprint trace image to the pre-trained fingerprint image processing model further comprises:
inputting the original fingerprint trace image to the fingerprint image processing model;
mirror-flipping the original fingerprint trace image by using the fingerprint image processing model to generate the mirror-flipped fingerprint trace image; and
restoring texture information of the fingerprint trace in the mirror-flipped fingerprint trace image by using the fingerprint image processing model, or reducing the value of color difference between the fingerprint trace in the original fingerprint trace image and the target object by adjusting the color value of the fingerprint trace in the mirror-flipped fingerprint trace image.

### Claim 17 (depends on 14)

The computer-implemented system according to claim 14, wherein before inputting the original fingerprint trace image to the pre-trained fingerprint image processing model, and wherein the operations further comprise:
obtaining a plurality of fingerprint trace images corresponding to the plurality of different fingers;
mirror-flipping the plurality of fingerprint trace images to generate the set of fingerprint trace image samples corresponding to the plurality of different fingers;
obtaining the set of real fingerprint image samples corresponding to the plurality of different fingers by using a fingerprint sensor; and
training the fingerprint image processing model by using the set of fingerprint trace image samples and the set of real fingerprint image samples corresponding to the plurality of different fingers.

### Claim 18 (depends on 17)

The computer-implemented system according to claim 17, wherein before inputting the original fingerprint trace image to the pre-trained fingerprint image processing model, and wherein the operations further comprise:
inputting a fingerprint trace image sample from the set of fingerprint trace image samples to the fingerprint image processing model for processing;
obtaining as output a processed fingerprint trace image sample from the fingerprint image processing model;
determining a matching result based on matching a fingerprint in the processed fingerprint trace image sample with a real fingerprint that corresponds to a same finger; and
optimizing the fingerprint image processing model based on the matching result.

### Claim 19 (depends on 14)

The computer-implemented system according to claim 14, wherein obtaining the original fingerprint trace image of the fingerprint trace left by the user on the target object comprises:
scanning a surface region on the target object that has the fingerprint trace by using an image scanning device.

### Claim 20 (depends on 14)

The computer-implemented system according to claim 14, wherein the fingerprint image processing model is a self-attention generative adversarial network (SAGAN) model.
