US-12620198-B2 - Information processing system and information processing method

US12620198B2US 12620198 B2US12620198 B2US 12620198B2US-12620198-B2

Abstract

An imaging control device includes an image acquiring part that acquires a first training image of a machine learning model, a display control part that causes a display device to display the first training image based on a distance between the display device and an imaging device that acquires a blurred image, an imaging control part that causes the imaging device to capture the first training image to acquire a second training image, and a storage control part that stores a data set including a set of the second training image and correct answer information. The display control part changes, when the distance is changed, a display size of the first training image so that a size of the second training image acquired by the imaging device is maintained. The imaging control part causes the imaging device to capture the first training image when the distance is changed.

Inventors

Satoshi Sato
Yasunori Ishii
Kunio Nobori

Assignees

PANASONIC INTELLECTUAL PROPERTY CORPORATION OF AMERICA

Dates

Publication Date: 20260505
Application Date: 20231018
Priority Date: 20210422

Claims (13)

1 . An information processing system, comprising: a processor; and a memory including a program that, when executed by the processor, causes the processor to: acquire a first training image of a machine learning model from a first storage; acquire a distance between a display device and an imaging device that acquires a blurred image by imaging; cause the display device to display the first training image based on the distance; cause the imaging device to capture the first training image displayed on the display device to acquire a second training image, and store a data set including a set of the second training image acquired by the imaging device and annotation information associated with the first training image in a second storage, wherein the processor changes, when the distance is changed, a display size of the first training image so that a size of the second training image acquired by the imaging device is maintained, and causes the display device to display the first training image having the changed display size, and wherein the processor causes the imaging device to capture the first training image when the distance is changed.
2 . The information processing system according to claim 1 , wherein the program, when executed by the processor, further causes the processor to direct a change of the distance between the display device and the imaging device.
3 . The information processing system according to claim 2 , wherein the processor directs the change of the distance more than once, wherein the processor changes the display size of the first training image so that the size of the second training image acquired by the imaging device is maintained every time the distance is changed more than once, and causes the display device to display the first training image having the changed display size, wherein the processor causes the imaging device to capture the first training image every time the distance is changed more than once to acquire a plurality of the second training images, and wherein the processor stores a second data set including a second set of each of the plurality of the second training images acquired by the imaging device and the annotation information in the second storage.
4 . The information processing system according to claim 2 , wherein the processor directs a moving device that moves at least one of the imaging device and the display device to move at least one of the imaging device and the display device.
5 . The information processing system according to claim 4 , wherein the processor moves at least one of the imaging device and the display device in an optical axis direction of the imaging device.
6 . The information processing system according to claim 4 , wherein the processor moves at least one of the imaging device and the display device in a direction intersecting an optical axis direction of the imaging device.
7 . The information processing system according to claim 1 , wherein the processor acquires the distance from a distance measuring device that measures the distance between the display device and the imaging device.
8 . The information processing system according to claim 1 , wherein the first training image stored in the first storage is an image without blurring acquired by another imaging device different from the imaging device.
9 . The information processing system according to claim 1 , wherein the processor changes the display size of the first training image in proportion to the distance between the display device and the imaging device.
10 . The information processing system according to claim 1 , wherein the program, when executed by the processor, further causes the processor to train the machine learning model using the data set including the set of the second training image and the annotation information, the data set being stored in the second storage.
11 . The information processing system according to claim 1 , wherein the annotation information associated with the first training image is stored in the first storage, and the processor acquires the annotation information from the first storage.
12 . The information processing system according to claim 1 , wherein the annotation information associated with the first training image is stored in the first storage, and the processor acquires the annotation information from the first storage to output the acquired annotation information to a storage control part.
13 . An information processing method with which a computer performs the information processing method, the information processing method comprising: acquiring a first training image of a machine learning model from a first storage; acquiring a distance between a display device and an imaging device that acquires a blurred image by imaging; causing the display device to display the first training image based on the distance; causing the imaging device to capture the first training image displayed on the display device to acquire a second training image; and storing a data set including a set of the second training image acquired by the imaging device and annotation information associated with the first training image in a second storage, wherein in the displaying of the first training image, when the distance is changed, a display size of the first training image is changed so that a size of the second training image acquired by the imaging device is maintained, and the display device is caused to display the first training image having the changed display size, and in the acquiring of the second training image, when the distance is changed, the imaging device is caused to capture the first training image.

Description

TECHNICAL FIELD The present disclosure relates to a technique that creates a data set to be used for training a machine learning model. BACKGROUND ART For example, Non-Patent Literature 1 discloses a method for displaying an image captured by a normal camera on a display and causing the lensless camera to capture the image displayed on the display to create a data set for training a face detection model using the lensless camera. However, in a case where the image displayed on the display is captured as in the conventional art to create a data set, a training data set including training images that are blurred variously depending on the distance between the display and the camera is not created. Thus, it is difficult to improve recognition accuracy of a machine learning model while protecting the privacy of a subject. CITATION LIST Non Patent Literature Non-Patent Literature 1: Jasper Tan, Li Niu, Jesse K. Adams, Vivek Boominathan, Jacob T. Robinson, and Richard G. Baraniuk, “Face Detection and Verification Using Lensless Cameras”, IEEE Transactions on Computational Imaging, vol. 5, No. 2, pp. 180-194, 2019 SUMMARY OF INVENTION The present disclosure has been made to solve the above problem, and an object of the present disclosure is to provide a technique that enables improvement of recognition accuracy of a machine learning model while protecting privacy of a subject. An information processing system of the present disclosure includes an image acquiring part that acquires a first training image of a machine learning model from a first storage part, a distance acquiring part that acquires a distance between a display device and an imaging device that acquires a blurred image by imaging, a display control part that causes the display device to display the first training image based on the distance, an imaging control part that causes the imaging device to capture the first training image displayed on the display device to acquire a second training image, and a storage control part that stores a data set including a set of the second training image acquired by the imaging device; and correct answer information associated with the first training image in a second storage part. The display control part changes, when the distance is changed, a display size of the first training image so that a size of the second training image acquired by the imaging device is maintained, and causes the display device to display the first training image having the changed display size. The imaging control part causes the imaging device to capture the first training image when the distance is changed. According to the present disclosure, it is possible to improve recognition accuracy of a machine learning model while protecting the privacy of a subject. BRIEF DESCRIPTION OF DRAWINGS FIG. 1 is a block diagram illustrating an example of an overall configuration of an imaging system according to a first embodiment of the present disclosure. FIG. 2 is a view schematically illustrating a structure of a multi-pinhole camera as one example of an imaging device. FIG. 3 is a flowchart for describing data set creation processing in an imaging control device according to the first embodiment of the present disclosure. FIG. 4 is a schematic view for describing a positional relationship between a display device and the imaging device in the first embodiment. FIG. 5 is a schematic view for describing an image captured through two pinholes in the multi-pinhole camera. FIG. 6 is a diagram illustrating an example of an image captured by the imaging device in a case where a distance between the imaging device and the display device is L1. FIG. 7 is a diagram illustrating an example of an image captured by the imaging device in a case where the distance between the imaging device and the display device is L2 (L1<L2). FIG. 8 is a diagram illustrating an example of a first training image displayed on the display device. FIG. 9 is a diagram illustrating an example of a second training image acquired by causing the imaging device to capture the first training image illustrated in FIG. 8 in a case where the distance between the imaging device and the display device is L1. FIG. 10 is a diagram illustrating an example of a second training image acquired by causing the imaging device to capture the first training image illustrated in FIG. 8 in the case where the distance between the imaging device and the display device is L2 (L1<L2). FIG. 11 is a flowchart for describing data set creation processing in an imaging control device according to a modification of the first embodiment of the present disclosure. FIG. 12 is a block diagram illustrating an example of an overall configuration of an imaging system according to a second embodiment of the present disclosure. FIG. 13 is a flowchart for describing data set creation processing in an imaging control device according to the second embodiment of the present disclosure. FIG. 14 is a block diagram illustrati