# US 2020/0404186 A1 · Defocus amount measuring device, defocus amount measuring method, defocus amount measuring program, and discriminator

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

- Number: US 2020/0404186 A1
- Document ID: US20200404186A1
- Status: Published application
- Kind: A1
- Application number: 17/013,680
- Filed: 2020-09-07
- Published: 2020-12-24
- Earliest claimed: 2018-03-22
- Assignees: FUJIFILM Corporation
- Applicants: Fujifilm Corporation
- Inventors: Takashi WAKUI
- Web page: https://patentgrep.com/patent/US20200404186A1

## CPC

- G02B 21/244: {using image analysis techniques}
- C12M 1/34: Measuring or testing with condition measuring or sensing means, e.g. colony counters
- G02B 7/28: Systems for automatic generation of focusing signals
- G02B 7/38: measured at different points on the optical axis {, e.g. focussing on two or more planes and comparing image data}
- G02B 21/008: {Details of detection or image processing, including general computer control}
- G02B 21/26: Stages; Adjusting means therefor
- G02B 21/36: arranged for photographic purposes or projection purposes (G02B21/18 takes precedence){or digital imaging or video purposes including associated control and data processing arrangements (image data processing per se G06T)}
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06N 20/00: Machine learning
- G06T 7/00: Image analysis
- G06V 20/693: {Acquisition}
- H04N 23/672: {based on the phase difference signals}
- G02B 21/14: affording illumination for phase-contrast observation
- G02B 21/367: {providing an output produced by processing a plurality of individual source images, e.g. image tiling, montage, composite images, depth sectioning, image comparison}
- G02B: OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- C12M: APPARATUS FOR ENZYMOLOGY OR MICROBIOLOGY; {APPARATUS FOR CULTURING MICROORGANISMS FOR PRODUCING BIOMASS, FOR GROWING CELLS OR FOR OBTAINING FERMENTATION OR METABOLIC PRODUCTS, i.e. BIOREACTORS OR FERMENTERS}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A marker image detection section detects a marker image from a captured image for determining a defocus amount. A discriminator discriminates the defocus amount of the marker image included in the captured image. The discriminator performs learning using feature amounts related to a plurality of teacher marker images captured with various defocus amounts and discriminates a defocus amount of an input marker image.

## Claims

### Claim 1

A defocus amount measuring device comprising at least one processor, wherein the processor is configured to:
detect a marker image from a captured image acquired by imaging a marker that is a measurement target of a defocus amount; and
discriminate a defocus amount of an input marker image by a discriminator that performs learning using feature amounts related to a plurality of teacher marker images captured with various defocus amounts.

### Claim 2 (depends on 1)

The defocus amount measuring device according to claim 1,
wherein the discriminator discriminates the defocus amount for each of a plurality of the marker images included in the captured image, and
the processor is further configured to determine a statistical value of a plurality of the defocus amounts as the defocus amount of the captured image.

### Claim 3 (depends on 1)

The defocus amount measuring device according to claim 1,
wherein the discriminator discriminates that the defocus amount is not clear.

### Claim 4 (depends on 1)

The defocus amount measuring device according to claim 1,
wherein the discriminator is configured by a neural network.

### Claim 5 (depends on 1)

The defocus amount measuring device according to claim 1,
wherein the discriminator learns a co-occurrence matrix related to the plurality of teacher marker images as the feature amount.

### Claim 6 (depends on 1)

The defocus amount measuring device according to claim 1,
wherein the marker has a fine cell structure.

### Claim 7 (depends on 1)

The defocus amount measuring device according to claim 1,
wherein the captured image includes the marker and is acquired by imaging a container in which an observation target is contained, by an imaging unit, and
wherein the processor is further configured to perform a control for focusing an image of the observation target in the container on the imaging unit on the basis of the defocus amount.

### Claim 8 (depends on 7)

The defocus amount measuring device according to claim 7, further comprising:
a stage on which the container in which the observation target is contained is placed,
wherein the captured image is acquired by scanning an observation region in the container placed on the stage and performing imaging of each observation region in the container, and
wherein the processor is configured to perform the control for focusing the image of the observation target in the container on the imaging unit on the basis of the defocus amount, in each observation region.

### Claim 9

A defocus amount measuring method comprising:
detecting a marker image from a captured image acquired by imaging a marker that is a measurement target of a defocus amount; and
discriminating, using a discriminator that performs learning using feature amounts related to a plurality of teacher marker images captured with various defocus amounts and that discriminates a defocus amount of an input marker image, the defocus amount of the input marker image.

### Claim 10

A non-transitory computer-readable storage medium that stores a defocus amount measuring program causing a computer to execute:
a process of detecting a marker image from a captured image acquired by imaging a marker that is a measurement target of a defocus amount; and
a process of discriminating, using a discriminator that performs learning using feature amounts related to a plurality of teacher marker images captured with various defocus amounts and that discriminates a defocus amount of an input marker image, the defocus amount of the input marker image.

### Claim 11

A discriminator that performs learning using feature amounts related to a plurality of teacher marker images captured with various defocus amounts and discriminates a defocus amount of an input marker image.

### Claim 12

A defocus amount measuring device comprising:
a discriminator that performs learning using feature amounts related to a plurality of teacher marker images captured with various defocus amounts and in a case where a captured image acquired by imaging a marker that is a measurement target of a defocus amount is input, discriminates a presence or absence of a marker image in the captured image and a defocus amount of the marker image in a case where the marker image is included in the captured image.

### Claim 13

A discriminator that performs learning using feature amounts related to a plurality of teacher marker images captured with various defocus amounts and in a case where a captured image acquired by imaging a marker that is a measurement target of a defocus amount is input, discriminates a presence or absence of a marker image in the captured image and a defocus amount of the marker image in a case where the marker image is included in the captured image.
