# US 2026/0228897 A1 · Iterative scheme for establishing optimal position of focusing lens and retinal cameras for implementing the same

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

- Number: US 2026/0228897 A1
- Document ID: US20260228897A1
- Status: Published application
- Kind: A1
- Application number: 19/153,267
- Filed: 2024-02-28
- Published: 2026-08-06
- Earliest claimed: 2023-02-28
- Assignees: Verily Life Sciences LLC
- Applicants: Verily Life Sciences LLC
- Inventors: Alireza DASTGHEIB; Karthik VIJAYRAGHAVAN
- Web page: https://patentgrep.com/patent/US20260228897A1

## CPC

- G06T 7/0014: {using an image reference approach}
- A61B 3/12: for looking at the eye fundus, e.g. ophthalmoscopes (A61B3/13 takes precedence)
- A61B 3/14: Arrangements specially adapted for eye photography
- G06T 5/70: Denoising; Smoothing
- G06T 5/73: Deblurring; Sharpening
- G06T 7/0002: {Inspection of images, e.g. flaw detection}
- G06T 2207/10048: Infrared image
- G06T 2207/30041: Eye; Retina; Ophthalmic
- G06T 2207/30168: Image quality inspection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

Introduced here is an approach to autofocusing in which an iterative scheme for performing pairwise comparison of digital images is performed in order to identify the optimal position for the focusing lens. This approach relies on the fact that digital images generated in rapid succession are not fully independent, but are of the same subject with different degrees of blur or defocus. In accordance with this approach, a retinal camera can proceed through a series of steps, analyzing pairs of the digital images, until the optimal position for the focusing lens is found.

## Claims

### Claim 1

A method comprising:
acquiring a pair of digital images of an eye of a patient captured by a retinal camera under a same lighting condition, the pair of digital images including a first digital image and a second digital image;
producing a first blurred digital image by providing the first digital image, as input, to a blurring algorithm;
producing a second blurred digital image by providing the second digital image, as input, to the blurring algorithm;
generating a first metric that is indicative of a magnitude of difference between the first blurred digital image and the second digital image by comparing the first blurred digital image against the second digital image;
generating a second metric that is indicative of a magnitude of difference between the second blurred digital image and the first digital image by comparing the second blurred digital image against the first digital image;
establishing that the first digital image is sharper than the second digital image based on an analysis of the first and second metrics; and
discarding the second digital image.

### Claim 2 (depends on 1)

The method of claim 1,
wherein the first metric is representative of mean absolute difference between the first blurred digital image and the second digital image, and
wherein the second metric is representative of mean absolute difference between the second blurred digital image and the first digital image.

### Claim 3 (depends on 1)

The method of claim 1, wherein the pair of digital images are captured in succession, with the first digital image being captured before the second digital image.

### Claim 4 (depends on 1)

The method of claim 1, wherein the same lighting condition involves illuminating the eye with infrared light, such that the first digital image is representative of infrared light reflected by the eye at a first point in time and the second digital image is representative of infrared light reflected by the eye at a second point in time.

### Claim 5 (depends on 4)

The method of claim 4,
wherein the first digital image is captured while a focusing lens is located in a first position, and
wherein the second digital image is captured while the focusing lens is located in a second position different than the first position.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
in response to said establishing,
causing a motor to reposition the focusing lens in the first position; and
causing a third digital image to be captured while visible light is shone into the eye, such that the third digital image is representative of visible light reflected by the eye at a third point in time.

### Claim 7

A non-transitory medium with instructions stored thereon that, when executed by a processor of a retinal camera, cause the retinal camera to perform operations comprising:
acquiring digital images that are captured as a motor moves a focusing lens among a plurality of positions,
wherein each of the digital images is associated with a different one of the plurality of positions;
performing a pairwise comparison of pairs of the digital images, such that for each pair, a sharper digital image is identified and combined with a next one of the digital images to form another pair; and
causing the motor to move the focusing lens to a given position that corresponds to a sharpest digital image among the digital images that is identified via the pairwise comparison.

### Claim 8 (depends on 7)

The non-transitory medium of claim 7, wherein the operations further comprise:
causing a digital image to be captured for diagnostic purposes in response to a determination that the focusing lens is located in the given position.

### Claim 9 (depends on 8)

The non-transitory medium of claim 8,
wherein the digital images are generated by the retinal camera based on non-visible light that is shone into, and reflected by, an eye presented to the retinal camera, and
wherein the digital image is generated by the retinal camera based on visible light that is shone into, and reflected by, the eye presented to the retinal camera.

### Claim 10 (depends on 7)

The non-transitory medium of claim 7, wherein said performing comprises:
for each pair that includes a first digital image and a second digital image,
producing a first blurred digital image by providing the first digital image, as input, to a blurring algorithm,
producing a second blurred digital image by providing the second digital image, as input, to the blurring algorithm,
comparing the first blurred digital image against the second digital image, so as to generate a first metric that is indicative of a magnitude of difference between the first blurred digital image and the second digital image,
comparing the second blurred digital image against the first digital image, so as to generate a second metric that is indicative of a magnitude of difference between the second blurred digital image and the first digital image, and
identifying the sharper digital image via analysis of the first and second metrics.

### Claim 11 (depends on 10)

The non-transitory medium of claim 10, wherein said performing is performed until a numerical optimization algorithm identifies a local maximum difference between the first and second metrics generated for each pair.

### Claim 12 (depends on 7)

The non-transitory medium of claim 7, wherein said performing comprises:
for each pair that includes a first digital image and a second digital image,
producing a first blurred digital image by providing the first digital image, as input, to a blurring algorithm,
producing a second blurred digital image by providing the second digital image, as input, to the blurring algorithm,
computing (i) a first metric that is indicative of a magnitude of difference between the first blurred digital image and the second digital image and (ii) a second metric that is indicative of a magnitude of difference between the second blurred digital image and the first digital image,
determining that the first metric is within a threshold amount of the second metric,
producing a third blurred digital image by providing the first blurred digital image, as input, to the blurring algorithm,
producing a fourth blurred digital image by providing the second blurred digital image, as input, to the blurring algorithm,
computing (i) a third metric that is indicative of a magnitude of difference between the third blurred digital image and the second digital image and (ii) a fourth metric that is indicative of a magnitude of difference between the fourth blurred digital image and the first digital image, and
identifying the sharper digital image via analysis of the third and fourth metrics.

### Claim 13 (depends on 12)

The non-transitory medium of claim 12, wherein the threshold amount is a static value.

### Claim 14 (depends on 12)

The non-transitory medium of claim 12, wherein the threshold amount is dynamically determined based on the first metric or the second metric.

### Claim 15

A non-transitory medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:
acquiring a plurality of digital images that are captured by a retinal camera under a first lighting condition as a motor moves a focusing lens among a plurality of positions,
wherein each digital image of the plurality of digital images is associated with a different one of the plurality of positions;
producing a plurality of blurred digital images by providing the plurality of digital images, as input, to a blurring algorithm;
performing a pairwise comparison of the plurality of digital images, such that a sharpest digital image among the plurality of digital images that is identified based on an analysis of the plurality of blurred digital images; and
causing the motor to move the focusing lens to a given position that corresponds to the sharpest digital image; and
causing the retinal camera to capture a digital image, with the focusing lens in the given position, under a second lighting condition.

### Claim 16 (depends on 15)

The non-transitory medium of claim 15,
wherein the plurality of digital images are captured in a first sequential order, from a first digital image to a last digital image, and
wherein the plurality of blurred digital images are produced in a second sequential order, wherein the first sequential order maps to the second sequential order.

### Claim 17 (depends on 16)

The non-transitory medium of claim 16, wherein said performing comprises:
implementing an image comparison scheme in which-a
first blurred digital image is compared against a second digital image that immediately follows the first digital image in the first sequential order, to generate a first metric that is indicative of a magnitude of difference between the first blurred digital image and the second digital image,
a second blurred digital image that immediately follows the first blurred digital image in the second sequential order is compared against the first digital image, to generate a second metric that is indicative of a magnitude of difference between the second blurred digital image and the first digital image,
a sharper digital image is identified from among the first and second digital images based on an analysis of the first and second metrics.

### Claim 18 (depends on 17)

The non-transitory medium of claim 17, wherein said implementing is performed iteratively, with the sharper digital image identified in each instance of the image comparison scheme being compared against a next digital image, until a sharpest digital image has been identified from among the plurality of digital images.

### Claim 19 (depends on 17)

The non-transitory medium of claim 17, wherein said implementing is performed iteratively, with the sharper digital image identified in each instance of the image comparison scheme being compared against a next digital image, until the first and second metrics converge within a threshold amount.

### Claim 20 (depends on 17)

The non-transitory medium of claim 17, wherein said implementing is performed iteratively, with the sharper digital image identified in each instance of the scheme being compared against a next digital image, until a predetermined amount of time elapses, and wherein following a conclusion of the predetermined amount of time, whichever digital image is presently identified as sharpest is identified as the sharpest digital image.
