# US 2025/0156650 A1 · Generating alternative text (“alt text”) for images

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

- Number: US 2025/0156650 A1
- Document ID: US20250156650A1
- Status: Published application
- Kind: A1
- Application number: 18/507,339
- Filed: 2023-11-13
- Published: 2025-05-15
- Earliest claimed: 2023-11-13
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: ANN M DEPAOLO; DANIELLE PALUMBO; DAVID F. HANS; DEBRA L. NOLL; HENRY D GORBSKY; KATHLEEN PFEIFFER; PHILIP SICONOLFI
- Web page: https://patentgrep.com/patent/US20250156650A1

## CPC

- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F 40/30: Semantic analysis
- G06F 40/56: Natural language generation
- G06V 10/40: Extraction of image or video features
- G06V 10/945: {User interactive design; Environments; Toolboxes}
- G06V 20/50: Context or environment of the image
- G06V 20/70: Labelling scene content, e.g. deriving syntactic or semantic representations
- G06V 2201/10: Recognition assisted with metadata
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Generating alternative text (“alt text”) for images, including: performing an image analysis of an image to generate data describing one or more visual attributes of the image; performing a natural language processing on the data to generate a text description of the image; and generating, based on the text description of the image, an alt text for the image.

## Claims

### Claim 1

A method comprising:
performing an image analysis of an image to generate data describing one or more visual attributes of the image;
performing a natural language processing on the data to generate a text description of the image; and
generating, based on the text description of the image, an alt text for the image.

### Claim 2 (depends on 1)

The method of claim 1, further comprising generating, based on the data describing the one or more visual attributes of the image and one or more data points associated with the image, an evaluation of the text description.

### Claim 3 (depends on 2)

The method of claim 2, wherein generating the alt text for the image comprises generating, based on the evaluation of the text description meeting a threshold, the alt text as the text description of the image.

### Claim 4 (depends on 2)

The method of claim 2, wherein generating the alt text for the image comprises:
updating, based on the evaluation of the text description falling a threshold, the text description; and
generating, as the alt text, the updated text description.

### Claim 5 (depends on 2)

The method of claim 2, further comprising flagging, based on the evaluation of the text description falling below a threshold, the alt text for review.

### Claim 6 (depends on 2)

The method of claim 2, wherein the one or more data points comprises metadata associated with the image.

### Claim 7 (depends on 2)

The method of claim 2, wherein the one or more data points comprises user feedback associated with the image.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
receiving user feedback for the alt text; and
updating the alt text based on the user feedback.

### Claim 9 (depends on 1)

The method of claim 1, wherein the text description of the image is further generated based on one or more contextual attributes associated with the image.

### Claim 10 (depends on 1)

The method of claim 1, wherein the one or more visual attributes comprises at least one of:
one or more identified objects, an image composition, or one or more facial expressions.

### Claim 11

An apparatus comprising:
a processing device; and
memory operatively coupled to the processing device, wherein the memory stores computer program instructions that, when executed, cause the processing device to:
perform an image analysis of an image to generate data describing one or more visual attributes of the image;
perform a natural language processing on the data to generate a text description of the image; and
generate, based on the text description of the image, an alt text for the image.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein the computer program instructions, when executed, further cause the processing device to further comprising generating, based on the data describing the one or more visual attributes of the image and one or more data points associated with the image, an evaluation of the text description.

### Claim 13 (depends on 11)

The apparatus of claim 11, wherein generating the alt text for the image comprises generating, based on the evaluation of the text description meeting a threshold, the alt text as the text description of the image.

### Claim 14 (depends on 11)

The apparatus of claim 11, wherein generating the alt text for the image comprises:
updating, based on the evaluation of the text description falling a threshold, the text description; and
generating, as the alt text, the updated text description.

### Claim 15 (depends on 11)

The apparatus of claim 11, further comprising flagging, based on the evaluation of the text description falling below a threshold, the alt text for review.

### Claim 16 (depends on 11)

The apparatus of claim 11, wherein the one or more data points comprises metadata associated with the image.

### Claim 17 (depends on 11)

The apparatus of claim 11, wherein the one or more data points comprises metadata associated with the image.

### Claim 18 (depends on 11)

The apparatus of claim 11, wherein the computer program instructions, when executed, further cause the processing device to:
receiving user feedback for the alt text; and
updating the alt text based on the user feedback.

### Claim 19 (depends on 8)

The apparatus of claim 8, wherein the text description of the image is further generated based on one or more contextual attributes associated with the image.

### Claim 20

A computer program product comprising a computer readable storage medium, wherein the computer readable storage medium comprises computer program instructions that, when executed:
perform an image analysis of an image to generate data describing one or more visual attributes of the image;
perform a natural language processing on the data to generate a text description of the image; and
generate, based on the text description of the image, an alt text for the image.
