# What is computer vision?

> Computer vision is AI that understands images and video: reading receipts, spotting objects, checking photos. Modern chat models do much of it built in.

Source: https://learn.ynteractive.com/content/glossary/computer-vision · Updated 2026-10-20 · Free from Stepthrough (https://learn.ynteractive.com)

[AI basics](https://learn.ynteractive.com/content/glossary#topic-ai-basics) · [AI glossary](https://learn.ynteractive.com/content/glossary)

Quick answer

Computer vision is the area of AI that gets meaning from images and video: reading the text and numbers on a receipt, recognizing objects in a photo, checking a scanned form, or describing a picture. Many chat models now include vision, so you can attach a photo and ask about it.

Last updated October 20, 2026

[Take the free module →](https://learn.ynteractive.com/courses/ai-for-accounting-firms/12)Module 12 of the free [AI for Accounting & Bookkeeping Firms](https://learn.ynteractive.com/courses/ai-for-accounting-firms) course, about 12 minutes. No account needed.

Updated October 20, 2026 · By [Robert Breen](https://learn.ynteractive.com/content/about)

## Why it matters for a small business

Lots of office data arrives as pictures: phone photos of receipts, scanned contracts, screenshots of an error. Vision lets an AI turn those into usable data without someone retyping it.

Vision models can misread blurry photos, small print, handwriting and look-alike characters, such as 1 and 7. Use clear images, and keep a person comparing the original with what was extracted for anything that touches money.

Vision is also what makes screenshots useful in a chat. Paste a screenshot of an error message or a confusing settings page and ask what it means, and the model reads the words and the layout together. Crop out anything private first, such as names or account numbers.

## In a real lesson: AI Receipt Extractor: Receipts to Google Sheets with n8n

In the [AI Receipt Extractor](https://learn.ynteractive.com/content/ai-receipt-extractor-n8n-google-sheets), you attach receipt.png, a photo of a Corner Mart receipt, in the n8n chat and type "Heres a receipt." The model looks at the image, finds the date, vendor and total, decides it is groceries, and calls the Google Sheets Tool to add a row to the Invoices sheet.

The lesson uses the photo, not the PDF, because the model is reading pixels. It then has you click receipt.png in the chat to compare the original before you trust the row.

[Try this lesson free](https://learn.ynteractive.com/modules/receipt-extractor) or [read the step-by-step guide](https://learn.ynteractive.com/content/ai-receipt-extractor-n8n-google-sheets).

## Common confusions

### Computer vision vs OCR

OCR turns printed text in an image into characters. Computer vision is broader and can also understand layout, objects and what the text means.

### Computer vision vs image generation

Vision reads and understands images. Image generation creates new ones.

## Tips

- Use clear, flat, well-lit photos.
- Ask for exactly the fields you need, not a description.
- Compare the image with the extracted values before saving.
- Remove names, card numbers and faces you don't need before you upload a photo.

## Related terms

[OCR (optical character recognition)](https://learn.ynteractive.com/content/glossary/ocr) · [Multimodal AI](https://learn.ynteractive.com/content/glossary/multimodal-ai) · [Data extraction](https://learn.ynteractive.com/content/glossary/data-extraction) · [Intelligent document processing](https://learn.ynteractive.com/content/glossary/intelligent-document-processing) · [Neural network](https://learn.ynteractive.com/content/glossary/neural-network)

## More AI basics terms

[Context window](https://learn.ynteractive.com/content/glossary/context-window) · [Data minimization](https://learn.ynteractive.com/content/glossary/data-minimization) · [Data poisoning](https://learn.ynteractive.com/content/glossary/data-poisoning) · [Deep learning](https://learn.ynteractive.com/content/glossary/deep-learning)

## Where you use it: free lessons

- [AI Receipt Extractor: Receipts to Google Sheets with n8n](https://learn.ynteractive.com/content/ai-receipt-extractor-n8n-google-sheets) (n8n, 12 min)
- [Make Images with ChatGPT for Your Business](https://learn.ynteractive.com/content/make-images-with-chatgpt-for-your-business) (ChatGPT, 7 min)

## Frequently asked questions

**Can ChatGPT read images?**

Yes. ChatGPT and other multimodal assistants can read photos and screenshots you attach, including text in them.

**Is computer vision accurate on receipts?**

Usually on clear photos. Faded paper, folds and handwriting cause errors, so check totals.

**What is the difference between computer vision and multimodal AI?**

Computer vision is the ability to understand images. A multimodal model combines it with text, and sometimes audio, so you can ask questions about a picture in plain words.

**Can AI read handwriting?**

Often, if it is neat and the photo is clear. Accuracy drops with messy writing, so check names and numbers against the original.

[All AI glossary terms, A to Z](https://learn.ynteractive.com/content/glossary) · [Free prompt templates](https://learn.ynteractive.com/content/prompts)