---
title: "Discussion on \"How Reverse Image Search Actually Works: 1024-Dimensional Embeddings and Cosine Similarity\" | Hashnode"
description: "Discussion on \"How Reverse Image Search Actually Works: 1024-Dimensional Embeddings and Cosine Similarity\". If you've ever clicked an image and asked \"find me more like this,\" you used a reverse image search. Under the hood, it has nothing to do with filenames or keywords. An image has no natural text token"
url: "https://hashnode.com/posts/how-reverse-image-search-actually-works-1024-dimensional-embeddings-and-cosine-similarity/6ad18960ac35882edafef651"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [How Reverse Image Search Actually Works: 1024-Dimensional Embeddings and Cosine Similarity](https://omnipic-studio.hashnode.dev/how-reverse-image-search-actually-works-1024-dimensional-embeddings-and-cosine-similarity?utm_source=hashnode&utm_medium=feed)

If you've ever clicked an image and asked "find me more like this," you used a reverse image search. Under the hood, it has nothing to do with filenames or keywords. An image has no natural text token

Oct 16 · 5 min read · omnipic-studio.hashnode.dev  
Read the article

## Written by

[eden zhang](https://hashnode.com/@edenzhang)

@edenzhang · Hefei, China

  
[View profile](https://hashnode.com/@edenzhang)

## Responses

Markdown supported · ⌘↵ to post

No responses yet.