---
title: "Discussion on \"Vector Image Search with Azure AI\" | Hashnode"
description: "Discussion on \"Vector Image Search with Azure AI\". Create an image search app using Azure Computer Vision API to find similar products or photos based on feature vectors"
url: "https://hashnode.com/posts/vector-image-search-with-azure-ai/66e796235470396d968a7c02"
---

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

Discussion

# [Vector Image Search with Azure AI](https://tjgokken.com/vector-image-search-with-azure-ai?utm_source=hashnode&utm_medium=feed)

Create an image search app using Azure Computer Vision API to find similar products or photos based on feature vectors

Sep 16, 2024 · 6 min read · tjgokken.com  
Updated Jan 5, 2025  
Read the article

-   [#azure-ai](https://hashnode.com/tag/azure-ai)

## Written by

[TJ Gokken](https://hashnode.com/@tjgokken)

@tjgokken · Sydney, New South Wales, AUS

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

Enterprise AI/ML | Quantum Computing | Software Engineering

TJ Gokken is an AI Systems Architect with a passion for bridging the gap between technology and practical application. Specializing in .NET frameworks and machine learning, TJ helps software teams operationalize AI to drive innovation and efficiency. With over two decades of experience in programming and technology integration, he is a trusted advisor and thought leader in the AI community.

## Responses 1

Markdown supported · ⌘↵ to post

[Alexander Kolobov](https://hashnode.com/@iamaleko)

[Sep 26, 2024](https://hashnode.com/posts/vector-image-search-with-azure-ai/66e796235470396d968a7c02/comment/66f4a8841196413bbf308d93)

What "image tags" are? What does ExtractImageTags function do?

[Alexander Kolobov](https://hashnode.com/@iamaleko)

[Sep 27, 2024](https://hashnode.com/posts/vector-image-search-with-azure-ai/66e796235470396d968a7c02/comment/66f4a8841196413bbf308d93#reply-66f72eb8079bf27221cc9f39)

[TJ Gokken](https://hashnode.com/@tjgokken) Is it possible, instead of base dictionary labeled images, get centers of common image clusters from API? Because if you try to match some distant from your dictionary images (image of a cat when your dictionary contains only oceans/forests) you will get very confusing results. Or is it possible to get at least somehow unified distances between detected tags (cat and tiger are more similar than cat and toaster)?

[TJ Gokken](https://hashnode.com/@tjgokken)

[Sep 28, 2024](https://hashnode.com/posts/vector-image-search-with-azure-ai/66e796235470396d968a7c02/comment/66f4a8841196413bbf308d93#reply-66f74bc27a6ff65f2fdd936d)

[Alexander Kolobov](https://hashnode.com/@iamaleko) Great question. Yes, it is possible and might actually be a better way to match images. However, the focus of this article was using Azure AI Services. That's why we relied on the image tags generated by Azure Vision API.

At the moment, Azure Vision API does not support clustering of similar images. You can get unified distances between similar tags, but that would require additional processing on top of Azure's services.

Another point is, we are working with a very small set of images as our dataset. If our dataset was 5,000 or 50,000 images instead of 5, then the tags generated by Azure Vision API become far more effective.

Hope this helps.

[TJ Gokken](https://hashnode.com/@tjgokken)

[Sep 28, 2024](https://hashnode.com/posts/vector-image-search-with-azure-ai/66e796235470396d968a7c02/comment/66f4a8841196413bbf308d93#reply-66f74ef98c0fd2c96d971504)

[TJ Gokken](https://hashnode.com/@tjgokken) It is also possible to use Azure Functions that runs Python code to calculate tag similarities using a library such as Word2Vec. This allows more advanced similarity calculations between tags.
