# Using ES for bag of visual words image search II

**URL:** <https://discuss.elastic.co/t/using-es-for-bag-of-visual-words-image-search-ii/170142>\
**Category:** Elasticsearch\
**Created:** [February 27, 2019, 10:38am UTC](https://discuss.elastic.co/t/using-es-for-bag-of-visual-words-image-search-ii/170142 "2019-02-27T10:38:47Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![IngoM](https://avatars.discourse-cdn.com/v4/letter/i/e480ec/32.png) [@IngoM](https://discuss.elastic.co/u/IngoM)\
**Post date:** [February 27, 2019, 10:38am UTC](https://discuss.elastic.co/t/using-es-for-bag-of-visual-words-image-search-ii/170142/1 "2019-02-27T10:38:47Z")

</div>

Hey,

This is a follow-up question to the following discussion:

> [@Using ES for bag of "visual" words image search?](https://discuss.elastic.co/t/using-es-for-bag-of-visual-words-image-search/81431):
>
> Disclaimer: Newbie here, forgive me if I'm butchering some terms/concepts. Hi all, I am currently working on a system for doing visual similarity search and am considering using ES to do the search and indexing. A popular method for visual search is the bag of "visual" words approach. The idea is to map the problem of visual search to text search so that text search techniques suddenly apply (inverted index, tf-idf, etc.). Without going into details, I currently have a function that takes an i…

Since the topic is roughly two years old, I wonder if there are any new resources or features solving this problem. As the previous author I'm planning on feeding encoded features vectors such as this into ES:

```auto
[word1: 10, word20: 3, word32: 4, word200: 11]

```

which basically encodes the TF of each word occuring in the current document. For testing if the concept works at all I spared the frequency encoding and passed my feature vectors plain as:

```auto
[word1 word1 word2 word3 word3 word3 ...]

```

However the matching performance of this approach in ES is already significantly worse than what I've implemented in a standalone application as a proof of concept where I basically just create an inverted index of all my indexed documents which is then queried with a bunch of test images.

This is exactly what I expected ES to do internally however it disproves me by showing significantly worse results. Do I have any errors in my thought process or is there any setting in ES that behaves differently than what I'm expecting?

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\
**Post date:** [March 27, 2019, 10:38am UTC](https://discuss.elastic.co/t/using-es-for-bag-of-visual-words-image-search-ii/170142/2 "2019-03-27T10:38:51Z")

</div>

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.