# Feature2D, feature extraction, A problem

**URL:** <https://forum.opencv.org/t/feature2d-feature-extraction-a-problem/10872>\
**Category:** Python\
**Tags:** features2d, programming\
**Created:** [November 8, 2022, 10:02am UTC](https://forum.opencv.org/t/feature2d-feature-extraction-a-problem/10872 "2022-11-08T10:02:42Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![CZH](https://avatars.discourse-cdn.com/v4/letter/c/e56c9b/32.png) [@CZH](https://forum.opencv.org/u/CZH)\
**Post date:** [November 8, 2022, 10:02am UTC](https://forum.opencv.org/t/feature2d-feature-extraction-a-problem/10872/1 "2022-11-08T10:02:42Z")

</div>

I found that the results of feature extraction with opencv, feature2D, detect() are saved as:

`[<KeyPoint 0x7f36b5b74e10>, <KeyPoint 0x7f36b5b529f0>, <KeyPoint 0x7f36b47fb030>, < KeyPoint 0x7f35e32f6030>, ...]`

What data format is this?` < >` What is the format? What does `KeyPoint` stand for? What `does 0x7f36b47fb030` stand for? Is there a corresponding implementation of the code for reference?

Thank you very much for your advice!

---

<div class="post-metadata">

**Author:** ![berak](https://avatars.discourse-cdn.com/v4/letter/b/85f322/32.png) [@berak](https://forum.opencv.org/u/berak)\
**Post date:** [November 8, 2022, 10:30am UTC](https://forum.opencv.org/t/feature2d-feature-extraction-a-problem/10872/2 "2022-11-08T10:30:51Z")

</div>

> [@CZH](#):
>
> What does `KeyPoint` stand for?

you got a list of [KeyPoint](https://docs.opencv.org/4.x/d2/d29/classcv_1_1KeyPoint.html) objects

> [@CZH](#):
>
> What `does 0x7f36b47fb030` stand for?

it’s the in-memory address of a resp. kp.

> [@CZH](#):
>
> Is there a corresponding implementation of the code for reference?

opencv is a c++ library, there is no python code for this.  
however, [have a look at the src code](https://github.com/opencv/opencv/tree/4.x/modules/features2d/src)

> [@CZH](#):
>
> I found that the results of feature extraction with opencv, feature2D, detect()

just to clarify - this only detects keypoints. computing feaures for those is done in a diferent step (compute())

---

<div class="post-metadata">

**Author:** ![crackwitz](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.opencv.org/crackwitz/32/14_2.png) [@crackwitz](https://forum.opencv.org/u/crackwitz)\
**Post date:** [November 8, 2022, 9:16pm UTC](https://forum.opencv.org/t/feature2d-feature-extraction-a-problem/10872/3 "2022-11-08T21:16:37Z")

</div>

> [@CZH](#):
>
> What data format is this?` < >` What is the format?

that is how objects represent themselves in Python if their full state can’t or shouldn’t be in the “repr”. learn about python:

> **[Built-in Functions](https://docs.python.org/3/library/functions.html#repr)**
>
> The Python interpreter has a number of functions and types built into it that are always available. They are listed here in alphabetical order.,,,, Built-in Functions,,, A, abs(), aiter(), all(), a...