# Gabor filter

**URL:** https://forums.openmv.io/t/gabor-filter/1895
**Category:** OpenMV Boards
**Created:** [August 21, 2020, 8:41am UTC](https://forums.openmv.io/t/gabor-filter/1895 "2020-08-21T08:41:07Z")
**Posts on this page:** 2
**Page:** 1

<div class="post-metadata">

### Author: ![openfablab](https://avatars.discourse-cdn.com/v4/letter/o/e79b87/32.png) [@openfablab](https://forums.openmv.io/u/openfablab)
#### Post date: [August 21, 2020, 8:41am UTC](https://forums.openmv.io/t/gabor-filter/1895/1 "2020-08-21T08:41:07Z")

</div>

Hello and many thanks for awesome product.

Do you have any plans to implement Gabor filter? It is very useful and we rely on it in threaded parts detection in manufacturing.  
Now we use RPi but wanted to switch to OpenMV due to its better embedability and debug simplicity.

---

<div class="post-metadata">

### Author: ![kwagyeman](https://yyz1.discourse-cdn.com/flex029/user_avatar/forums.openmv.io/kwagyeman/32/4_2.png) [@kwagyeman](https://forums.openmv.io/u/kwagyeman)
#### Post date: [August 21, 2020, 2:22pm UTC](https://forums.openmv.io/t/gabor-filter/1895/2 "2020-08-21T14:22:34Z")

</div>

You should just hand code the kernels for use, then use the morph() method on the image.

You can create copies of the small image patch you want to look at with crop() and then morph() the different kernels there. You can then sum up each morphed image using a method like get\_stats() to commute image stats.