---
title: "segmentation in the feature space"
url: "https://openforis.support/questions/78/segmentation-in-the-feature-space"
tags: ["geospatialtoolkit"]
status: "answered"
score: 0
answer_count: 1
asked: "2014-10-29T08:44:40"
last_activity: "2014-10-29T09:34:02"
source: "Open Foris Support - Q&A Forum"
license: "Copyright Open Foris, 2026. Some rights reserved under creative commons license."
---

# segmentation in the feature space

Asked by Anssi on 2014-10-29

A question received via email: 

I used the oft-cluster.bash and oft-clump on two sets of images: 1973 and 2014. The results for 1973 did not look good. For 2014, the results were superb except for one thing. The very tiny polygons. How to remove them?


## Answer (score 0, by Anssi on 2014-10-29)

Link: https://openforis.support/questions/78/segmentation-in-the-feature-space/79

There are at least two nice ways to accomplish this. First, you can use oft-seg, pass the output of the oft-clump to the program using the -um option and give a desired minimum size in pixels. Second, you can use the gdal_sieve.py. The difference between the two is that whereas oft-seg merges the small segments with the **most similar** neighboring segment gdal_sieve.py merges them with the **largest** neighboring polygon.