Some links in this post may be affiliate links. We may get paid if you buy something or take an action after clicking one of these, but without addictional costs for you compared to direct buying.

Oil Paint image transformation with Raspberry PI and OpenCV

Raspberry pi opencv oilpainting featured image

Beside being a fantastic tool for Artificial Intelligence computing, OpenCV also makes available a number of options to create cool effects applied to pictures. One of these is Oilpainting, which creates an oil paint from your image, able to run in a Raspberry PI

In this tutorial, I’m going to show you how to setup and use oilpainting effect from Raspberry PI with OpenCV and Python.

OpenCV isn’t new in my posts, as I already used it to cartoonize images with Raspberry PI. Tosay’s effect is similar, but getting a more artistic result.

The biggest problem is that OpenCV xphoto module isn’t available in default python3-opencv package, but requires opencv-contrib-python (available from pip package manager). I tried installing latest version, but I had same problem as many users: it takes a veeeery long time to compile. Some heroes measured that in their Raspberry PI 3 model B this installation required up to 8 hours!

Solution is using secon-last version, according to opencv-contrib-python releases page. This makes compiling faster. At the time of this article, latest version is, so I’ll use

For this project I’m going to use a Raspberry PI 3 model B+, but this will also work with newer Raspberry PI computer boards.

What We Need

Raspberry PI 3 Model B+ image

As usual, I suggest adding from now to your favorite e-commerce shopping cart all needed hardware, so that at the end you will be able to evaluate overall costs and decide if continuing with the project or removing them from the shopping cart. So, hardware will be only:

Check hardware prices with following links:

Amazon raspberry pi boards box
Amazon Micro SD box
Amazon Raspberry PI Power Supply box

Prepare Operating System

Start preparing your Raspberry PI OS, with install Raspberry PI OS Lite guide (to have a fast, headless OS) or install Raspberry PI OS Desktop (getting a Desktop environment, so working with its internal terminal). I will use Lite distribution and I will move files by sftp session (with filezilla).

Make your OS up to date. From terminal:

sudo apt update -y && sudo apt upgrade -y

Install required packages. Beside pip3, opencv has a long listo of dependencies non resolved automatically… Moreover, as opencv-contrib-python requires pip version >= 19.3 (check with “pip -V” command), we also need to upgrade pip:

sudo apt install python3-pip libatlas-base-dev python3-h5py libharfbuzz0b libwebp-dev libtiff5 libjasper-dev libilmbase23 libopenexr-dev libavcodec-dev libavformat-dev libswscale-dev libv4l-dev libqtgui4 libqt4-test libgstreamer1.0-0 libgtk-3-dev 
pip3 install --upgrade pip
python3 -m pip install opencv-contrib-python==

OpenCV Oil Painting Image Script

You can get a copy of this script directly in your Raspberry PI with following terminal command:


You can also explore script content with cat or nano commands. This script can be used with following terminal command, caring that image filename shouldn’t include a dot (excluding the one before file extension):

python3 your_image.jpeg

Please find below script description. As oilpainting is a direct OpenCV, we need only to open image file, apply transformation and save new file.

opencv_oilpainting script starts importing required libraries:

import cv2
import sys

After this, filename variable gets image file name from our command, by splitting name from extension using “.” as delimeter:

filename = sys.argv[1].split(".")

Image is then read to “img” variable. Oilpainting module applies desired effect, saving results to “oil” variable:

img = cv2.imread(sys.argv[1])
oil = cv2.xphoto.oilPainting(img, 10, 1)

Oilpainting function requires following variables:

  • src: Input three-channel or one channel image
  • size: neighbouring size is 2-size+1
  • dynRatio: image is divided by dynRatio before histogram processing
  • [, dst] (optional): Output image of the same size and type as src.

So, changing “size” parameter you can get different results on image processing.

Finally, oilpaint-ed image is saved with a different name to avoid overwriting:

cv2.imwrite(filename[0]+"_oil."+filename[1], oil)

OpenCV Oilpainting Examples

I’ll use some example pictures from free Pixabay service to show some results.

Raspberry pi opencv oilpainting examples

Following picture, on the other side, compares different setting for size parameter, which enables different resolution used for transforming original image:

Raspberry pi opencv oilpainting different sizes


How useful was this post?

Click on a star to rate it anonymously!

Average rating 0 / 5. Vote count: 0

No votes so far! Be the first to rate this post.

We are sorry that this post was not useful for you!

Let us improve this post!

Tell us how we can improve this post?

Leave a Reply

Your email address will not be published. Required fields are marked *

I accept the Privacy Policy