← Marketplace

Image Augmentor


Coming back soon: currently not available. Performs histogram normalization and denoising (optional) on one (or more) images in preparation for further processing such as change detection.

Technical information

The Augmentor first applies a color quantization algorithm that reduces the number of distinct pixel colors in the image to 64. Histogram equalization is then applied, increasing contrast in the image, followed by a final adaptive denoising and color denoising algorithm that can be set depending on the amount of noise in the image.
The Augmentor is applicable to a variety of instances due to its ability to take custom denoising and color denoising factors depending on the noise of the image. The default denoising factor is 0 and the default color denoising factor is 10, with a recommended denoising value of around 50 for images with high noise like oil spills, and a recommended denoising value of 0 for images with high amounts of detail like cities.

Use cases include Vegetation Management, Urban Planning & Construction, Fire Risk Estimation, Land Use and Management, Forestry, Powerline inspection, Trainline inspection

Supported Workflows:

Data platform:

Data blocks:


“denoising_factor” – default 0
description “Parameter regulating filter strength for luminance component. Bigger h value perfectly removes noise but also removes image details, smaller h value preserves details but also preserves some noise”

“colour_denoising_factor” – default 10 if denoising_factor different from 0, and 0 otherwise.
The same as h but for color components. For most images value equals 10 will be enought to remove colored noise and do not distort colors

Note: For block versions 2.0.5-public and higher, the output is in the CRS "EPSG:3857".

Example Input for Data blocks




Terms & conditions

View the End User License Agreement conditions

Ready to get started?

Explore UP42 now.

Sign in or create an account