# CatSIM: A Categorical Image Similarity Metric

arXiv: https://arxiv.org/abs/2004.09073 · HTML: https://mlsanity.com/paper/2004.09073/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 45 references that are in the map.
- First posted on arXiv 20 Apr 2020.

## Builds on (most cited first, 2 of 2)

- [Efficient Segmentation: Learning Downsampling Near Semantic Boundaries](https://mlsanity.com/paper/1907.07156/) (2019)
- [FAST Adaptive Smoothing and Thresholding for Improved Activation Detection in Low-Signal fMRI](https://mlsanity.com/paper/1702.00111/) (2017)

## Abstract (arXiv)

We introduce CatSIM, a new similarity metric for binary and multinary two- and three-dimensional images and volumes. CatSIM uses a structural similarity image quality paradigm and is robust to small perturbations in location so that structures in similar, but not entirely overlapping, image or volumetric regions are rated higher than by simple matching. The metric can also compare arbitrary regions inside images and volumes. CatSIM is evaluated on artificial data sets, validated by comparing with human perception in two separate image quality assessment surveys, and illustrated on two datasets. The publicly available R package textttcatsim implements the methodology.