Adaptive Gabor Filters for Interpretable Color Texture Classification

2022

We introduce the use of trainable feature extractors, based on the Gabor function, into the interpretable machine learning domain. The use of adaptive Gabor filters allows for interpretable feature extraction to be learned automatically in a domain agnostic way, and comes with the benefit of a large reduction in trainable parameters. We implemented the filters into an image classification variant of learning vector quantization. We extend and compare the image classification variant of learning vector quantization with adaptive Gabor filters and demonstrate the proposed technique on VisTex color texture images. The adaptive Gabor filters show promising results for interpretable and efficient color texture classification.

Link

@inproceedings{Luimstra2022,
title = {Adaptive Gabor Filters for Interpretable Color Texture Classification},
author = {Gerrit Luimstra and Kerstin Bunte},
month = {5-7 October},
organization = {},
editor = {Michel Verleysen},
booktitle = {Proc. of the  30th "European Symposium on Artificial Neural Networks (ESANN)},
year = {2022},
publisher = {i6doc.com},
address = {Bruges (Belgium) and online event},
pages = {61--66},
abstract = {We introduce the use of trainable feature extractors, based on the Gabor function, into the interpretable machine learning domain. The use of adaptive Gabor filters allows for interpretable feature extraction to be learned automatically in a domain agnostic way, and comes with the benefit of a large reduction in trainable parameters. We implemented the filters into an image classification variant of learning vector quantization. We extend and compare the image classification variant of learning vector quantization with adaptive Gabor filters and demonstrate the proposed technique on VisTex color texture images. The adaptive Gabor filters show promising results for interpretable and efficient color texture classification.},
doi = {},
url = {https://www.esann.org/sites/default/files/proceedings/2022/ES2022-87.pdf},
isbn = {978287587084-1},
}