Dude, Everyone Wants Pattern Analysis Tools (DEWPAT): Tools for measuring visual pattern diversity from digital images
Sanderson, J. A.; Aumentado-Armstrong, T.; Dufresne-Camaro, C.-O.; Mahler, D. L.
Show abstract
O_LIExploring the diversity and function of complex colour patterns is a fundamental interest in ecology and evolutionary biology, but progress on many questions is limited by our ability to quantify diverse visual patterns. We address this problem by introducing Dude, Everyone Wants Colour Pattern Analysis Tools (DEWPAT), a Python package for characterizing multidimensional pattern complexity. C_LIO_LIDEWPAT is a flexible framework designed to extract a diversity of components of visual pattern complexity from standard RGB and multispectral images, including entropy (information content), average gradient magnitude (edge content), high frequency content (detail granularity), generalized variance (heterogeneity), and patch dissimilarity. DEWPAT offers optional image transformation functionality, including blurring to model receiver acuity and segmentation to reduce noise. C_LIO_LIFunctions in this package return both quantitative measurements and graphical representations of color and pattern diversity. We demonstrate DEWPATs key functions and applications with three empirical examples (longhorn beetles, anole lizards, and flowers). C_LIO_LIDEWPAT has the potential to quantitatively characterize previously intractable pattern phenotypes in ways that make their features available for biological analysis. C_LI
Matching journals
The top 1 journal accounts for 50% of the predicted probability mass.
Similar papers in this journal
- Quantitative Colour Pattern Analysis (QCPA): A Comprehensive Framework for the Analysis of Colour Patterns in Nature 95%
- A General Method for Detection and Segmentation of Terrestrial Arthropods in Images 94%
- Thinking like a naturalist: enhancing computer vision of citizen science images by harnessing contextual data 93%
Similar papers in this journal
- Using machine learning to count Antarctic shag (Leucocarbo bransfieldensis) nests on images captured by Remotely Piloted Aircraft Systems 93%
- Insect Size Matters: Using Image and Dimensions Together Improves Image Classification 91%
- Exploiting facial side similarities to improve AI-driven sea turtle photo-identification systems 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.