Leaf clustering using circular densities

TL;DR

This paper introduces a novel leaf clustering method based on circular density normalization of centroid contour distances, enabling effective hierarchical clustering of leaf shapes in botany.

Contribution

The paper proposes a new approach using circular densities for leaf shape normalization and clustering, improving shape recognition accuracy.

Findings

Effective clustering demonstrated on small and large datasets.

Circular density normalization improves shape comparison.

Hierarchical clustering based on density distances yields meaningful groups.

Abstract

In the biology field of botany, leaf shape recognition is an important task. One way of characterising the leaf shape is through the centroid contour distances (CCD). Each CCD path might have different resolution, so normalisation is done by associating each contour to a circular density. Densities are rotated by subtracting the mean or mode preferred direction. Distance measures between densities are used to produce a hierarchical clustering method to cluster the leaves. We illustrate our approach with a motivating small dataset as well as a larger dataset.