Delaunay Triangulation on Skeleton of Flowers for Classification

TL;DR

This paper introduces a novel flower classification method using Delaunay triangulation on skeletons derived from segmented flower images, extracting geometric features for accurate categorization.

Contribution

It presents a new approach combining skeletonization, Delaunay triangulation, and interval-valued features for flower classification, validated on a custom dataset.

Findings

Effective classification accuracy demonstrated on 30 flower classes

Skeleton-based geometric features improve classification robustness

Proposed method outperforms traditional feature-based approaches

Abstract

In this work, we propose a Triangle based approach to classify flower images. Initially, flowers are segmented using whorl based region merging segmentation. Skeleton of a flower is obtained from the segmented flower using a skeleton pruning method. The Delaunay triangulation is obtained from the endpoints and junction points detected on the skeleton. The length and angle features are extracted from the obtained Delaunay triangles and then are aggregated to represent in the form of interval-valued type data. A suitable classifier has been explored for the purpose of classification. To corroborate the efficacy of the proposed method, an experiment is conducted on our own data set of 30 classes of flowers, containing 3000 samples.