Chaotic-to-Fine Clustering for Unlabeled Plant Disease Images

TL;DR

This paper introduces a self-supervised clustering method for unlabeled plant disease images that leverages Kernel K-means and deep learning to improve classification accuracy across multiple datasets.

Contribution

It proposes a novel chaotic-to-fine clustering framework that reduces manual labeling by automatically grouping plant disease images using a cross iterative under-clustering approach.

Findings

Outperforms five state-of-the-art methods on multiple datasets

Effective in both balanced and unbalanced datasets

Achieves high accuracy in plant disease classification

Abstract

Current annotation for plant disease images depends on manual sorting and handcrafted features by agricultural experts, which is time-consuming and labour-intensive. In this paper, we propose a self-supervised clustering framework for grouping plant disease images based on the vulnerability of Kernel K-means. The main idea is to establish a cross iterative under-clustering algorithm based on Kernel K-means to produce the pseudo-labeled training set and a chaotic cluster to be further classified by a deep learning module. In order to verify the effectiveness of our proposed framework, we conduct extensive experiments on three different plant disease datatsets with five plants and 17 plant diseases. The experimental results show the high superiority of our method to do image-based plant disease classification over balanced and unbalanced datasets by comparing with five state-of-the-art existing works in terms of different metrics.