An efficient segmentation using adaptive radial basis function neural network for tomato and mango plant leaf images

Abstract

Agriculture has become simply to feed ever-growing populations. The tomato is arguably the most well-known vegetable in agricultural areas and plays a significant role in the growth of vegetables in our daily lives. However, because this tomato has multiple diseases, image segmentation of the diseased leaf shows a key role in classifying the disease by the leaf's symptoms. Therefore, in this paper, an efficient plant disease segmentation using an adaptive radial basis function neural network (ARBFNN) classifier. The proposed radial basis function (RBF) neural network is enhanced by using the flower pollination algorithm (FPA). Firstly, the noise is detached by an adaptive median filter and histogram equalization. Then, from every leaf image, different kind of color features is extracted. After the extraction of features, those are fed to the segmentation phase to section the disease serving from the input image. The efficiency of the suggested method is analyzed based on various metrics and our technique attained a better accuracy of 97.58%.

Plant phenotyping relevance

植物葉画像から病徴領域を自動抽出する画像セグメンテーション手法の開発・評価が中心であり、植物病害状態の表現型推定に該当する。

Code and data availability

The paper uses PlantVillage leaf images (a cited public dataset, not a paper-specific deposit) and reports segmentation results, but provides no public code, models, or paper-specific data. The authors state their supporting data are available only on request from the corresponding author.

No evidence-backed public reproduction asset is currently recorded.