Texture and shape attribute selection for plant disease monitoring in a mobile cloud-based environment

Abstract

We focus on feature extraction and selection to best represent texture and shape properties of plant diseases in an imagebased leaf monitoring system implemented in a mobile-cloud environment. A number of textural and region-based features are aggregated from previous studies; also we introduce mean and peak indices of histogram-of-shape as disease property representations along with the proposed and enhanced shape features based on diseased regions. A total of 260 colour-based attributes and 163 shape attributes are searched to find the best potential features based on different aspects: probability of feature error, correlation, targeted-class relevancy and the separability quality of a feature. Experimental results show that the best selected feature set which combines colour-based and shape features yields high classification accuracy on wheat disease images captured by a smartphone camera and also provides insights into potential sets of features to be further implemented as a lightweight standalone mobile application.

A cluster-based feature selection method for image texture classification

“…The critical features are selected by SFS method after ranking them using three methods that are namely ACC, ReliefF, and mRMR. The experiment results proved that the combination of color and shape features listed by mRMR has the best classification performance and results respectively (using Linear SVM) [13]. In addition to, a study presented in [14] for multi-textural features classification; the texture features are basic statics (mean, standard deviation, range, and median), Tamura, GLCM, and LBP.…”

“…The best classification result obtained by polynomial-SVM and GLCM features using the Ranker as a feature selection method [12]. Likewise, Siricharoen et al, [13] proposed a plant's disease detection system which is performed in a mobile-cloud environment. The system is based on many color and shape methods to describe images of leaf plant to discover the disease.…”