Mango Leaf Ailment Detection using Neural Network Ensemble and Support Vector Machine

This paper presents a Neural Network Ensemble (NNE) for Mango Leaf Ailment Detection (MLAD) system. At first, the images of Mango leaves were cropped, then were resized and converted to their value of threshold. After that, the feature extraction methodology was applied. For pattern recognition, NNE and SVM were used. Subsequently, test images of affected leaves were uploaded to the system and then were matched to the trained ailments. The training data and test data were crossvalidated to sustain equilibrium among over-fitting and underfitting issues.