Lack of apparent shape and texture features in disease recognition (Powdery Mildew and Anthracnose) of crop is a key challenge of Agriculture domain in the last few decades. The various soft computing techniques exists in computer vision system still there is need of most efficient methods to meet accuracy. In this work An enhanced Wavelet-PCA based Statistical Feature Extraction technique along with Modified Rotation Kernel Transformation (MRKT) based directional features is proposed in order to address the issues arising in different methodologies for plant disease recognition. This enhanced scheme extracts twenty wavelet features in addition to twelve direction features for different plant parts mango flower, fruit and leaf. This research work is an extended part presents in reference 1 by the authors. The feature set of total 32 features is used to train with Artificial Neural Network to diagnose both Powdery Mildew and Anthracnose disease which occur in the form of Fungus and black spots respectively on different parts of mango plant. The results obtained are found with accuracy of 98.50%, 98.75%, and 98.70% respectively for flower, fruit and leaf 

Machine vision and soft computing techniques have been promising in the field of agriculture and horticulture to remove the barriers of conventional methods for detecting the plant diseases using different plant parts. Image segmentation technique is first and primary step in all the related researches such as fruit grading, leaf lesion region detection etc. In this paper, a robust technique for Mango crop using different plant parts such as Fruit, Flower and Leaf has been proposed in order to detect the disease more accurately. The captured real time images are pre-processed for illumination normalization and color space conversion before segmentation. The standard K-Means clustering scheme has been made adaptive and edge detection transforms have been applied to improve the segmentation results. Here, the objective function of K-Means clustering technique has been modified and cluster centers also have been updated to segment the diseased parts from images. The results obtained are better in the terms of both general human observation and in computational time.