combinepdf (5)

PROPOSEDMETHODOLOGY:
1.Image Acquisition: First we need to select the plant which is affected by the disease and then
collect the leaf of the plant and take a snapshot of leaf and load the leaf image into the system.
2.Segmentation: It meansrepresentation of the image in more meaningful and easy to analyse
way. In segmentation a digital image is partitioned into multiple segments can defined as superpixels.
Low Contrast: image pixel values are concentrated near a narrow range.
Contrast Enhancement: In figure.2, the original image is the image given to the system and the
output of the system after contrast enhancement.
3. Feature extractions, is the process done after segmentation. According to the segmented
information and predefined dataset some features of the image should be extracted. This
extraction could be the any of statistical, structural, fractal or signal processing. Color cooccurrence
Method, Grey Level Co-occurrence Matrices (GLCM), Spatial Gray-level
Dependence Matrices (SGDM) method, Gabor Filters, Wavelets Transform and Principal
component analysis are some methods used for feature extraction
4. Classification of diseases
Classification technique is used for training and testing to detect the type of leaf disease.
Classification deals with associating a given input with one of the distinct class. In the given
system support vector machine [SVM] is used for classification of leaf disease. The classification
process is useful for early detection of disease, identifying the nutrient deficiency.
Based on classification leaves are mainly affected with fungal, bacterial and viral. The
following describes common symptoms of fungal, bacterial and viral plant leaf diseases.
a) Bacterial disease symptoms:
The disease is characterized by yellowish green spots which come into view as watersoaked.
The lesions amass and then appear as dry dead spot
86