A Survey on Detection and Classification of Cotton Leaf Diseases

A Survey on Detection and Classification of Cotton Leaf Diseases

A Survey on Detection and Classification of Cotton Leaf Diseases . Cotton is the most important cash crop in India. It is also known as “White Gold” or “The King of fibres” among all cash crops in the country. About 80-90% of the diseases which occur on the leaves of cotton are Alternaria leaf spot, Cercospora leaf spot, Bacterial blight and Red spot. This paper presents a survey on detection and classification of cotton leaf diseases. It is difficult for human eyes to identify the exact type of leaf disease which occurs on the leaf of plant.

The aim of pre-processing is to improve the quality of image by removing unwanted noise from the image. Few researchers have worked on removal of background and shadow from the image. There are various types of noises which are present in the images such as Gaussian noise, Salt and Pepper noise.

 

A Survey on Detection and Classification of Cotton Leaf Diseases

 

A Survey on Detection and Classification of Cotton Leaf Diseases

A Survey on Detection and Classification of Cotton Leaf Diseases

a) Otsu Thresholding:

Otsu thresholding method involves iterating through all the possible threshold values and calculating the object data using the measure of spread. The example for this is the number of pixels that either falls in the foreground or the background. The aim of Otsu thresholding technique is to find out the threshold value where the sum of foreground and background spreads is at its minimum . When Otsu thresholding is applied on the gray diseased leaf image then using one threshold value.

B) K-means Clustering:

K-means clustering is a simplest unsupervised learning algorithm, which makes k (number of clusters) clusters for image segmentation. A cluster is a collection of objects which have similar property and are “dissimilar” to the objects that belongs to other clusters . K means clustering works as, it first chooses initial k centroids, then it form k clusters by assigning all data points to closest centroid and finally it recompute the centroids of each cluster. The weakness of k-means technique is that, with a few samples of image data, it may result into inaccurate clustering.

 

Leave a Comment