14-12-2012, 01:30 PM
LEAF DISEASE SEVERITY MEASUREMENT USING IMAGE PROCESSING
LEAF DISEASE SEVERITY.docx (Size: 24.92 KB / Downloads: 25)
INTRODUCTION:
Sugarcane being a long duration crop of 10 to 18 months, attacked by a number of diseases. Fungi caused diseases in sugarcane are the most predominant diseases which appear as spots on the leaves. These spots prevent the vital process of photosynthesis to take place, hence to a large extent affects the growth and consequently the yield. In case of severe infection, the leaf becomes totally covered with spots. The various types of diseases on sugarcane determine the quality, quantity, and stability of yield. The diseases in sugarcane not only reduce the yield but also deteriorate of the variety and its withdrawal from cultivation.Excessive uses of pesticide for plant diseases treatment increases the danger of toxic residue level on agricultural products and has been identified as a major contributor to ground water contamination also pesticides are among the highest components in the production cost their use must be minimized. This can be achieved by estimating severity of disease and target the diseases places, with the appropriate quantity and concentration of pesticide. The naked eye observation method is generally used to decide diseases severity in the production practice but results are subjective and it is not possible to measure the disease extent precisely. Grid counting method can be used to improve the accuracy but this method has cumbersome operation process and time consuming. Image processing technology in the agricultural research has made significant development.
PRESENT THEORY:
To recognize and classify sugarcane fungi disease an automated system has been implemented using algorithm such as chain code technique, bounding box method and moment
analysis[1].To measure severity of Rust disease on Soybean, disease spot have segmented by Sobel operator to find out spot edge and plant disease severity has measured by calculating the quotient ofdisease spot area and leaf area[2].Earlier severity of attack of herbivorous insects on leaves have been calculated using video digitizer for pesticide application[3].Extent of color patches due to micronutrient
deficiency or fungal disease on leaves have calculated by color thresholding method [4].In particular disease color as well as shape of leaves also changes that have measured by using HSV color space, Speeded Up Robust Features (SUFR), Scale Invariant and Feature Transformation (SIFT)[5].By choosing color difference due to fungal infection and lookup table it is possible to distinguish the healthy leaf area from diseased one[6].Disease severity can be measured in three different ways that are Visual Rating, Image Analysis and Hyper spectral Imaging[7].Using multispectral images thresholding operation Ratio of Infected Area (RIA), Lesion Color Index (LCI) and Severity Index of Soybean rust have been calculated[8]. Similarly using reflectance value in the green and NIR regions, same time the SWIR domains, orange rust of sugarcane has detected[9].These spectral reflectance value is also useful to determine chlorophyll index which is helpful for sugarcane infected plots detection and monitoring from Satellite imagery[10].Disease in wheat plant has detected in early stage using spectral reflectance of plant and neural network[11].
RELEVANCE:
Fungi-caused diseases in sugarcane are the most predominant diseases which appear as spots on the leaves. If not treated on time, causes the severe loss. Excessive use of pesticide for plant diseases treatment increases the cost and environmental pollution so their use must be minimized. This can be achieved by targeting the diseases places, with the appropriate quantity and concentration of pesticide by estimating disease severity using image processing technique. Simple threshold and Triangle thresholding methods are used to segment the leaf area and lesion regionarea respectively. Finally diseases are catcogrise by calculating the quotient of lesion area and leaf area. The accuracy of the experiment is found to be 98.60 %. Research indicates that this method to calculate leaf disease severity is fast and accurate.