Browsing by Author "Perera, K.K.C."

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Image Recognition System for Paddy Leaf Diseases in Sri Lanka
    (Uva Wellassa University of Sri Lanka, 2013) Perera, K.K.C.; Rajapaksha, R.W.V.P.C.
    Paddy is the major economic crop in Sri Lanka There are mainly two seasons for paddy cultivation calls Yalaand Maha. Paddy diseases pose a major threat to rice production in Sri Lanka because of millions of rupees in direct loses and loses related to use of control measures. Ever since humans started farming, diseases have been one of the major obstacles in maximizing production. There are numerous diseases of rice such as fungi, bacteria, viruses and nematode. If we can identify these diseases in primary ages, it will give an additional advantage to prevent the diseases and to minimize the spread of them. There are mainly three paddy leaf diseases in Sri Lanka that spread speedily. Those diseases are Rice Blast (Magnaporthegrisia), Rice sheath blight (Rhisoctonisolani) and Brown spot (Cochiobolusmiyabeanus). Methodology After giving chance to upload images of infected paddy leaves in the field, first the selected image needs to be digitized. Then separate the plant leaf from its background and its known as segmentation. For second step of the process, the infected spots in the space that represent the common color (reddish brown) for all three diseases need to be calculated. Then the ratio of surface area of spots over surface area of leaf is calculated(Gliverer,et al., 2001). Finally that function compares the ratio value with given conditions and identify the disease.
  • Thumbnail Image
    Item
    Image Recognition system for Paddy Leaf Diseases in Sri Lanka
    (Uva Wellassa University of Sri Lanka, 2013) Perera, K.K.C.
    Rice is the single most important crop occupying 34 % of the total cultivated area in Sri Lanka. But rice is attacked by a number of diseases. Although some diseases are of minor importance, others cause serious economic damage. The classification and recognition of paddy diseases is one of the major technical and economical important in the agricultural industry. Consideration of the spread of specific color range of each infected leaves, shapes, textures are very important to automate this activities. The goal of this research is to develop an image recognition system that can recognize paddy diseases. Three major diseases commonly found in Sri Lanka, Rice blast (Magnaporthe grisea), Rice sheath blight (Rhizoctonia solani) and Brown spot (Cochiobolus miyabeanus) were selected for this study. Image processing starts with the digitized a color image of paddy disease leaf. Then color features of color image of disease spot on leaf were extracted and many mathematical operations was introduced to segment these images according to range of a specific color that early defined. That color ratio value is used to identify the rice disease. This approach yields excellent results by using many images of infected leaves. Use of powerful RGB camera would allow higher precision of the image color and segmentation. The proposed system is based on the JavaCV library and image processing methods.