Computer Vision Approach for Cauliflower Disease Recognition

Abstract

Cauliflower dominates a major share in terms of total winter cropping area and production in Bangladesh. It has many health benefits like decrease the risk of obesity, diabetes, heart disease etc. It is a cultivated and winter crop and has huge demand in the country. But if proper care is not taken many serious disease will effects on plants and will reduce productivity, quantity and quality of cauliflower. Manually monitoring of plant disease is very difficult as it requires tremendous amount of work and excessive time. Automatic recognition of disease through computer vision approach is becoming more popular day by day. So in this paper we introduced a modern technique to recognize diseases that occur on plants in cauliflower. The most common disease in cauliflower disease is Bacteria Soft Rot, Black Rot, Buttoning, Downy mildew in Bangladesh. Our proposed solution would support agriculture industry of Bangladesh to grow cauliflower more effectively and will increase its production by taking proper step after automated recognize of these diseases. In our work, for image segmentation, k-means clustering is used after image preprocessing method is applied, ten relevant features are extracted. For classification, we compared various classification technique. Random Forest algorithm achieves overall 81.68% accuracy