Sunflower Diseases Recognition Using Computer Vision-Based Approach

Abstract

Sunflower (Helianthus annuus) is a plant categorized as a low to medium drought-sensitive crop. It adds a significant value to the agricultural-based economy. But nowadays worldwide sunflower production is in crisis due to its many diseases. But if proper action is not adopted earlier, many serious diseases will have affect plants. Consequently, it will reduce the productivity, quantity, and quality of sunflower. Manual identification of disease is a very tedious task or perhaps impossible at times. Nowadays, computer vision-based technique has gained its popularity in the field of object recognition. In this paper, we proposed an approach for sunflower disease recognition. A total of 650 images were used to accomplish this work. The image data processing techniques such as resizing, contrast, and color enhancement have also been used. We have used k-means clustering for segmenting the diseases affected region and then extracted features from the segmented images. The classification has performed using five classifiers. We calculated the seven performance evaluation metrics for the performance measurement of each classifier. The highest average accuracy of 90.68% has been obtained for the Random Forest classifier that outperformed others.