Image Segmentation Method for Crop Nutrient Deficiency Based on Fuzzy C-Means Clustering Algorithm

As the fact that the emergence and development of crop nutrient deficiency has become more common nowadays, this research aims to find a method to segment and determine nutrient deficiency regions of crop images based on image processing technology. The experiment starts by obtaining 256 images of various crops such as oat, wheat, beet, maize, rye, potato, kidney been and sunflower with nutrient deficiency. Secondly all the experimental images are pre-processed by color transformation and enhancement to improve quality. Finally the nutrient deficiency diseased regions of crop images were segmented by fuzzy c-means clustering (FCM) algorithm based on fuzzy clustering algorithm. In the experimental course, color space of image was transformed from RGB to HSV and images were enhanced by use of median filter method, which not only remove the noise of the image, but also keep clear edge and efficiently highlight the disease regions. To test the accuracy of segmentation, other common algorithms such as threshold, edge detection and domain division were compared with FCM. Results showed that the FCM algorithm was the appropriate algorithm for segmentation of complexity and uncertainty images of crop disease. Applying fuzzy set theory in dividing the nutrient deficiency regions is the new point of the research, and this research has great practical significance in variable rate fertilization based on image processing technology.