AUTOMATIC SEGMENTATION OF PLANT LEAF DISEASE USING IMPROVED FAST FUZZY C MEANS CLUSTERING AND ADAPTIVE OTSU THRESHOLDING (IFFCM-AO) ALGORITHM
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 3, Pages 5447-5462
AbstractAutomatic segmentation of plant leaves is vital for the detection of plant leaf diseases. In this research, we propose a novel framework for segmentation of plant leaf images using Improved Fast Fuzzy C Means Clustering and Adaptive Otsu threshold (IFFCM-AO) algorithm. In the proposed framework, initially, the plant leaf images are preprocessed using filtering and enhancement techniques. Image filtering is done for the removal of noise. In our work, we have proposed 2D Adaptive Anisotropic Diffusion Filter (2D AADF) for noise removal. Using these de-noised images, enhancement is done using Adaptive Mean Adjustment (AMA) technique. This step helps to intensify the region of interest in the image. Using the enhanced image, segmentation is performed by means of clustering and threshold. Clustering is done using the proposed Improved Fast Fuzzy C Means Clustering (IFFCMC) Algorithm and image threshold is performed using the proposed Adaptive Otsu (AO) threshold algorithm. The materials are collected in real time images for processing on it. Experimental results show that the proposed framework is effective and achieves best segmentation results compared to the previous works proposed in the literature. In addition, to show the credibility of the proposed noise removal algorithm, we have compared the proposed 2D Adaptive Anisotropic Diffusion Filter with 2D Adaptive Median Filter. In addition, we have also compared the proposed IFFCMC Algorithm with the conventional K-means clustering algorithm. Quantitative results clearly show that the proposed algorithms perform better than the traditional ones and hence aid in achieving better segmentation results.
- Article View: 123
- PDF Download: 344