Authors : J. Sujatha and S.P. Rajagopalan
Abstract: This study proposes a method to identify Parkinson disease classifying patients as normal or abnormal using the latest machine learning algorithms. The image is acquired, converted to gray scale, preprocessed using Wiener filter. Canny edge detection method is used which involves image smoothing, gradient operation, non maxima suppression, hysteresis thresholding and connectivity analysis. Then image is segmented using fuzzy C-means. Features are extracted using GLCM technique and ANFIS classification is used to classify patients as normal or abnormal. Experimental results proves that patients suffering from neurological disease can be effectively detected using this method. A total of 167 spiral images were used out of which 56 were normal patient and 111 were abnormal collected from various sources. A classification accuracy of 99% is achieved.
J. Sujatha and S.P. Rajagopalan, 2017. Handwritten Image Analysis to Identify Parkinson Disease using Fuzzy C-means, GLCM and ANFIS Classification. Journal of Engineering and Applied Sciences, 12: 8295-8301.