CLASSIFICATION OF IRIS IMAGE OF PATIENT CHRONIC RENAL FAILURE (CRF) USING WATERSHED ALGORITHM AND SUPPORT VECTOR MACHINE (SVM).

  • Source: Journal of Theoretical & Applied Information Technology . 9/30/2016, Vol. 91 Issue 2, p390-396. 7p.
  • Author(s): WIBAWA, ADHI. D.; SITORUS, MAYA. A. R.; PURNOMO, MAURIDHI. H.
  • Abstract: Iridology is an alternative method in studying the condition of human internal organ through the image of iris. Iris chart has been introduced by scientists (Bernard Jensen) long time ago. In this paper we classified the iris image of patients CRF (Chronic Renal Failure) on stage 5 (End Stage of Renal Disease). Sixty one hemodialysis patients and 21 healthy volunteer with normal or nearest normal kidneys participated in this research. Iris image of CRF patients were taken using specific iris camera. Watershed transform technique was used to extract the features of iris image of hemodialysis patients. The ROI (region of interest) of iris image of renal organ is at 5.35-5.95 (252° – 268°) for right eye and at 6.05-6.6 (272° – 288°) for left eye assuming that the circle of iris is divided into 120 points (360°). The medical records of participants were used to validate the result of this study. The result showed that 87.5% of patients hemodialysis has shown broken tissue on their right iris and 89.3% has shown broken tissue on their left iris. In conclusion, the condition of renal organ of CRF patients mostly showed broken tissue in their iris image. SVM was used to recognize the iris image whether it contains broken tissue that showing kidney disease or not, and the accuracy showed that for learning and testing dataset, best mean of precission is 87.5% and best mean recall is 91.7% given by the percentage split 90 (where the data training was 90% and data testing was 10%).
  • Copyright of Journal of Theoretical & Applied Information Technology is the property of Journal of Theoretical & Applied Information Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder’s express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.

Leave a Reply

Your email address will not be published. Required fields are marked *

Please slide to verify that you are human *