Detection of Decreased Kidney And Lung Function Through the Iris of the Eye Using the Method Convolutional Neural Network (CNN)
Keywords:
Iridology, Human Iris, Excretion, Convolutional Neural Network, deep learningAbstract
Iridology is a scientific study of the shape and structure of the iris that can provide an overview of every organ in the human body. Research on computerized iridology has been carried out. Cases of decreased organ excretion through iridology that are commonly found are the organs of the lungs and kidneys. The purpose of this research using a deep learning approach namely Convolutional Neural Network to detect decreased organ function in the lungs and kidneys through the iris of the eye. The study of iridology and iris image obtained from iridologists. The cropping method is used to extract the identified part of the eye image. The cropping method consists of a median filter to remove noise, a hough circle transforms to get an iris circle and a region of interest to get the identified part. Image cropping results are used as training data and test data. The Convolutional Neural Network training process uses the VGG16 model with 2 classes, normal and not normal. The results of Convolutional Neural Network research can detect decreased organ function in excretion through the iris of the eye. From 40 testing data with details of 20 right eyes and 20 left eyes, the accuracy is 90%.
References
Li Xu , Jimmy SJ Ren, Ce Liu, Jiaya Jia, 2014, “Deep convolutional neural Network for Image deconvoluton”, Advances in Neural Information Processing Systems 27 (NIPS 2014)
NS Sarode, 2015, Iris Recognition using LBP with Classifiers-KNN and NB, International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Index Copernicus Value (2013)
Goodfellow, I., Bengio, Y, and Courville, A. 2016. Deep Learning (Adaptive Computation and Machine Learning Series). The IMT Press.
GB Huang, 2005, P Saratchandran “A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation”, IEEE, http://www.eng.buffalo.edu/~psingla/Teaching/MAE502/ReadingPapers/MRANPapers.pdf
Saccharin, Farida. 2005, Iridology: A Complete Guide To Diagnosing Through the Iris And To Related Forms of Treatment, New York, USA
Smereka, Marcin & Duleba, Ignacy. (2008). Circular Object Detection Using a Modified Hough Transform. Applied Mathematics and Computer Science. 18. 85-91. 10.2478/v10006-008-0008-9.
Sherif E.Hussein,Osama A.Hassan,Malcolm H.Granat,"Assessment of the potential iridology for diagnosing kidney disease using wavelet analysis and neural networks , Biomedical Signal Processing and Control journal, Volume 8, Issue 6, November 2013, Pages 534-541
Liu, Tianyi, Shuangsang Fang, Yuehui Zhao, Peng Wang dan Jun Zhang. 2015. Implementation of Training Convolutional Neural Networks. https://arxiv. org/ftp/arxiv/papers/1506/1506.01195.pdf.
