Early Rubeosis Iridis Detection Using Feature Extraction Process
Iris image analysis studies the relationship between human health and changes in the anatomy of the iris. One of the changes related to the anatomy of the iris is diabetes. This illness can be determined from the iris of human eyes because it affects the eyes. Latest advanced technologies are introduced in the image processing that helps automate the detection of diabetes based on the analysis of iris feature extractions. Various features are detected on iris such as texture, colour, histogram and shape. In this paper, the dataset of iris image from Warsaw Biobase are used to detect and recognise the rubeosis iridis by extracting their details using image processing methods. The results obtained from the experiment show that the normal and abnormal iris image can be classified using original and small size of iris image. Through this experiment, it was discovered that images for abnormal original are greater than 1,200,000 pixels while for small size are less than 35,000 pixels. On the contrary, normal original size are less than 1,200,000 pixels and for small are less than 25,000 pixel. By considering these results, the proposed method can be extended to the iris monitoring system.