期刊名称：International Journal of Electrical and Computer Engineering
电子版ISSN：2088-8708
出版年度：2016
卷号：6
期号：6
页码：2674-2681
DOI：10.11591/ijece.v6i6.pp2674-2681
语种：English
出版社：Institute of Advanced Engineering and Science (IAES)
摘要：Retinal disease is the very important issue in medical field. To diagnose the disease, it needs to detect the true retinal area. Artefacts like eyelids and eyelashes are come along with retinal part so removal of artefacts is the big task for better diagnosis of disease into the retinal part. In this paper, we have proposed the segmentation and use machine learning approaches to detect the true retinal part. Preprocessing is done on the original image using Gamma Normalization which helps to enhance the image that can gives detail information about the image. Then the segmentation is performed on the Gamma Normalized image by Superpixel method. Superpixel is the group of pixel into different regions which is based on compactness and regional size. Superpixel is used to reduce the complexity of image processing task and provide suitable primitive image pattern. Then feature generation must be done and machine learning approach helps to extract true retinal area. The experimental evaluation gives the better result with accuracy of 96%.
其他摘要：Retinal disease is the very important issue in medical field. To diagnose the disease, it needs to detect the true retinal area. Artefacts like eyelids and eyelashes are come along with retinal part so removal of artefacts is the big task for better diagnosis of disease into the retinal part. In this paper, we have proposed the segmentation and use machine learning approaches to detect the true retinal part. Preprocessing is done on the original image using Gamma Normalization which helps to enhance the image that can gives detail information about the image. Then the segmentation is performed on the Gamma Normalized image by Superpixel method. Superpixel is the group of pixel into different regions which is based on compactness and regional size. Superpixel is used to reduce the complexity of image processing task and provide suitable primitive image pattern. Then feature generation must be done and machine learning approach helps to extract true retinal area. The experimental evaluation gives the better result with accuracy of 96%.
