SUPER RESOLUTION USING ARTIFICIAL INTELLIGENCE FOR RETINA IMAGE ENHANCEMENT
The retina image is an important area for medical treatment of the disease. By observing the changes in the blood vessels in the retina lines, doctors can diagnose diseases, to collect and analyze the symptoms and the development of related treatments. Consequently, improving retinal image quality is an important preprocessing step. In order to improve retinal image quality, several techniques have been proposed such as wavelet transform [1,2,3], very-deep-super-resolution (VDSR) , super-resolution-convolutional neural network (SRCNN) ... but still can not provide high efficiency by persistent high noise, poor image results, not optimal for computational complexity and memory consumption. Therefore, in this paper, we propose a particular method of retinal images quality enhancement via super resolution using artificial intelligence to directly reconstruct the high resolution image from the original low resolution image. By the analysis and calculated results in picture quality parameters through experimental treatment, we will demonstrate that the proposed method is superior to the state-of-the-art methods, especially in terms of time performance.