Retinal Digital Image Quality Improvement As A Diabetes Retinopatic Disease Detection Effort

Image processing is a technical term that is useful for modifying images in various ways. In medicine, image processing has a very important role. One example of images in the medical world, namely retinal images that can be obtained from a fundus camera. The image of the retina is useful in the detection of diabetic retinopathy. In general, the detection of diabetic retinopathy is done by direct observation by a doctor on the retinal image. The weakness of this method is the slow handling of the disease. For this reason, a computer system is needed to help doctors detect diabetes retinopathy quickly and accurately. This system involves a series of digital image processing techniques that are able to process retinal images into images with good quality. In this research, a method to improve the quality of retinal images will be designed by comparing the methods for adjusting histogram equalization, contrast stretching, and increasing brightness. The performance of the three methods will be evaluated using Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), and Signal to Noise Ratio (SNR). Low MSE values and high PSNR and SNR values of an image indicate that the image has good quality. From the results of the study, it was obtained that the image used was the best to use, as evidenced by the lowest MSE values and the highest SNR and PSNR values compared to other techniques. This indicates that adaptive histogram equalization techniques can improve image quality while maintaining information from the image itself.