Abstract-Slit Lamp (SL) is the equipment commonly used in most eye clinics. This instrument allows to observe ocular structures of both the anterior segment and posterior segment with different magnification values. Currently is very common obtain images from SL with a Smartphone (for documentation purposes) by means of a simple adapter in the eyepiece. These images lose their diagnostic quality due to the information lose to correct the lack correction of optical aberrations and noise introduced by this system. This paper analyzes the hardware settings and image characterization to need diagnostic quality image in SL. For this purpose a universal adapter for SLR cameras were developed. To adquisition process image the camera software capture were use. They were captured 128 images: 73 of anterior segment, 25 fundus and the rest with a magnifying glass and panfunduscope. These images were characterized by type and noise power.
Color images of the retina inherently involve noise and illumination artifacts. In order to improve the diagnostic quality of the images, it is desirable to homogenize the nonuniform illumination and increase contrast while preserving color characteristics. The visual result of different pre-processing techniques can be very dissimilar and it is necessary to make an objective assessment of the techniques in order to select the most suitable. In this article the performance of eight algorithms to correct the non-uniform illumination, contrast modification and color preservation was evaluated. In order to choose the most suitable a general score was proposed. The results got good impression from experts, although some differences suggest that not necessarily the best statistical quality of image is the one of best diagnostic quality to the trained doctor eye. This means that the best pre-processing algorithm for an automatic classification may be different to the most suitable one for visual diagnosis. However, both should result in the same final diagnosis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.