Tracing of Strabismus Detection Using Hough Transform

Abstract

The Strabismus (squint) is one of the most common vision disorders in children. It can bring a discomfort and serious negative impacts on daily life. A timely diagnosis is needed to prevent from getting worse. However, the traditional diagnosis screening is usually done manually and requires expertise, time, and high cost due to the sophisticated equipment. Thus, the proposed automated strabismus detection using computer aided diagnosis can help to reduce time for the ophthalmologist to diagnose the strabismus and the types. The proposed system consists of early stages for the detection of the strabismus: (1) pre-processing as the early stage to get better visualization by removing the unwanted noise and (2) the feature extraction of the iris position to get the information on types of strabismus. The eyes image from the Columbia Gaze Dataset (CAVE), Kaggle: Eye disease datasets and Siblings Database (SiblingsDB) will be used as the input image for the system. Hence, the proposed method in the early stages gives out the value of Mean Square Error (MSE) and Peak Signal-to-Noise Ratio (PSNR) of 0.0003 and 84.35% respectively for CAVE dataset slightly higher than Eye disease dataset and SiblingsDB. By utilizing the image processing approach, this system will be able to assists the ophthalmology and health care practitioners as strabismus screening tools.