1 Abstract—Eyes are considered to be the most sensitive and important organ for human being. Thus, any eye disorder will affect the patient in all aspects of life. Cataract is one of those eye disorders that lead to blindness if not treated correctly and quickly. This paper demonstrates a model for automatic detection, classification, and grading of cataracts based on image processing techniques and artificial intelligence. The proposed system is developed to ease the cataract diagnosis process for both ophthalmologists and patients. The wavelet transform combined with 2D Log Gabor Wavelet transform was used as feature extraction techniques for a dataset of 120 eye images followed by a classification process that classified the image set into three classes; normal, early, and advanced stage. A comparison between the two used classifiers, the support vector machine SVM and the artificial neural network ANN were done for the same dataset of 120 eye images. It was concluded that SVM gave better results than ANN. SVM success rate result was 96.8% accuracy where ANN success rate result was 92.3% accuracy. Keywords—Cataract, classification, detection, feature extraction, grading, log-gabor, neural networks, support vector machines, wavelet. I. INTRODUCTION HE eyes consists of many complicated components such as the lens. The eye lens is like a camera lens as it focuses light onto the retina at the back of the eye so that the image can be recorded. It also controls the eye’s focus, to see things whether they are close or far away. Lenses are made of water and protein and are always transparent, but sometimes the protein clumps up behind the lens which clouds small area of the lenses with white color and causes troubles in the sight. This area may grow larger by time which leads to blindness when it covers the whole lens; this cloudy area is the cataract. When the cloudy area is relatively small, the cataract is considered to be in its early stages, but when the cloudy area is almost or fully covering the lens, the cataract is considered to be in advanced stage, moreover, the cataract can be detected in the pupil area when the eye is being examined externally. The only treatment for cataract is surgery and it is preferred to be treated at early stages to decrease the surgery risks and saves the patient from total blindness. If cataract is left untreated for Hadeer R. M. Tawfik and Amani A. Saad are with the College of Engineering and Technology, Arab Academy for Science, Technology and Maritime Transport (AASTMT), Alexandria, Egypt (e-mail: hadeertawfik91@yahoo.com, Amani.saad@aast.edu). Rania A. K. Birry is with the College of Engineering and Technology, AASTMT, Alexandria, Egypt (phone: +20100-1708732; (e-mail: rania_kadry2012@yahoo.com). long time or covers the whole eye lens which is an advanced stage of cataract, this will lead to total blindness since the removal of the cataract will be very difficult causing serious complications such as excessive bleeding, severe and lasting inflammation and Glaucoma also it impairs the view of retina which complicates the surgery for the surgeon, furthermore, One of the common reasons behind the difficulty of removing cataract at advanced stage is that it may convert to a hyper mature cataract in which the lens becomes solid, shrinks and wrinkles or becomes soft and liquid [1]-[3], leading to a complicated surgery for the surgeon with dangerous, unsuccessful results on the patient. Thus, the ophthalmologists will have to weigh the surgery risks against the regain of the patient' sight. A recommendation will be given to leave the cataract untreated in such case. Ophthalmologists advice to have the cataract surgery at an early stage. Cataracts usually affect people above 50 years old, or because of diabetes, long exposure to sun, smoking, obesity and eye injuries. Cataract is the main reason behind 51% of blindness around the world (2010) according to World Health Organization (WHO) [4]. There exist obstacles which prevent the patients from getting through eye examination and surgery, such as ignorance, war zones, poor villages that suffer the lack of clinics or the rarity of finding an ophthalmologist and long waiting lists to be treated. In this paper, a model of cataract detection, classification and grading system is proposed to help with the cataract diagnosis since the system can be used to help the ophthalmologist in diagnosing cataract patients in less time with high accuracy, also it can be used to develop an application to serve patients in needs who live in areas that lake health care centers or eye clinics. This could be done by uploading digital images of their Iris that can be photographed by digital camera and smart phones. II. REVIEW OF RELATED WORK Different Cataract detection and classification systems have been modeled and implemented by many researchers. Acharya et al. [5] used tiff natural eye images as the image set, then the histogram equalization was used for enhancing the images contrast, after that, k-means clustering algorithm extracted the images' features that were fed to Neural Network classifier, also The ANN classified the images into different eye diseases which were Cataract, Corneal haze, Iiridocycleitis, Corneal arcus and Normal with accuracy of 90%. Moreover, Acharya et al. [6] used optical RGB eyes' images, histogram equalization was used as a preprocessing step, then fuzzy k Early Recognition and Grading of Cataract Using a Combined Log Gabor/Discrete Wavelet Transform with ANN and SVM Hadeer R. M. Tawfik, Rania A. K. Birry, Amani A. Saad T World Academy of Science, Engineering and Technology International Journal of Computer and Information Engineering Vol:12, No:12, 2018 1038 International Scholarly and Scientific Research & Innovation 12(12) 2018 Digital Open Science Index, Computer and Information Engineering Vol:12, No:12, 2018 waset.org/Publication/10009852