Intelligent Automatic Extraction of Canine Cataract Object with Dynamic Controlled Fuzzy C-Means based Quantization

Abstract

Canine cataract is developed with aging and can cause the blindness or surgical treatment if not treated timely. Since the pet owner do not have professional knowledge nor professional equipment, there is a growing need of providing pre-diagnosis software that can extract cataract-suspicious regions from simple photographs taken by cellular phones for the sake of preventive public health. In this paper, we propose a software that is highly successful for that purpose. The proposed software uses dynamic control of FCM clusters in quantification and trapezoid membership function in fuzzy stretching in order to enhance the intensity contrast from such rough photograph input. Through experiment, the proposed system demonstrates sufficiently enough accuracy in extraction (successful in 42 out of 45 cases) with better quality comparing with previous attempt.