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.

Robust Automatic Segmentation of Inflamed Appendix from Ultrasonography with Double-Layered Outlier Rejection Fuzzy C-Means Clustering

“…To identify the target object from low contrasted ultrasonography, pixel clustering method is a viable alternative and has been proven to be effective in engineering and medical domains [18][19][20][21][22]. In this pixel-based approach, the automatic segmentation process is usually divided into two phases-brightness enhancement for noise reduction and quantization-based object formation.…”

Intelligent Automatic Segmentation of Wrist Ganglion Cysts Using DBSCAN and Fuzzy C-Means

“…For n data vectors and c fuzzy clusters (c < n), FCM classifies the image into clusters having similar pixels in the feature space with iteratively minimizing the cost function dependent on the distance of the pixels to the cluster centers in the feature domain. With such flexibility, FCM has been successful in segmentation problems in many medical and engineering domains [ 17 , 18 , 19 , 20 , 21 , 22 , 23 ].…”

Efficient Fuzzy Image Stretching for Automatic Ganglion Cyst Extraction Using Fuzzy C-Means Quantization

“…Thus, FCM classifies the image into clusters with similar pixels in the feature space, iteratively minimizing the cost function defined by the distance between the pixel and the candidate cluster centers in the feature domain. With such flexibility, FCM has been successful in solving segmentation problems in many medical and engineering domains [16][17][18][19][20][21][22]. However, it still suffers from object disconnection problems during learning, and our retrospective analysis of it [14] concluded that we need a better image-enhancement policy to overcome the difficulty of a cyst forming during the FCM process.…”