Automated Exudates Detection in Retinal Fundus Image Using Morphological Operator and Entropy Maximization Thresholding

Blindness which is considered as degrading disabling disease is the final stage that occurs when a certain threshold of visual acuity is overlapped. It happens with vision deficiencies that are pathologic states due to many ocular diseases. Among them, diabetic retinopathy is nowadays a chronic disease that attacks most of diabetic patients. Early detection through automatic screening programs reduces considerably expansion of the disease. Exudates are one of the earliest signs. This paper presents an automated method for exudates detection in digital retinal fundus image. The first step consists of image enhancement. It focuses on histogram expansion and median filter. The difference between filtered image and his inverse reduces noise and removes background while preserving features and patterns related to the exudates. The second step refers to blood vessel removal by using morphological operators. In the last step, we compute the result image with an algorithm based on Entropy Maximization Thresholding to obtain two segmented regions (optical disk and exudates) which were highlighted in the second step. Finally, according to size criteria, we eliminate the other regions obtain the regions of interest related to exudates. Evaluations were done with retinal fundus image DIARETDB1 database. DIARETDB1 gathers high-quality medical images which have been verified by experts. It consists of around 89 colour fundus images of which 84 contain at least mild non-proliferative signs of the diabetic retinopathy. This tool provides a unified framework for benchmarking the methods, but also points out clear deficiencies in the current practice in the method development. Comparing to other recent methods available in literature, we found that the proposed algorithm accomplished better result in terms of sensibility (94.27%) and specificity (97.63%).

Mathematical Modeling of Shear Stress and Direct Shear Test for Compressible Soil: Case of Soil Bordering the Wouri River

This paper focuses on the development of the mathematical model of shear stress by direct shear test for compressible soil of the littoral region, which will be a great tool in the hand of geotechnical engineers. The most common use of a shear test is to determine the shear strength which is the maximum shear stress that a material can withstand before the failure occurs. This parameter is useful in many engineering designs such as foundations, roads and retaining walls. We carried out an experimental laboratory test of ten samples of undisturbed soil taken at different points of the border of Wouri river of Cameroon. The samples were collected at different depths and a direct shear test was conducted. The investigations have been performed under constant vertical stresses and constant sample volume with the aim to determine the frictional angle and the cohesion of the compressible soil which are so important to establish the conditions of buildings stability. Special care was taken to derive loading conditions actually existing in the ground and to duplicate them in the laboratory. Given that the buildings constructed in this area are subjected to settlement, landslide, and punch break or shear failure, the cohesion and the frictional angle are determined through the rupture line after assessed the mean values of the shear stress for the considered ten samples. The bearing capacity of the soil, which is the fundamental soil parameter, was calculated. From the laboratory experimental results, the least squared method was used to derive an approximated mathematical model of the shearing stress. Many optimizations methods were then considered to reach the best adjustment.

Polynomial robust observer implementation based passive synchronization of nonlinear fractional-order systems with structural disturbances

A robust polynomial observer is designed based on passive synchronization of a given class of fractional-order Colpitts(FOC)systems with mismatched uncertainties and disturbances.The primary objective of the proposed observer is to minimize the effects of unknown bounded disturbances on the estimation of errors.A more practicable output-feedback passive controller is proposed using an adaptive polynomial state observer.The distributed approach of a continuous frequency of the FOC is considered to analyze the stability of the observer.Then we derive some stringent conditions for the robust passive synchronization using Finsler’s lemma based on the fractional Lyapunov stability theory.It is shown that the proposed method not only guarantees the asymptotic stability of the controller but also allows the derived adaptation law to remove the uncertainties within the nonlinear plant’s dynamics.The entire system using passivity is implemented with details in PSpice to demonstrate the feasibility of the proposed control scheme.The results of this research are illustrated using computer simulations for the control problem of the fractional-order chaotic Colpitts system.The proposed approach depicts an efficient and systematic control procedure for a large class of nonlinear systems with the fractional derivative.