![]() Protection of digital assets is of priority in research. As a result of this, protection mechanism required for the These digital assets are subjected to various types The availability of bandwidth for internet access is sufficient enough toĬommunicate digital assets. Keywords: histogram texture parameters, texture analysis, characterization, classification, brain tissues, stroke, computed tomography The characterizationĪnd classification of brain tissue using histogram parameters were satisfactory and may be suitable for automated diagnosis of stroke. ![]() With ANN and k-NN, the weighted sensitivity and specificity were above 0.9 while the false positive and false negative rates were negligible. Three parameters namely mean, 90 and 99 percentiles discriminated between normal brain tissue, ischaemic and haemorrhagic stroke lesions. Haemorrhagic lesions using the radiologists’ categorization as the gold standard, and further analysed using the ROC curve. The artificial neural network (ANN) and k-nearest neighbour (k-NN) algorithms were used to classify the ROIs into normal tissue, ischaemic and Raw data analysis identified parameters that discriminated between normal brain tissue, ischaemic and haemorrhagic stroke lesions. Histogram texture parameters were calculated for them. Four regions of interest (ROIs) in each CT slice with lesion were selected for analysis two each represented the lesion and normal tissue. In the case study, two radiologists independently inspected non-contrast CT images of 164 stroke to identify and categorize brain tissue into normal, ischaemic and haemorrhagic strokes. It explored texture analysis in medical imaging. This chapter describes histogram-based texture characterization and classification of brain tissue in CT images of stroke patients using a case study. This paper reviews the different current research works on prototype instruments and a comparison of this new alternative instrument with available commercial ones. The aim of the present contribution is to distinguish soiling from degradations (abrasion or corrosion of the reflective layer). The analysis of the images will quantify the soiling rate in order to optimize the frequency of cleaning water operations. This equipment allows addressing variable wavelength, incidence and acceptance angles, to compare specular and hemispherical reflectance from other devices. CEA has developed a new kind of laboratory sensor to measure separately the loss of reflectance due to the degradation and soiling, thanks to a CCD camera and photodiodes. Several commercial instruments already exist to measure optical reflectance, but they are dedicated to a single wavelength range or angle, punctual measurements or to laboratory analyses. ![]() In order to provide an adequate cleaning strategy, operators need to determine soiling-induced performance loss. In both cases, small degradations or dust deposition cause an optical reflectance loss. It is imperative to dissociate soiling that requires cleaning from irreversible degradations which affect the plant performance. ![]() The goal of this document is introducing these mathematical descriptions in a way easily to understand.ĭuring the life time of Concentrated Solar Power (CSP) plants, optical performance of solar mirrors is affected by soiling phenomena and surface degradation. However, these objects must be described mathematically when they are to be detected automatically with a computer. Scientists, engineers and medical doctors who intend to analyze images usually know how their images were generated and how the objects of interest look like. ![]() This document explains how digital images can be represented mathematically and basic methods for finding objects and describing regions. There are some basic methods to distinguish between objects and background and to describe regions in digital images. When processing an image with a computer, it must be digitized or created in a digital format. Images are generated by optical cameras, ultrasound, x-ray machines and other imaging devices. detection of surface defects in industrial quality control, detection of anatomical landmarks in surgery, counting cells in bio- technology and classification of regions in remote sensing. There are various applications of image processing, e. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |