Two unsupervised classifiers for optimum multithreshold are presented; fast Otsu and k-means. The unparametric methods produce an efficient procedure to separate the regions (classes) by select optimum levels, either on the gray levels of image histogram (as Otsu classifier), or on the gray levels of image intensities(as k-mean classifier), which are represent threshold values of the classes. In order to compare between the experimental results of these classifiers, the computation time is recorded and the needed iterations for k-means classifier to converge with optimum classes centers. The variation in the recorded computation time for k-means classifier is discussed.
Background: e cerebellum is divided into two hemispheres and contains a narrow midline zone called thevermis. A set of large folds are conventionally used to divide the overall structure into ten smaller "lobules". evermis receives fibres from the trunk and proximal portions of limbs, But the question is that does the cerebellum have the same measurementvalues in males and females of the same age?Material and method: e present study used 80 sectional brain MRI images (40: males, 40: females); 35-50 years old as indices of size for thevermian structures of the Cerebellum. is middle age group was taken because as known generally it could be neither an age of growth as inthe young nor of atrophy as in old individuals. e aim rega
... Show MoreInformation is an essential and valuable object in all systems. The more information you have about your issue, the better you can conform to the world around you. Moreover, information recognizes companies and provides influence that helps one company be more effective than another. So, protecting this information using better security controls and providing a high level of access to authorized parties becomes an urgent need. As a result, many algorithms and encryption techniques have been developed to provide a high level of protection for system information. Therefore, this paper presents an enhancement to the Blowfish algorithm as one of the cryptography techniques. Then it proposes an enhancement for increasing efficiency
... Show MoreThe aim of this paper, is to discuss several high performance training algorithms fall into two main categories. The first category uses heuristic techniques, which were developed from an analysis of the performance of the standard gradient descent algorithm. The second category of fast algorithms uses standard numerical optimization techniques such as: quasi-Newton . Other aim is to solve the drawbacks related with these training algorithms and propose an efficient training algorithm for FFNN
In many video and image processing applications, the frames are partitioned into blocks, which are extracted and processed sequentially. In this paper, we propose a fast algorithm for calculation of features of overlapping image blocks. We assume the features are projections of the block on separable 2D basis functions (usually orthogonal polynomials) where we benefit from the symmetry with respect to spatial variables. The main idea is based on a construction of auxiliary matrices that virtually extends the original image and makes it possible to avoid a time-consuming computation in loops. These matrices can be pre-calculated, stored and used repeatedly since they are independent of the image itself. We validated experimentally th
... Show MoreIn the present work, classification of radioactive wastes based on Annual Intake (AI) values is studied. Where the characterization of radionuclides was done by hand held GeLi detector with an overall efficiency better than 42%. It was noted the most predominant contaminant are Cs-137, Co-60 and Pa-234.The radioactive waste in disposal silo has been divided into five categories according to the harmful effect of radionuclides.For the purpose of storageradioactive wastein a safe manner, it wassuggesteda new method by shielding radioactive waste in each category with concrete;where the thickness of shielding is the time required to reduce the annual dose to 10%.
The dipstick test was evaluated for sero-diagnosis of visceral leishmaniasis. We compared two types of dipstick (rKE16, rK39) tests . The sensitivity of both tests were determined using sera from fifty-two children suspected of having visceral leishmaniasis and thirty healthy children as a control group collected from Central Teaching Hospital of Pediatric in Baghdad. Fifty (96.15%) cases were confirmed to have infection by rKE16 dipstick test while, fourty-six (88.46%) cases were positive by rK39 dipstick test. Non of the sample taken from healthy control showed reactivity in any of these tests. The study indicated that rKE16 test had better sensitivity than rK39 in the diagnosis of VL(100%) ,(92 %) respectively.
The 2D imaging survey was conducted across an unknown K- 3 cavity that is located in Haditha area-Western Iraq.2D measurements are collected along two intercrossing traverses above the cavity with 105m length of each one. Dipole-dipole array is performed with n-factor of 6 and a-spacing equals to 5m. The inverse models of 2D imaging technique showed clearly that the resistivity contrast between the anomalous part of cavity and background resistivity of rocks is about 800:100 Ωm .In addition, the invers models showed that the depth from ground surface to the upper roof of cavity approximately equals to 11m near the cavity operator. So, the K-3 cavity is well defined from 2D imaging with Dipole –dipole array in comparison with the actua
... Show More