Yazar "Ceylan M." seçeneğine göre listele
Listeleniyor 1 - 7 / 7
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Determination of benign and malign lesions by fusion of the different phases of liver MR [Karaci?er MR Görüntülerindeki Farkli Fazlarin Füzyonu ile İyi Huylu ve Kötü Huylu Lezyonlarin Belirlenmesi](Institute of Electrical and Electronics Engineers Inc., 2017) Ervural S.; Ceylan M.In this study, different phases of T1-weighted, dynamic contrast-enhanced liver magnetic resonance (MR) images were combined with wavelet-based image fusion to support decisions of radiologists. Used images has labelled as 6 different focal lesion types which focal nodular hyperplasia (FNH), hemangioma, cyst, colangiocellular carcinoma (CCC), hepatocellular carcinoma (HCC) and liver metastases. In application used images are taken by 4 different phases called pre-contrasted, arterial, portal venous, and delay venous from 30 patient. Images registered with efficient subpixel registration by cross correlation method. Discrete wavelet transform(DWT) based image fusion algorithm used and maximum selection method applied as fusion rule. As result 180 fused images obtained The performances of fusion results compared with structural similarity index (SSIM), peak to noise ratio (PSNR) and fusion factor (FF) metrics. In the fusion of portal venous phase and delay venous phase images, 98.7% SSIM and 74.95 dB PSNR values were obtained, respectively. FF value in the fusion of pre-contrast phase & arterial phase images measured as 7.258. In comparison of lesion types were represented with 98.5% SSIM. © 2017 IEEE.Öğe Determining the number of tetrominoe orders for denoising applications performed by Tetrolet transform [Tetrolet dönüşümüyle gerçekleş tirilen gürültü giderme uygulamalari için tetromin dizilimi sayisinin belirlenmesi](IEEE Computer Society, 2014) Ceylan M.; Ozturk A.E.While Tetrolet transform (TT) which is one of the multi-resolution analysis improved recently is applied to images, 5 different shape called tetrominoes is gathered for 4×4 pixel blocks and TT is performed by arranging pixels according to this order. Tetrominoes can be chosen with 117 different combinations. In this study, firstly benchmark images (Lena, Barbara, Boat, Mandrill, Cameraman) and liver MR (magnetic resonance) images are denoised by utilizing TT with 1 to 117 different tetrominoe combinations respectively and optimal number of orders is determined for different noise rates by comparing obtained PSNR (peak signal to noise ratio) results. After that, images are denoised by using just optimal number of tetrominoe orders and all 117 combinations seperately. The operation times are compared. It is clearly seen that using all possible combinations for denoising causes redundant processes and an optimal number of tetrminoe orders can be specified for different image sets according to noise ratio. Decreasing number of combinations shortened the operation time seriously. © 2014 IEEE.Öğe A digital image processing based bio-identification application from planum nasale of Kangal dogs [Kangal köpeklerinin planum nasale'sinden sayisal görü ntü i?sleme tabanli bir biyo-kimlikleme uygulamasi](2011) Bilgin E.; Ceylan M.; Yalçin H.In this study, digital image processing based bio-identification application is realized to analyze of nose-print for Kangal dogs. First of all, the image is filtered and the masks for each image is get by using threshold value of the image. And then, when the mask is applied on the image,the algorithms of creating triangle and finding number of circle like shapes by finding angle values of three biggest holes in nose-print with location of holes were applied on the remained data. As a conclusion, statistics results are very different from each other. It is because of the face that the images are unique within themselves. In this study, the nose-prints of ten Kangal dogs are taken in the control of a vet. © 2011 IEEE.Öğe Increasing lesion specificity with fusion of manually and automatically segmented liver MR images [Manuel ve otomatik bölütlenmiş karaci?er MR görüntülerinin füzyonu ile lezyon belirginli?inin artirilmasi](Institute of Electrical and Electronics Engineers Inc., 2018) Ervural S.; Ceylan M.In this study, it is aimed to analyze the magnetic resonance (MR) images used in the diagnosis of liver focal lesions using image fusion methods and to help diagnosis by adding automatic segmentation results to the manual segmentation process preferred by experts. For this aim fusions of liver MR images, segmented by a fuzzy method and segmented manually. 120 T1-weighted dynamic contrast-enhanced liver MR images of pre-contrast phase, arterial phase, portal vein phase and late venous phase, taken from 30 different patients, were used. Each phase image is also fused with images segmented by the fuzzy c-means algorithm in the same phase, so that the lesion surfaces and contours are displayed on the segmented image manually. Thus, the significance of the lesion was increased before the information in the MR image in which the liver function information was displayed was lost. The resulting new image contains more useful information for automatic decision systems. The results obtained were evaluated using structural similarity index, peak signal-to-noise ratio and fusion factor quality metrics. © 2018 IEEE.Öğe A new approach for open-close eye states detection: Complex wavelet transform and complex-valued ANN [Açik-kapali göz durumlarinin belirlenmesi i?çin yeni bir yaklaşim: Karmaşik dalgacik dönüşü mü ve karmaşik de?erli YSA](2010) Çelebi M.; Ceylan M.A novel method for open-close eye states detection, based on complex wavelet transform (CWT) and complex-valued artificial neural network (CVANN) is proposed in this study. Firstly, color information of images is used. Red images for eye are chosen as intensity image of color image. After getting the red image of seperately right and left eye, the color information is used to feature extraction with CWT. Features of eyes are extracted using CWT with 4th level and image size is reduced. After then, four statistical features (maximum value, minimum value, mean value and standard deviation) are obtained from extracted features. These new statistical features are presented to CVANN as inputs. Image set including ten person images with open and close eye states is used in this study, CVANN detected eye states with % 6.7 numerical test error. Classification results shown that, one of ten images is misclassified for two states. ©2010 IEEE.Öğe A new channel equalization method for digital communication systems using complex valued neural networks [Kompleks De?erli Yapay Sinir A?larini Kullanarak Sayisal Haberleşme Sistemleri İçin Yeni Bir Kanal Dengeleme Metodu](2004) Ceylan M.; Arican S.; Özbay Y.Disturbed effects, interference, noise etc., occured in digital communication channel cause corrupts at transmitted signals. For regulate corrupted signals, equalization techniques use in entry of receiver. Aim of this study is to design a new equalization structure for digital communication systems by using complex valued neural network. © 2004 IEEE.Öğe Thermal image analysis for neonatal intensive care units (First evaluation results) [Yenido?an yo?un bakim ünitelerinde termal görüntüleme analizi (ilk de?erlendirme sonuçlari)](Institute of Electrical and Electronics Engineers Inc., 2018) Savasci D.; Ceylan M.Measuring the body temperature of a neonatal has a vital importance for daily baby care. Especially for premature babies, measuring the neonatal baby's body temperature is considerably significant. The rapid development of the medical thermography technologies provides the measurement of body temperature accurately without any contact. Recently, the use of non-invasive, un-ionized, fast and reliable method of infrared thermal imaging has got importance in neonatal intensive care unit. The importance of monitoring 'thermal asymmetry ' or 'time-dependent thermal differences' in the evaluation of disease pre-diagnosis or post-diagnosis follow-up is vital. The purpose of this study is to create an analytical system based on infrared thermal imaging, non-contact, non-invasive, non-ionized and with a lower error rate than existing systems. © 2018 IEEE.
