Mühendislik-Mimarlık Fakültesi Bilgisayar Mühendisliği Bölümü Bildiri Metinleri Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe Multi-feature extraction and multi-classification techniques with computer aided breast cancer detection(Batman Üniversitesi, 2018) Çalışkan, Abidin; Acar, Emrullah; Budak, CaferÖğe Comparison of multiple biometric identification with a single biometric identification system(Batman Üniversitesi, 2018) Çalışkan, Abidin; Acar, Emrullah; Budak, CaferÖğe Bulut bilişimde kripto para madenciliği(Batman Üniversitesi, 2018) Çalışkan, Abidin; Çelebi, Selahattin Barış; Karaman, Ömer Ali; Emiroğlu, Bülent GürselÖğe Classification of soil surface wetness by histogram of oriented gradients and extreme learning machine models(Batman Üniversitesi, 2018) Çalışkan, Abidin; Acar, Emrullah; Budak, CaferÖğe Detection and recognition of Turkish license plate characters with image segmentation based correlation method(Batman Üniversitesi, 2018) Çalışkan, Abidin; Acar, Emrullah; Orun, ÖzgeÖğe Parmak izi tanıma tekniklerine genel bir bakış(Batman Üniversitesi, 2018) Çalışkan, Abidin; Budak, Cafer; Acar, EmrullahÖğe Comparison of methods used to eliminate harmonics in power systems(Batman Üniversitesi, 2018) Çalışkan, Abidin; Karaman, Ömer Ali; Çelebi, Selahattin Barış; Cebeci, MehmetÖğe 3D imaging and visualization studies(Batman Üniversitesi, 2018) Çalışkan, Abidin; Karaman, Ömer Ali; Çelebi, Selahattin BarışÖğe 2B ve 3B medikal görüntülerde gürültü temizleme tekniklerinin karşılaştırmalı incelenmesi(Batman Üniversitesi, 2018) Çalışkan, Abidin; Çevik, Ulus; Acar, EmrullahÖğe An overview of denoising methods in medical images(Bandırma Onyedi Eylül Üniversitesi, 2021) Çalışkan, Abidin; Ateş, Feyzi FeratGünümüzde, dijital görüntüler tıp bilimi, mühendislik gibi çeşitli alanlarda kullanılmaktadır. Medikal alanda dijital görüntülerin analizi hayati önem taşımaktadır. Medikal görüntüler birçok hastalığı tanımlamak için kullanılmaktadır. Bu görüntüleri oluşturan kaynaklar nedeniyle zaman zaman görüntülerde gürültüler oluşabilmektedir. Özellikle medikal görüntülerde bu gürültüleri temizlemek son derece önemlidir, çünkü bu gürültüler görüntülerin kalitesini düşürerek hastalığın tanınmasını engelleyebilmektedir. Bu çalışmada, medikal görüntülerde gürültü temizleme yöntemleri araştırılmış ve gürültü temizleme yöntemlerine ilişkin kapsamlı bir inceleme yapılmış olup; tıbbi görüntülerin radyografik, ultrason (US), manyetik rezonans (MR) ve bilgisayarlı tomografi (BT) görüntüsü olarak sınıflandırılması anlatılmaktadır. Medikal görüntülerin gürültülerden arındırılması ile alakalı gelişmeler son dönemlerde araştırmacıların ilgisini çekmektedir.Öğe Fingerprint recognition system based on law’s texture energy measures with extreme learning machines(INESEC, 2017) Çalışkan, Abidin; Acar, Emrullah; Budak, CaferFingerprint recognition systems are one of the most popular biometric systems used in many areas, including prisons, border controls, educational institutions and forensic medicine. This paper presents a new approach based on the texture features for fingerprint recognition system. The dataset which employed in this study is obtained from the Hong Kong Polytechnic University High-ResolutionFingerprint database. The proposed system was implemented in two basic stages. Firstly, the texture feature vectors were extracted from the images by using Law’s Texture Energy Measures (TEM) and totally 9 parameters were extracted for each image as a feature vector. Then, the obtained feature vectors were classified by using Extreme Learning Machines (ELM) model. Finally, the average performance of the proposed system was computed according to different tuning parameters and the highest accuracy rate was observed as 83.92 % among the all system architectures.Öğe Palmprint recognition system based on gabor wavelet transform with K-NN classifier model(INESEC, 2017) Çalışkan, Abidin; Ergen, Burhan; Acar, EmrullahPalmprint recognition system is regarded as reliable and accurate biometric identification system. The biometric approach palm recognition system has attracted the attention of researchers in recent times because of the presenting a new biometric feature compared to other models. In this work, gabor wavelet transform (GWT) based palmprint recognition system has been developed. Firstly, image coordinate system is determined in order to facilitate image alignment for feature extraction. Then, region of interest is cropped from the palmprint images. With the developed system, features are extracted from the region of interest and they are given to k-nearest neighbors (k-NN) classifier as input parameters. Finally, the highest success rate for GWT based systematic sampling was computed as 86.90% according to the non-request data selection and it was observed that the proposed recognition system provide successful results in classification of palmprint images. Moreover, a good identification of the feature vector is the main factor that affects performance. Thus, the performance can also be improved by finding more suitable feature vectors.Öğe Fingerprint recognition system based on gray level co-occurrence matrix(INESEC, 2017) Çalışkan, AbidinThe biometric system provides an automatic identification of any person, depending on characteristic and feature/attribution of person. Fingerprint is, today, one of the biometric systems that have a wide range of use in many investigation areas. Fingerprint, especially used for authentication, is more reliable comparing to the other traditional methods which are used for access. In this study, a gray level co-occurrence matrix (GLCM) based fingerprint recognition system which provides successful results in tissue type imagining recognition has been implemented. The purpose of this study is to show the effectiveness of the GLCM in fingerprint recognition. By using GLCM which is a feature extracting method, fingerprint images are classified by multilayer perceptron (MLP) artificial neural network classification technique. Statistical methods were used to extraction the feature by obtaining the GLCM matrix for the gray level images. In the first step of system analysis, the system is trained by using GLCM attribute parameters and performance information is measured for different network topologies of the MLP classifier. After the classification stage, when the results are compared with the success rates of previously made fingerprint recognition systems, the success rate of 88.25% is considered as acceptable. As a result, it is considered that the results are reasonable when results are compared with other studies in the literature. Experimental results have also shown that the proposed method can improve the accuracy of existing methods.Öğe Biometric systems and hand based biometric recognition characteristics(Fırat Üniversitesi, 2011) Çalışkan, Abidin; Ergen, BurhanA biometric system provides automatic identification of an individual based on a unique feature or characteristic possessed by the individual. Palmprint recognition is regarded as the reliable and accurate biometric identification system available. In this work, a analysis of biometric technologies has been realized and a palmprint recognition system has been researched. Viewed in the palm of biometric approaches, compared to other models because it is a new handheld biometric feature recognition systems has recently attracted the attention of researchers.Öğe 3D medical image processing by using filtering methods(Dicle University, 2016) Çalışkan, Abidin; Çevik, UlusIn this paper, data having medical file extensions were passed through various image processing stages, and boundary determination operations were performed. We aimed to obtain three-dimensional (3D) images after transferring the two-dimensional (2D) CT slices, obtained from the existing medical imaging devices, and to provide a mesh structure between them. At the phase of obtaining 3D images, image processing techniques such as surface and volume imaging techniques were used, and the complexity and effectiveness of the imaging algorithms were investigated, and image improving algorithms were used, as well. The noise filtering techniques for the images have been reviewed and 3D surface model has been obtained using volume rendering techniques.Öğe Polen görüntülerinin yapısal özellikler ile sınıflandırılması(IEEE, 2013) Çalışkan, Abidin; Kaya, Yılmaz; Erez, Mehmet EmreBu çalışmada, bitkilere ait polen tanelerini bir uzman kişinin yardımına ihtiyaç duymadan farklı taksonomik kategorilere ayıran bir bilgisayarla görü sistemi geliştirilmiştir. Polen taneleri üç boyutlu karmaşık bir yapıya sahip olmalarına rağmen birbirlerinden ayırt edilebilir özellikler taşırlar. Çalışmada polen görüntülerin sınıflandırılması için yerel kenar örüntüler (YKÖ) kullanılmıştır. Önerilen sistem 3 aşamadan oluşmaktadır. Birinci aşamada polen görüntülerine Sobel kenar algoritması uygulanarak yapısal özelliklerin belirgin olduğu yeni görüntüler elde edilmiştir. İkinci aşamada yeni görüntülerden YKÖ elde edilmiş, son aşamada ise elde edilen özellikler ile makine öğrenmesi yöntemleri ile sınıflandırma işlemi gerçekleştirilmiştir. YKÖ ile %98,48 gibi önemli bir sınıflandırma başarısı elde edilmiştir.Öğe Bazi euphorbia (Euphorbiaceae) tohum türlerinin siniflandirilmasi için yerel ikili örüntüler tabanli bir bilgisayar görü sistemi(IEEE, 2013) Çalışkan, Abidin; Kaya, Yılmaz; Karabacak, OsmanBu çalışmada tohum görüntülerin sınıflandırılması için bir bilgisayar görü sistemi önerilmiştir. Sayısal tohum görüntülerinden elde edilen yerel ikili tekdüze örüntüler kullanılarak tohum sınıflandırılması gerçekleştirilmiştir. Çalışmada 240 (120 eğitim ve 120 test) tohum görüntüsü kullanıldı. Öncelikle eğitim setindeki her tohum türü için ortalama tekdüze histogramlar (tohum türü sınıfları) elde edildi. Daha sonra test setindeki her tohum için LBP histogramı üretilip ve tohum türü sınıflarına ait histogramlar ile karşılaştırılarak en yakın komşuluk yöntemi ile sınıflandırma işlemi gerçekleştirildi. Tohum örnekleri arasındaki uzaklıkların hesaplanmasında ise Öklit uzaklığı, hata kareler toplamı, histogram kesişimi ölçütü ve Chi-kare istatistiği kullanıldı. Önerilen yöntem ile tohum görüntülerin %95,83 doğru teşhis edilmiştir. Sonuç olarak tohumların yüzey şekilleri taksonomik ilişkilerin belirlenmesi açısından önemli desen bilgileri barındırdığından bilgisayar görü sistemleri tohum türünün tanımlanmasında önemli avantajlar sağlayacağı öngörülmektedir.Öğe Electrical parameters of safranine T N silicon contacts(İstanbul University, 2015) Güllü, Ömer; Arsel, İsmail; Özkan, Samet; Özaydın, Cihat; Pakma, Osman; Turut, AbdülmecitIn this work, it has been investigated current-voltage (I-V) andcapacitance-voltage-frequency (C-V-f) characteristics of the Al/SafranineT(ST)/n-Si structure. The values of the ideality factor, series resistance and barrier height calculated by using different methods were compared. It was seen that there was an agreement with each other. Also, it was seen that the barrier height value for our device was higher than one value of 0.50 eV of conventional Al/n-Si Schottky contact. The change in the barrier height value of the device was ascribed to ST thin layer modifying the effective barrier height by influencing the space charge region of the Si inorganic semiconductor. The downward concave curvature of the forward bias current-voltage characteristics at sufficiently large voltages have been attributed to the effect of series resistance. Thus, the concavity of the forward bias current-voltage characteristics increases with increasing series resistance value. It has been seen that the values of capacitance are almost independent to a certain value of frequency, after this value, the capacitance decreases with increasing frequency. The higher values of capacitance at low frequencies have been attributed to the excess capacitance resulting from the interface states in equilibrium with the n-Silicon that could follow the alternating current signal.Öğe I V and C V F characteristics of aniline green N type silicon diode(İstanbul University, 2015) Özkan, Samet; Güllü, Ömer; Arsel, İsmail; Özaydın, Cihat; Pakma, Osman; Turut, AbdülmecitWe have studied the I-V, C-V and C-f characteristics of the Aniline Green (AG)/n-type Si structure. In organic/inorganic semiconductor contact applications, in order to keep the technological difficulties and unknowns to a minimum, silicon is generally chosen as the substrate semiconducting material. In this structure, deposition of organic materials on the inorganic semiconductor can generate large number of interface states at the semiconductor surface that strongly influence the electrical properties of the AG/n-Si structure. The values of the ideality factor, series resistance and barrier height obtained from two methods were compared, and it was seen that there was an agreement with each other. The downward concave curvature of the forward bias current-voltage characteristics at sufficiently large voltages is caused by the presence of the effect of series resistance. Thus, the concavity of the forward bias current-voltage characteristics increases with the increasing series resistance value. The high resistance values have given the high ideality factors. Also, the higher values of capacitance at low frequencies were attributed to the excess capacitance resulting from the interface states in equilibrium with the nSi that can follow the ac signal.Öğe Structural and optical investigations on ZrO2 thin films prepared by wet chemical synthesis method(İstanbul University, 2015) Özdemir, Cengiz; Pakma, Osman; Kari̇per, İshak Afşin; Özaydın, Cihat; Güllü, ÖmerThe aim of the study is to develop a more economic and easier method which has lower temperature in obtaining ZrO2 thin films contrary to the literature. In this study, we produced thin ZrO2 films on amorphous glass substrates through the wet chemical method by using different chemicals with the same starting reactive. X-ray diffraction (XRD), scanning electron microscopy (SEM) and ultraviolet-visible (UV-VIS) spectroscopy measurements of the produced films were conducted and the results were compared. The best method has been identified at the end of the analysis and it has been observed that the features of the films produced with this method have given better results than both the films produced by using different reagents and the films produced in literature.
