Computer Engineering / Bilgisayar Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/10
Browse
5 results
Search Results
Conference Object Citation - Scopus: 1Doǧal İmgelerde Çizge Tabanlı Gösterimle Karakter Bölütlenmesi(IEEE, 2018) Koksal, Ali; Isik, ZerrinComputer vision approaches like shape based descriptors use silhouettes of objects in images. In this paper, a method to extract silhouettes of objects by segmenting images is proposed in order to describe them, especially characters that are obtained from natural images by using shape based descriptors. This method is binary segmentation approach that has a graph-based representation. Dominant intensity values of segments of an image and cut off intensity value to separate those segments are computed dynamically. Thus, characters that have similar dominant intensity value to the background can be segmented as well. Moreover, the performance of the proposed graph based method is compared with the performance of the global thresholding and it is observed that the success of the proposed method is better than the global thresholding.Conference Object Citation - Scopus: 3Derin Öǧrenme ile Zemin Dokusu Sınıflandırma(IEEE, 2018) Ozuysal, MustafaIn this study, we investigate the use of transfer learning on various deep neural network architectures pretained on the ImageNet data set for ground texture classification purposes. We introduce a new ground texture data set collected from seven different areas. We retrain deep neural network's last layer or when possible the full set of layers on this data set. The results show that it is possible to discriminate the ground textures even when very small images are used.Conference Object Citation - WoS: 2Citation - Scopus: 2Türkçe Manzara Metni Veri Kümesi(IEEE, 2017) Erdogmus, NesliScene text localization and recognition keeps attracting an increasing interest from researchers due to its valuable advantage in extracting content from real world images and in image retrieval via text search. Nevertheless, due to the fact that the majority of the image datasets that are commonly used in this field is comprised of text in English, the related studies have mostly been limited to a single language. On that account, in order to apply the technologies developed for scene text detection and recognition to Turkish scene text, analyze their performances and to develop Turkish language specific algorithms, a Turkish scene text database is collected for the first time in the literature. In this paper, the contents of this database, shortly called STRIT (Scene Text Recognition In Turkish), are detailed. Additionally, two baseline methods are tested to detect and recognize scene text in Turkish and the preliminary results are presented.Conference Object Parça Tabanlı Eǧitimin Evrişimli Yapay Sinir Aǧları ile Nesne Konumlandırma Üzerindeki Etkisi(IEEE, 2017) Orhan, Semih; Bastanlar, YalinIn recent years, Convolutional Neural Networks (CNNs) have shown great performance not only in image classification and image recognition tasks but also several tasks of computer vision. A lot of models which have different number of layers and depths, have been proposed. In this work, locations of leopards are tried to be identified by deep neural networks. To accomplish this task, two different methods are applied. First of them is training neural network using with entire images, second of them is training neural networks using with image patches which are cropped from full size of images. Patch training model has shown better performance than full size of image trained model.Conference Object Düşük Sükroz Derişimlerinin Görünür Bölge Spektroskopisi ve Yapay Sinir Aǧları ile Kestirimi(IEEE, 2017) Mezgil, Bahadir; Erdogan, Duygu; Alduran, Yesim; Yildiz, Umit Hakan; Yildiz, Ahu Arslan; Bastanlar, YahnLow sucrose concentrations in solutions is estimated by means of localized surface plasmon resonance of immobilized gold nanoparticles. The ultraviolet-visible spectra (UV-Vis) of samples with different sucrose concentrations were prepared and used to train artificial neural networks. In our study, MATLAB Neural Networks Toolbox was used and effect of different input sizes and network structures on the estimation accuracy is investigated. It is observed that using complete spectrum instead of peak point results in higher accuracy.