Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed
Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741
Browse
8 results
Search Results
Publication Metadata only An hierarchical approach for human computer interaction using eyelid movements, Göz kapaǧi hareketleriyle insan bilgisayar etkileşimi için siradüzensel yaklaşim(IEEE Computer Society [email protected], 2014) Çelik, Anıl; Arica, Nafiz; Çelik, Anıl, Bahçeşehir Üniversitesi, Istanbul, Turkey; Arica, Nafiz, Bahçeçehir Üniversitesi, Istanbul, TurkeyThis work proposes a method to achieve real-time HumanComputer interaction with the movements of the eyelids in low-resolution video. Classification of left and right eye states as closed or open are performed by an hierarchical approach of tracking by detection. After the initial detection of the face area, an efficient face tracking algorithm is used to reduce the search space for detection of eye region. By seperating the eye region into two overlapping pieces, left and right eyes are detected and classified as closed or open. The proposed method is robust against mimics and multiple faces in the frame, while being unaffected by the negative effects of aliasing and resizing. Thus, people who suffer from medical conditions limiting their physical movement capabilities can interact with computers with their eyelid movements. © 2014 IEEE. © 2014 Elsevier B.V., All rights reserved.Publication Metadata only Atmospheric turbulence mitigation using feature based optical flow, Atmosferik türbülans etkilerinin öznitelik tabanli optik akiş yöntemi ile azaltilmasi(IEEE Computer Society [email protected], 2014) Çaliskan, Tufan; Arica, Nafiz; Çaliskan, Tufan, Deniz Harp Okulu, Tuzla, Turkey; Arica, Nafiz, Mühendislik Fakültesi, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn this paper, we propose a fast and effective feature based registration technique in removing the distortions caused by atmospheric turbulence. We utilize optical flow method and combine the advantages of previous approaches based on space-invariant deconvolution and lucky frame idea. After an optical flow based registration of degraded image sequence, a patch-wise multi-frame reconstruction technique is applied to fuse the registered images. Blind-deconvolution technique is implemented to deblur the fused image to obtain a single high quality image. The experiments performed on common datasets show that the proposed method produces higher quality images more efficiently than the available methods. © 2014 IEEE. © 2014 Elsevier B.V., All rights reserved.Publication Metadata only Object tracking by combining tracking-by-detection and marginal particle filter, Tespit-ile-Takip ve Marjinal Parçacik Süzgecinin Birleştirilmesiyle Nesne Takibi(Institute of Electrical and Electronics Engineers Inc., 2016) Maraş, Bahri; Arica, Nafiz; Ertüzün, Ayşin Baytan; Maraş, Bahri, Boğaziçi Üniversitesi, Bebek, Turkey; Arica, Nafiz, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Ertüzün, Ayşin Baytan, Boğaziçi Üniversitesi, Bebek, TurkeyIn this paper, we propose a new algorithm based on tracking-by-detection approach for tracking of the objects having non-linear dynamic motion. For this purpose, the tracking-by-detection method depending on the Gauss kernel using the circulant matrix theory and the Fourier transform is employed together with the marginal particle filter method. Marginal particle filter uses the scores derived from the Gauss kernel at the measurement update phase of the filter to weight the particles propagated around the target that has been tracked. While updating the state variables by marginal particle filter, the object coordinates, the correction values belonging to these coordinates and the dimensions of the image window surrounding the object is estimated. The proposed method is tested on the video sequences which include the object having a high non-linear motion, and it was observed that marginal particle filter enhanced the performance of the track-by-detection method in an important scale. © 2017 Elsevier B.V., All rights reserved.Publication Metadata only Risk classification for breast cancer diagnosis using HER2 testing, Meme Kanseri Tanisi için HER2 Testine Dayali Risk Siniflandirmasi(Institute of Electrical and Electronics Engineers Inc., 2016) Aktan, Pinar Ece; Hatipoglu, Gokhan; Arica, Nafiz; Aktan, Pinar Ece, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Hatipoglu, Gokhan, Virasoft, Istanbul, Turkey; Arica, Nafiz, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, TurkeyTrastuzumab is one of the effective treatment for breast cancer. It is an antibody against the protein product of the human epidermal growth factor receptor type 2 (HER2) gene. In HER-2 testing protein levels are determined by IHC staining. For a proper treatment IHC stains are evaluated together with ISH stains. The widespread approach done by the experts is to determine membranes manually, yet it leads subjective interpretation by pathologist and it increases their workload. In this paper, we propose a new method for HER-2 testing based on image analysis algorithms on membrane regions. After, maximally stable extremal regions algorithm is employed for detecting the membrane regions, these areas of those regions are analyzed quantitatively for IHC classification. In the next step, complete/incomplete membrane regions are determined for IHC 2+ classification. The experiments conducted on the IHC stains taken from the clinic patients. Analysis resulted with the successful classification rates. © 2017 Elsevier B.V., All rights reserved.Publication Metadata only Face frontalization enhanced by deep learning, Derin Öǧrenme Destekli Yüz Önleştirme(Institute of Electrical and Electronics Engineers Inc., 2017) Çelik, Anıl; Arica, Nafiz; Çelik, Anıl, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Arica, Nafiz, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn this study, a new approach based on 3-D models and deep learning to frontalize face images is proposed. Specifically designed for facial expression analysis, the proposed approach aims to reduce possible negative effects that a posed face image can generate, by normalizing the face region. In the first phase, the face image is semi-frontalized, with a pre-established 3-D reference model based approach. Then, missing regions on semi-frontalized images due to geometric transformation are reconstructed with the help of a denoising stacked autoencoder network. In this phase, missing regions created by line of sight are learned, with a deep architecture, using numerous images. When examined, it can be said that, faces acquired with the proposed approach, are objectively better than the faces acquired with a deep learning or 3-D based method alone. Therefore, it is assumed that the proposed approach can be used in face based computer vision methods as a beneficial pre-processing step. © 2017 Elsevier B.V., All rights reserved.Publication Metadata only Facial emotion classification using deep embedding with triplet loss function, Üçlü Yitim Fonksiyonu Tabanli Derin Gömme ile YÜz Duygu Siniflandirmasi(Institute of Electrical and Electronics Engineers Inc., 2017) Bircanoglu, Cenk; Arica, Nafiz; Bircanoglu, Cenk, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Arica, Nafiz, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn this paper, a deep embedding method using triplet loss function is proposed for classification of the emotions in face images. The originality of proposed method lies in the loss function, different from the other deep learning-based facial emotion classification approaches. The input face images are embedded into a lower dimensional feature space using a multi-layer convolutional neural network. In this embedding process the loss function is calculated by taking triple samples in the training dataset. For each sample in batches, two samples are selected in such a way that one of them is from the same class and the other one from the different class. The loss function aims to close the samples belonging to the same class to each other in the Euclidean space and to move away from the samples in the different class. In the performance analysis of proposed method, two popular deep architectures, namely AlexNet and VGG are used on two datasets called CIFE and GaMo. The experiments show that the proposed method outperforms the other popular loss functions and the available studies on this particular datasets. © 2017 Elsevier B.V., All rights reserved.Publication Metadata only A case study on transfer learning in convolutional neural networks, Evrişimli sinir aǧlarinda eǧitim transferi için örnek çalişma(Institute of Electrical and Electronics Engineers Inc., 2018) Gürkaynak, Cahit Deniz; Arica, Nafiz; Gürkaynak, Cahit Deniz, Bahçeşehir Üniversitesi, Istanbul, Turkey; Arica, Nafiz, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn this work, a case study is performed on transfer learning approach in convolutional neural networks. Transfer learning parameters are examined on AlexNet, VGGNet and ResNet architectures for marine vessel classification task on MARVEL dataset. The results confirmed that transferring the parameter values of the first layers and fine-tuning the other layers, whose weights are initialized from pre-trained weights, performs better than training network from scratch. It's also observed that preprocessing and regularization improves overall scores significantly. © 2018 Elsevier B.V., All rights reserved.Publication Metadata only A comparison of activation functions in artificial neural networks, Yapay sinir aǧlarinda aktivasyon fonksiyonlarinin karşilaştirilmasi(Institute of Electrical and Electronics Engineers Inc., 2018) Bircanoglu, Cenk; Arica, Nafiz; Bircanoglu, Cenk, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Arica, Nafiz, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn this study, the effects of Activation Functions (AF) in Artificial Neural Network (ANN) on regression and classification performance are compared. In comparisons, success rates in test data and duration of training are evaluated for both problems. A total of 11 AF functions, 10 AF commonly used in the literature and Square function proposed in this study, are compared using 7 different datasets, 2 for regression and 5 for classification. 3 different ANN architectures, which are considered to be the most appropriate for each dataset are employed in the experiments. As a result of totally 231 different training procedures, the effects of Afs are examined for different datasets and architectures. Similarly, the effects of AF on training time are shown for different datasets. In the experiments it is shown that ReLU is the most succesfull AF in general purposes. In addition to ReLU, Square function gives the better results in image datasets. © 2018 Elsevier B.V., All rights reserved.