Kitap Bölümü Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe Face Reconstruction from profile to frontal evaluation of face recognition(Springer Science and Business Media Deutschland GmbH, 2020) Afra, Salim; Alhajj, RedaOne of the main challenges in face recognition is handling extreme variation of poses which may be faced for images collected in labs and in the wild. Recognizing faces in profile view has been shown to perform poorly compared to using frontal view of faces. Indeed, previous approaches failed to capture distinct features of a profile face compared to a frontal one. Approaches to enhance face recognition on profile faces have been recently proposed following two different trends. One trend depends on training a neural network model with big multi-view face datasets to learn features of faces by handling all poses. The second trend generates a frontal face image (face reconstruction) from any given face pose and applies feature extraction and face recognition on the generated face instead of profile faces. Recent methods for face reconstruction use generative adversarial networks (GAN) learning model to train two competing neural networks to generate authentic frontal view of any pose preserving person’s identity. For the work described in this paper, we trained a feature extraction neural network model to learn representation of any face pose which is then compared with each other using Euclidean distance. We also used two recent face reconstruction techniques to generate frontal faces. We evaluated the performance of using the generated frontal faces against the posed counterparts. In the conducted experiments, we used three face datasets that contain several challenges for face recognition having faces in a variety of poses and in the wild.Öğe Approaches for early detection of glaucoma using retinal images: A performance analysis(Springer Science and Business Media Deutschland GmbH, 2020) Sarhan, Abdullah; Rokne, Jon; Alhajj, RedaSight is one of the most important senses for humans, as it allows them to see and explore their surroundings. Multiple ocular diseases damaging sight have been detected over the years such as glaucoma and diabetic retinopathy. Glaucoma is a group of diseases that can lead to blindness if left untreated. No cure for glaucoma exists apart from early detection and treatment by an ophthalmologist. Retinal images provide vital information about an eye’s health. On the basis of advancements in retinal images technology it is possible to develop systems that can analyze these images for better diagnosis. To test the efficiency of some of the developed techniques, we obtained the code for four different approaches and did a performance analysis using four public datasets. We investigated the results along with the analysis time. The outcomes of the study are approaches for glaucoma detection;behavior of glaucoma related approaches on retinal images with different ocular diseases;challenges faced when analyzing retinal images; andglaucoma risk factors.Öğe User's research interests based paper recommendation system: A deep learning approach(Springer International Publishing AG, 2020) Bulut, Betül; Gündoğan, Esra; Kaya, Buket; Alhajj, Reda; Kaya, Mehmet[Abstract Not Available]Öğe Crowd behavior modeling in emergency evacuation scenarios using belief-desire-intention model(Springer International Publishing AG, 2020) Şahin, Coşkun; Alhajj, Reda[Abstract Not Available]
