Browsing by Subject "Descriptors"
Now showing 1 - 12 of 12
Results Per Page
Sort Options
Item Open Access Carcinoma cell line discrimination in microscopic images using unbalanced wavelets(IEEE, 2012-03) Keskin, Furkan; Suhre, Alexander; Erşahin, Tüli,; Çetin Atalay, Rengül; Çetin, A. EnisCancer cell lines are widely used for research purposes in laboratories all over the world. In this paper, we present a novel method for cancer cell line image classification, which is very costly by conventional methods. The aim is to automatically classify 14 different classes of cell lines including 7 classes of breast and 7 classes of liver cancer cells. Microscopic images containing irregular carcinoma cell patterns are represented by randomly selected subwindows which possibly correspond to foreground pixels. For each subwindow, a correlation descriptor utilizing the fractional unbalanced wavelet transform coefficients and several morphological attributes as pixel features is computed. Directionally selective textural features are preferred primarily because of their ability to characterize singularities at multiple orientations, which often arise in carcinoma cell lines. A Support Vector Machine (SVM) classifier with Radial Basis Function (RBF) kernel is employed for final classification. Over a dataset of 280 images, we achieved an accuracy of 88.2%, which outperforms the classical correlation based methods. © 2012 IEEE.Item Open Access Covariance matrix-based fire and flame detection method in video(Springer, 2011-09-17) Habiboğlu, Y. H.; Günay, O.; Çetin, A. EnisThis paper proposes a video-based fire detection system which uses color, spatial and temporal information. The system divides the video into spatio-temporal blocks and uses covariance-based features extracted from these blocks to detect fire. Feature vectors take advantage of both the spatial and the temporal characteristics of flame-colored regions. The extracted features are trained and tested using a support vector machine (SVM) classifier. The system does not use a background subtraction method to segment moving regions and can be used, to some extent, with non-stationary cameras. The computationally efficient method can process 320×240 video frames at around 20 frames per second in an ordinary PC with a dual core 2.2 GHz processor. In addition, it is shown to outperform a previous method in terms of detection performance.Item Open Access Flame detection method in video using covariance descriptors(IEEE, 2011) Habiboǧlu, Y.H.; Günay, Osman; Çetin, A. EnisVideo fire detection system which uses a spatio-temporal covariance matrix of video data is proposed. This system divides the video into spatio-temporal blocks and computes covariance features extracted from these blocks to detect fire. Feature vectors taking advantage of both the spatial and the temporal characteristics of flame colored regions are classified using an SVM classifier which is trained and tested using video data containing flames and flame colored objects. Experimental results are presented. © 2011 IEEE.Item Open Access Labeling of faces in personal photo albums(IEEE, 2013) Şener, Emre; Yücel, Utku Can; Aksoy, Sercan; Büyükgebiz, ibrahim; Uzun, Burak; Duygulu, PınarIn this study, we propose a system for organizing personal photo collections. Motivated with the fact that people related queries are the most desired ones, we propose a method for labeling faces in photographs. After representing the detected faces based on the descriptors extracted around facial features, the similarities between all faces in the dataset are found. When user provides labels for a few set of faces, these labels are carried out to other faces using the automatic labeling process. For this pur pose, we proposed a method based on the confidence decisions of three different methods. The user is allowed to provide feedback to increase the performance. Roth search and browsing mechanisms are provided to the user to get the pictures of single or multiple people. © 2013 IEEE.Item Open Access Microscopic image classification via WT-based covariance descriptors using Kullback-Leibler distance(IEEE, 2012) Keskin, Furkan; Çetin, A. Enis; Erşahin, Tülin; Çetin-Atalay, RengülIn this paper, we present a novel method for classification of cancer cell line images using complex wavelet-based region covariance matrix descriptors. Microscopic images containing irregular carcinoma cell patterns are represented by randomly selected subwindows which possibly correspond to foreground pixels. For each subwindow, a new region descriptor utilizing the dual-tree complex wavelet transform coefficients as pixel features is computed. WT as a feature extraction tool is preferred primarily because of its ability to characterize singularities at multiple orientations, which often arise in carcinoma cell lines, and approximate shift invariance property. We propose new dissimilarity measures between covariance matrices based on Kullback-Leibler (KL) divergence and L 2-norm, which turn out to be as successful as the classical KL divergence, but with much less computational complexity. Experimental results demonstrate the effectiveness of the proposed image classification framework. The proposed algorithm outperforms the recently published eigenvalue-based Bayesian classification method. © 2012 IEEE.Item Open Access Nearest-neighbor based metric functions for indoor scene recognition(Academic Press, 2011) Cakir, F.; Güdükbay, Uğur; Ulusoy, ÖzgürIndoor scene recognition is a challenging problem in the classical scene recognition domain due to the severe intra-class variations and inter-class similarities of man-made indoor structures. State-of-the-art scene recognition techniques such as capturing holistic representations of an image demonstrate low performance on indoor scenes. Other methods that introduce intermediate steps such as identifying objects and associating them with scenes have the handicap of successfully localizing and recognizing the objects in a highly cluttered and sophisticated environment. We propose a classification method that can handle such difficulties of the problem domain by employing a metric function based on the Nearest-Neighbor classification procedure using the bag-of-visual words scheme, the so-called codebooks. Considering the codebook construction as a Voronoi tessellation of the feature space, we have observed that, given an image, a learned weighted distance of the extracted feature vectors to the center of the Voronoi cells gives a strong indication of the image's category. Our method outperforms state-of-the-art approaches on an indoor scene recognition benchmark and achieves competitive results on a general scene dataset, using a single type of descriptor. © 2011 Elsevier Inc. All rights reserved.Item Open Access Osmanlica belgelerde kelime erişimi(IEEE, 2011-04) Arifoǧlu, Damla; Duygulu, PınarBu çalışmada, Osmanlıca arşivlerinin analizi amacıyla, kelime erişimi problemi iki farklı resim eşleme yöntemi ile çözülmeye çalışılmaktadır. Bu amaçla (1) Dinamik Zaman Bükmesi (DZB) tabanlı kelime eşleme yöntemi [7] ve (2) Şekil İçeriği (shape context) tanımlayıcısı [10] Osmanlıca belgeler üzerinde uyarlanmıştır. Öncelikle, verilen bir Osmanlıca belgedeki tüm alt-kelimeler bulunmuştur. Birinci yöntemde, her alt-kelime grubu için, üst ve alt kelime profili, siyah pikselden beyaz piksele geçiş sayısı ve dikey izdüşüm özniteliklerinden oluşturulmuş 4 parçalı öznitelik vektörü çıkartılmış, bu özniteliklerin birbirine olan uzaklığı DZB algoritmasıyla bulunmuştur. İkinci yöntemde ise, Şekil İçeriği tanımlayıcısı kullanılarak, alt-kelimelerin birbirine olan uzaklıkları hesaplanmıştır. Uygulanan yöntemler, Fuzuli’nin Leyla ve Mecnun divanının 10 sayfasından oluşan bir Osmanlıca veri kümesi üzerinde denenmiştir. In this paper, two image matching methods are adapted to retrieve words in Ottoman documents. The first method is based on Dynamic Time Warping (DTW) method proposed in [7], while the second method is based on the Shape Context descriptor [10]. Firstly, all sub-words in a given Ottoman document are extracted. In the first method, a 4-variant feature vector (upper and lower word profiles, background to ink transition, vertical projection) is calculated for each subword and feature vectors' distance to each other is found by DTW algorithm. In the second method, shape context descriptor is used to calculate the distances of sub-word images. The methods are tested on an Ottoman data set, which consists of 10 pages of Leyla and Mecnun Divan of Fuzuli. © 2011 IEEE.Item Open Access Real-time wildfire detection using correlation descriptors(IEEE, 2011) Habiboğlu, Y. Hakan; Günay, Osman; Çetin, A. EnisA video based wildfire detection system that based on spatio-temporal correlation descriptors is developed. During the initial stages of wildfires smoke plume becomes visible before the flames. The proposed method uses background subtraction and color thresholds to find the smoke colored slow moving regions in video. These regions are divided into spatio-temporal blocks and correlation features are extracted from the blocks. Property sets that represent both the spatial and the temporal characteristics of smoke regions are used to form correlation descriptors. An SVM classifier is trained and tested with descriptors obtained from video data containing smoke and smoke colored objects. Experimental results are presented. © 2011 EURASIP.Item Open Access Region covariance descriptors calculated over the salient points for target tracking(IEEE, 2012) Çakir, S.; Aytaç, T.; Yildirim, A.; Beheshti, S.; Gerek Ö.N.; Çetin, A. EnisFeatures extracted at salient points in the image are used to construct region covariance descriptor (RCD) for target tracking purposes. In the classical approach, the RCD is computed by using the features at each pixel location and thus, increases the computational cost in the scenarios where large targets are tracked. The approach in which the features at each pixel location are used, is redundant in cases where image statistics do not change significantly between neighboring pixels. Furthermore, this may decrease the tracking accuracy while tracking large targets which have background dominating structures. In the proposed approach, the salient points are extracted via the Shi and Tomasi's minimum eigenvalue method and a descriptor based target tracking structure is constructed based on the features extracted only at these salient points. Experimental results indicate that the proposed method provides comparable and in some cases even better tracking results compared to the classical method while providing a computationally more efficient structure. © 2012 IEEE.Item Open Access Sıkıştırılmış algılama kullanarak yeni bir yüz gösterimi(IEEE, 2011-04) Eleyan, A.; Köse, Kıvanç; Çetin, A. EnisBu bildiride yüz resimleri için yeni bir tanımlayıcı sunulmaktadır. Sıkıştırılmış Algılama (Compressive Sensing) fikri kullanılarak, yüz imgelerinden öznitelikler çıkarılmıştır. Öznitelik çıkarımı sırasında Rastgele Gauss dağılımına sahip elemanları ya da rasgele ikili elemanları olan ölçüm matrisleri kullanılmıştır. Bu sayede elde edilen öznitelik vektörleri en yakın komşu sınıflandırıcısı kullanılarak sınıflandırılmıştır. Hesaplama karmaşıklığı konusunda büyük bir indirim sağlanmış ve bunun yanında tanıma oranlarında büyük bir düşüş yaşanmamıştır.Item Open Access Understanding responses to materials and colors in interiors(Wiley, 2017) Ulusoy, B.; Olguntürk, N.This article investigates the free associations of materials and colors in the context of interior architecture. Materials and colors rarely appear alone in interiors; therefore, in the scope of this study, the researchers explored material pairs and color pairs in addition to single materials and single colors. To elicit free associations from these interior design elements, 192 randomly selected volunteers participated in an experiment using a group of material (fabric, timber, plasterboard) and color (red, green, white) models under controlled conditions. The results contribute to an increased understanding of the associations between the concepts of materials and colors in interiors. While, each model was associated with sensory descriptors, only some models were associated with symbolic or affective descriptors. Single materials were related to different descriptors in interiors on their own, but when they were paired they were associated with fewer affective descriptors. The results showed that color pairs were always associated with all types of descriptors with an exception of red and green color pair, which was not mentioned with affective descriptors. The study findings are expected to be beneficial for interior architects, architects, product designers and researchers who want to shape and investigate a user's experience of interiors. © 2016 Wiley Periodicals, Inc. Col Res Appl, 42, 261–272, 2017. © 2016 Wiley Periodicals, Inc.Item Open Access What is usual in unusual videos? trajectory snippet histograms for discovering unusualness(IEEE, 2014-06) İşcen, Ahmet; Armağan, Anıl; Duygulu, PınarUnusual events are important as being possible indicators of undesired consequences. Moreover, unusualness in everyday life activities may also be amusing to watch as proven by the popularity of such videos shared in social media. Discovery of unusual events in videos is generally attacked as a problem of finding usual patterns, and then separating the ones that do not resemble them. In this study, we address the problem from a different perspective, and try to answer what type of patterns are shared among unusual videos that make them resemble to each other regardless of the ongoing event. With this challenging problem at hand, we propose a novel descriptor to encode the rapid motions in videos utilizing densely extracted trajectories. The proposed descriptor, which is referred to as trajectory snipped histograms, is used to distinguish unusual videos from usual videos, and further exploited to discover snapshots in which unusualness happen. Experiments on domain specific people falling videos and unrestricted funny videos show the effectiveness of our method in capturing unusualness. © 2014 IEEE.