Browsing by Subject "Image matching"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item Open Access Alignment of uncalibrated images for multi-view classification(IEEE, 2011) Arık, Sercan Ömer; Vuraf, E.; Frossard P.Efficient solutions for the classification of multi-view images can be built on graph-based algorithms when little information is known about the scene or cameras. Such methods typically require a pair-wise similarity measure between images, where a common choice is the Euclidean distance. However, the accuracy of the Euclidean distance as a similarity measure is restricted to cases where images are captured from nearby viewpoints. In settings with large transformations and viewpoint changes, alignment of images is necessary prior to distance computation. We propose a method for the registration of uncalibrated images that capture the same 3D scene or object. We model the depth map of the scene as an algebraic surface, which yields a warp model in the form of a rational function between image pairs. The warp model is computed by minimizing the registration error, where the registered image is a weighted combination of two images generated with two different warp functions estimated from feature matches and image intensity functions in order to provide robust registration. We demonstrate the flexibility of our alignment method by experimentation on several wide-baseline image pairs with arbitrary scene geometries and texture levels. Moreover, the results on multi-view image classification suggest that the proposed alignment method can be effectively used in graph-based classification algorithms for the computation of pairwise distances where it achieves significant improvements over distance computation without prior alignment. © 2011 IEEE.Item Open Access Matching ottoman words: an image retrieval approach to historical document indexing(ACM, 2007-07) Ataer, Esra; Duygulu, PınarLarge archives of Ottoman documents are challenging to many historians all over the world. However, these archives remain inaccessible since manual transcription of such a huge volume is difficult. Automatic transcription is required, but due to the characteristics of Ottoman documents, character recognition based systems may not yield satisfactory results. It is also desirable to store the documents in image form since the documents may contain important drawings, especially the signatures. Due to these reasons, in this study we treat the problem as an image retrieval problem with the view that Ottoman words are images, and we propose a solution based on image matching techniques. The bag-of-visterms approach, which is shown to be successful to classify objects and scenes, is adapted for matching word images. Each word image is represented by a set of visual terms which are obtained by vector quantization of SIFT descriptors extracted from salient points. Similar words are then matched based on the similarity of the distributions of the visual terms. The experiments are carried out on printed and handwritten documents which included over 10,000 words. The results show that, the proposed system is able to retrieve words with high accuracies, and capture the semantic similarities between words. Copyright 2007 ACM.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 Osmanlıca kelimeleri eşleme(IEEE, 2007-06) Ataer, Esra; Duygulu, PınarOsmanlı arşivleri dünyanın pek çok yerinden araştırmacının ilgi alanına girmektedir. Fakat bu belgelerin elle çevirisi zor bir iş olduğu için, bu arşivler kullanılamaz durumdadır. Otomatik çeviri gerekmektedir, fakat Osmanlıca’nın yazma özelliklerinden dolayı karakter tabanlı tanıma sistemleri istenen başarıyı gösterememektedir. Ayrıca, belgeler minyatür ve tuğra gibi önemli kısımlar içerdiği için, imge formatında saklanmaları gerekmektedir. Bu nedenle, bu çalışmada Osmanlıca kelimeleri imge olarak görerek probleme imge erişim problemi olarak yaklaşıldı ve kelime eşleme tekniği üzerine bir çözüm önerisinde bulunuldu. Nesne tanımada başarılı olan görsel öğeler kümesi (bag-of-visterms) tekniği kelime eşleme işlemine uyarlandı ve böylece her kelime imgesi taç noktalarından çıkarılan SIFT özelliklerinin ¨ vektor¨ nicemlemesiyle sembolize edildi. Benzer kelimeler görsel ögelerin dağılımına göre eşlendi. Deneyler 10,000 kelimenin üzerindeki matbu ve elyazması belge üzerinde yapıldı. Sonuçlar sistemin benzer kelimeleri yüksek doğrulukla eşlediğini ve anlamsal benzerlikleri bulduğunu gösteriyor Large archives of Ottoman documents are challenging to many historians all over the world. However, these archives remain inaccessible since manual transcription of such a huge volume is difficult. Automatic transcription is required, but due to the characteristics of Ottoman documents, character recognition based systems may not yield satisfactory results. It is also desirable to store the documents in image form since the documents may contain important drawings, especially the signatures. Due to these reasons, in this study we treat the problem as an image retrieval problem with the view that Ottoman words are images, and we propose a solution based on image matching techniques. The bag-of-visterms approach, which is shown to be successful to classify objects and scenes, is adapted for matching word images. Each word image is represented by a set of visual terms which are obtained by vector quantization of SIFT descriptors extracted from salient points. Similar words are then matched based on the similarity of the distributions of the visual terms. The experiments are carried out on printed and handwritten documents which included over 10,000 words. The results show that, the proposed system is able to retrieve words with high accuracies, and capture the semantic similarities between words.Item Open Access SAR image reconstruction by expectation maximization based matching pursuit(Academic Press, 2015) Ugur, S.; Arıkan, Orhan; Gürbüz, A. C.Synthetic Aperture Radar (SAR) provides high resolution images of terrain and target reflectivity. SAR systems are indispensable in many remote sensing applications. Phase errors due to uncompensated platform motion degrade resolution in reconstructed images. A multitude of autofocusing techniques has been proposed to estimate and correct phase errors in SAR images. Some autofocus techniques work as a post-processor on reconstructed images and some are integrated into the image reconstruction algorithms. Compressed Sensing (CS), as a relatively new theory, can be applied to sparse SAR image reconstruction especially in detection of strong targets. Autofocus can also be integrated into CS based SAR image reconstruction techniques. However, due to their high computational complexity, CS based techniques are not commonly used in practice. To improve efficiency of image reconstruction we propose a novel CS based SAR imaging technique which utilizes recently proposed Expectation Maximization based Matching Pursuit (EMMP) algorithm. EMMP algorithm is greedy and computationally less complex enabling fast SAR image reconstructions. The proposed EMMP based SAR image reconstruction technique also performs autofocus and image reconstruction simultaneously. Based on a variety of metrics, performance of the proposed EMMP based SAR image reconstruction technique is investigated. The obtained results show that the proposed technique provides high resolution images of sparse target scenes while performing highly accurate motion compensation.