Retinal blood vessels have a significant role in the diagnosis and treatment of various retinal diseases such as diabetic retinopathy, glaucoma, arteriosclerosis, and hypertension. For this reason, retinal vasculature extraction is important in order to help specialists for the diagnosis and treatment of systematic diseases. In this paper, a novel approach is developed to extract retinal blood vessel network. Our method comprises four stages: (1) preprocessing stage in order to prepare dataset for segmentation; (2) an enhancement procedure including Gabor, Frangi, and Gauss filters obtained separately before a top-hat transform; (3) a hard and soft clustering stage which includes K-means and Fuzzy C-means (FCM) in order to get binary vessel map; and (4) a postprocessing step which removes falsely segmented isolated regions. The method is tested on color retinal images obtained from STARE and DRIVE databases which are available online. As a result, Gabor filter followed by K-means clustering method achieves 95.94% and 95.71% of accuracy for STARE and DRIVE databases, respectively, which are acceptable for diagnosis systems.

No abstract

No abstract

No abstract

No abstract

Retinal image processing provides tools for automatic diagnosis and monitoring of retinal diseases such as diabetic retinopathy (DR), age related macular degeneration (ARMD), glucoma and such. The properties of vessel structures on the other hand are widely utilized in locating morphologic structures such as optic disc and macula and in automatic diagnosis of the retinal diseases. Due to the importance of retinal vessels, we propose a simple approach for vessel tracking and measuring vessel diameter in retinal fundus images. Images having manually segmented retinal vasculatures are obtained from STARE database and used in this study. Our method first finds the midlines of the vessel network on the segmented images by employing Zhang-Suen thinning algorithm and then tracks the vessel branches through those midlines. Lastly, the diameters of the vessel segments in different parts of the vasculature are calculated along with the tracking operation. The performed test results show that the proposed automatic method is quite successfully tracks the vessel network and measure the diameter.

Özetçe -Medikal görüntüleri kullanan Bilgisayar Destekli Tanı (BDT) sistemleri son yıllarda oldukça geniş bir kullanım alanına erişmiştir. Retinal fundus görüntülerden çıkarılan kan damarları da sistematik bazı hastalıkların teshis ve tedavisinde önemli öznitelikler sunmaktadırlar. Kan damarlarındaki dallanma, çaprazgeçiş noktaları gibi öznitelikler görüntü çakıştırma uygulamalarında oldukça fazla kullanılmaktadır. Çalışmada ikili retinal damar görüntüleri kullanılarak görüntü çakıştırma işlemi gerçekleştirilmektedir.İlk olarak damar inceltme işlemi ile kan damarlarının iskeleti çıkarılmaktadır. Daha sonra görüntü çakıştırma işleminde kullanılacak öznitelik noktaları belirlenmektedir. Son olarak tek bir retinal damar agını temsil edecek karakteristik matris çıkarılmaktadır. Döndürülmüş, ötelenmiş ve ölçeklenmiş ikinci bir retinal damar görüntüsü üzerinde de aynı işlemler gerçekleştirilmektedir. Buşekilde aynı retinaya ait iki farklı ikili damar görüntüsü karşılaştırılarak eşleşen noktalar belirlenmekte ve görüntü çakıştırma işlemi gerçekleştirilmektedir.Anahtar Kelimeler-retinal kan damarları, görüntü çakıştırma, dallanma noktaları, çapraz geçiş noktaları, inceltme, graf Abstract-Computer Aided Diagnosis (CADx) systems have been reached to a large usuage area in recent years. Blood vessels extracted from retinal fundus images provide us important features for diagnosis and treatment of some systematic diseases. These features such as bifurcation and crossover points are mostly used in image registration applications. In this paper, an image registration study is performed by using binary retinal vessel map. Firstly, a thinnig operation is performed in order to obtain skeletonized vessel image. Then feature points like bifurcations and crossovers are extracted in order to use for image registration. Lastly, a characteristic matrix is extracted to represent the retinal vessel network. Similar operations are performed on a second rotated, translated and scaled retinal vessel network image. By this way, two retinal vessel network images belong to the same person are compared and each feature points are paired with each others in order to develope an image registration process.

Ozetce I,aret dilinin ,czumlenmesi karmapsik hesapsal sure,leri i,ermekte ses i,leme, goruntu i,leme, oruntu tanima, dogal dil i,leme gibi degi,ik alanlarl kapsamaktadzr. I,aretin ve sesin taninmasinda gerekli olan bu sure,ler, insan-bilgisayar etkile,iminin geli,mesinde onemli rol oynamaktadzr. Bu makalede insan konu,masinin taninmasinda goruntu bilgilerinden faydalanilarak bilgisayarli dudak okuma uzerinde durulmaktadzr. Dudak bolgesinin bulunmasi, dudak hareketlerinin takibi ve bilgisayarli dudak okuma i,in gerekli ozelliklerin elde edilmesi ile ilgili yaklapsimlar 6nerilmektedir. AbstractThe analysis of sign language covers different areas such as audio and image processing, pattern recognition, natural language processing that require complex computational processing. These processes required recognizing the sign and audio, plays an important role in development of humancomputer interaction. In this paper we focused on automatic lipreading by utilizing visual information in speech recognition. Some approaches aboutfinding lip area, tracking lip contours and obtaining required features about automatic lipreading are suggested.