Generalized ICM for image segmentation based on Tsallis statistics

Kılıç, İlker; Kayacan, Ozhan

doi:10.1016/j.physa.2011.12.062

Cited by 9 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Olasılık tabanlı MRF algoritması görüntüdeki pikselleri dağılım fonksiyonlarına göre etiketle yapar [21]. Clique ( ∈ ) ise birbirine komşu olan noktalar bütünüdür (∀ ′ ∈ , ∈ ′ ) şeklinde tanımlanır.…”

Section: Markov Random Field (Mrf)unclassified

Beyin Tümörü Tespitinde Görüntü Bölütleme Yöntemlerine Ait Başarımların Karşılaştırılması ve Analizi

Bulut¹,

Kılıç²,

Ince³

2018

deufmd

View full text Add to dashboard Cite

Özet: Görüntü işleme teknikleri klinik karar destek sistemlerinde (KKDS) sıklıkla kullanılmaktadır. Bu çalışmada çağın önemli bir hastalığı olan beyin tümörlerinin görüntü işleme teknikleri ile tespit edilebilmesi amaçlanmıştır. Manyetik Rezonans görüntülerinden (MRI) yararlanarak beyin tümörünün görüntü segmentasyonu ile tespit edilmesine yönelik bir çalışma gerçekleştirilmiştir. Devlet hastanelerinden MR görüntüleri resmi izinlerle alınmış ve çalışmada kullanılmıştır. Markov Random Field (MRF), Kapur, Kittler ve Otsu algoritmaları ile MR görüntülerindeki tümörlü bölgeler tespit edilmeye çalışılmıştır. Algoritmalar, MR görüntülerinin daha önceden belirlenmiş bölgelerine (ROI -Region of Interest) ayrı ayrı uygulanmıştır. Yapılan deneysel uygulamada Markov Random Field (MRF) algoritmasının beyin tümörü tespitinde diğer algoritmalara oranla daha başarılı sonuçlar verdiği gözlemlenmiştir.

show abstract

Section: Markov Random Field (Mrf)unclassified

Beyin Tümörü Tespitinde Görüntü Bölütleme Yöntemlerine Ait Başarımların Karşılaştırılması ve Analizi

Bulut¹,

Kılıç²,

Ince³

2018

deufmd

View full text Add to dashboard Cite

show abstract

“…[15][16][17][18] Let S denotes an M × N lattice that indexes the pixels in the image. In our method, we conduct sea-land segmentation based on the MRFs method.…”

Section: Sea-land Segmentation and Morphological Processingmentioning

confidence: 99%

Method for inshore ship detection based on feature recognition and adaptive background window

Zhao

Wang

Huang

et al. 2014

J. Appl. Remote Sens

View full text Add to dashboard Cite

Inshore ship detection in synthetic aperture radar (SAR) images is a challenging task. We present an inshore ship detection method based on the characteristics of inshore ships. We first use the Markov random field (MRF) method to segment water and land, and then extract the feature points of inshore ships using polygonal approximation. Following this, we propose new rules for inshore ship extraction and use these rules to separate inshore ships from the land in binary images. Finally, we utilize the adaptive background window (ABW) to complete the clutter statistic and successfully detect inshore ships using a constant false alarm rate (CFAR) detector with ABW and G 0 distribution. Experimental results using SAR images show that our method is more accurate than traditional CFAR detection based on K-distribution (K-CFAR), given the same CFAR, and that the quality of the image obtained through our method is higher than that of the traditional K-CFAR detection method by a factor of 0.165. Our method accurately locates and detects inshore ships in complicated environments and thus is more practical for inshore ship detection.

show abstract

“…The q-algebra is derived from Tsallis definition of non-extensive entropy. There are some works in the literature that used with success the Tsallis q-entropy into the image processing [5][6][7] and image analysis 8,9 fields. The q-Gaussian kernels was previously used to noise reduction 10 .…”

Section: Introductionmentioning

confidence: 99%

Performing edge detection by Difference of Gaussians using q-Gaussian kernels

Assirati¹,

Silva²,

Berton

et al. 2014

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In image processing, edge detection is a valuable tool to perform the extraction of features from an image. This detection reduces the amount of information to be processed, since the redundant information (considered less relevant) can be unconsidered. The technique of edge detection consists of determining the points of a digital image whose intensity changes sharply. This changes are due to the discontinuities of the orientation on a surface for example. A well known method of edge detection is the Difference of Gaussians (DoG). The method consists of subtracting two Gaussians, where a kernel has a standard deviation smaller than the previous one. The convolution between the subtraction of kernels and the input image results in the edge detection of this image. This paper introduces a method of extracting edges using DoG with kernels based on the q-Gaussian probability distribution, derived from the q-statistic proposed by Constantino Tsallis. To demonstrate the method's potential, we compare the introduced method with the traditional DoG using Gaussians kernels. The results showed that the proposed method can extract edges with more accurate details.

show abstract

Generalized ICM for image segmentation based on Tsallis statistics

Cited by 9 publications

References 32 publications

Beyin Tümörü Tespitinde Görüntü Bölütleme Yöntemlerine Ait Başarımların Karşılaştırılması ve Analizi

Beyin Tümörü Tespitinde Görüntü Bölütleme Yöntemlerine Ait Başarımların Karşılaştırılması ve Analizi

Method for inshore ship detection based on feature recognition and adaptive background window

Performing edge detection by Difference of Gaussians using q-Gaussian kernels

Contact Info

Product

Resources

About