Flag Counter
AKILLI SİSTEMLER VE UYGULAMALARI DERGİSİ
JOURNAL OF INTELLIGENT SYSTEMS WITH APPLICATIONS
J. Intell. Syst. Appl.
E-ISSN: 2667-6893
Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License.

Investigation of Segmentation Performances of Superpixel Algorithms for Noisy Images

Süperpiksel Algoritmalarının Gürültülü İmgeler İçin Bölütleme Performansının İncelenmesi

How to cite: Özer F, Özkaya U. Investigation of segmentation performances of superpixel algorithms for noisy images. Akıllı Sistemler ve Uygulamaları Dergisi (Journal of Intelligent Systems with Applications) 2019; 2(1): 58-65. DOI: 10.54856/jiswa.201905063

Full Text: PDF, in Turkish.

Total number of downloads: 617

Title: Investigation of Segmentation Performances of Superpixel Algorithms for Noisy Images

Abstract: Superpixels, used espically in image and video segmentation applications, are the visiual structures composed of pixels having same color, intensity and texture behavior. In this work, segmentation performances of superpixel algorithms for noisy images are investigated. Moreoever, the effect of denoising to segmentation accuracy is also investigated. For this purpose, most common three superpixel algorithms are implemented to the images selected from image segmentation database. As a result of efforts made, noise sensitivity and segmentation performance of superpixel algorithms are investigated. Also, the effect of denoising process as a preprocessing step to the segmentation performance is also examined.

Keywords: Superpixel; image segmentation; noise


Başlık: Süperpiksel Algoritmalarının Gürültülü İmgeler İçin Bölütleme Performansının İncelenmesi

Özet: Süperpikseller, özellikle imge ve video bölütleme uygulamalarında kullanılan; bir imgeye veya videoya ait benzer renk, yoğunluk ve doku özellikleri benzerlik gösteren piksellerden oluşan görsel yapılardır. Bu çalışmada süperpiksel algoritmalarının gürültülü imgeler için bölütleme performansı incelenmiştir. Ayrıca, bölütleme uygulamalarında filtre kullanımının bölütleme performansına etkisi de incelenmiştir. Bu amaçla, en yaygın kullanılan üç süperpiksel algoritması imge bölütleme veri setinden seçilen imgelere uygulanmıştır. Gerçekleştirilen uygulamalar sonucunda, süperpiksel algoritmalarının gürültü bağışıklığı ve bölütleme performansları incelenmiştir. Ayrıca, ön işlem olarak filtre kullanımının bölütleme performansına olan etkisi incelenmiştir.

Anahtar kelimeler: Süperpiksel; imge bölütleme; gürültü


Bibliography:
  • Li Z, Wu XM, Chang SF. Segmentation using superpixels: A bipartite graph partitioning approach. In 2012 IEEE Conference on Computer Vision and Pattern Recognition, June 16-21, 2012, Providence, RI, USA, pp. 789–796.
  • Zhang L, Gao Y, Xia Y, Lu K, Shen J, Ji R. Representative discovery of structure cues for weakly supervised image segmentation. IEEE Transactions on Multimedia 2014; 16(2): 470–479.
  • Mori G. Guiding model search using segmentation. In Tenth IEEE International Conference on Computer Vision (ICCV'05), October 17-21, 2005, Beijing, China, pp. 1417-1423.
  • Sun X, Shang K, Ming D, Tian J, Ma J. A biologically-inspired framework for contour detection using superpixel-based candidates and hierarchical visual cues, Sensors 2015; 15(10): 26654-26674.
  • Despotovic I, Jelaca V, Vansteenkiste E, Philips W. Noise-robust method for image segmentation. In International Conference on Advanced Concepts for Intelligent Vision Systems, December 13-16, 2010, Sydney, Australia, pp. 153-162.
  • Stutz D, Hermans A, Leibe B. Superpixels: An evaluation of the state-of-the-art. Computer Vision and Image Understanding 2018; 166: 1-27.
  • Roels J, De Vylder J, Aelterman J, Lippens S, Saeys Y, Philips W. Superpixel quality in microscopy images: The impact of noise & denoising. In XIV Mediterranean Conference on Medical and Biological Engineering and Computing, March 31-April 2, 2016, Paphos, Cyprus, pp. 258-263.
  • Wu CH, Chang HH. Superpixel-based image noise variance estimation with local statistical assessment. EURASIP Journal on Image and Video Processing 2015; 2015: 38.
  • Fu P, Li C, Sun Q, Cai W, Feng DD. Image noise level estimation based on a new adaptive superpixel classification. In 2014 IEEE International Conference on Image Processing (ICIP), October 27-30, 2014, Paris, France, pp. 2649-2653.
  • Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Susstrunk S. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 2012; 34(11): 2274-2282.
  • Levinshtein A, Stere A, Kutulakos KN, Fleet DJ, Dickinson SJ, Siddiqi, K. Turbopixels: Fast superpixels using geometric flows. IEEE Transactions on Pattern Analysis and Machine Intelligence 2009; 31(12): 2290-2297.
  • Fu H, Cao X, Tang D, Han Y, Xu D. Regularity preserved superpixels and supervoxels. IEEE Transactions on Multimedia 2014; 16(4): 1165-1175.