Araştırma Makalesi
BibTex RIS Kaynak Göster

Kullanıcı Yardımına Kararlı, Uzlamsal Adaptif DGL Test Tabanlı Çoklu Görüntü Kesitleme

Yıl 2022, Cilt: 37 Sayı: 2, 569 - 576, 30.06.2022
https://doi.org/10.21605/cukurovaumfd.1146610

Öz

Son dönemde DGL testi, kullanıcı yardımlı görüntü kesitleme problemine başarıyla uygulanmış ve etiketlenmiş pikseller, kesit çerçeveleri ve piksel tohumları gibi farklı kullanıcı girdileriyle kararlı bir şekilde çalışarak çoklu görüntü kesitleme problemine basit ve etkili bir çözüm olarak sunulmuştur. Fakat, sunulan temel yöntemde kullanıcı girdilerinin görüntü kesitleri hakkında sağladığı uzlamsal bilgiden faydalanılmamış ve test sadece renk uzayında uygulanmıştır. Bu çalışmada, kullanıcı girdilerinin uzlamsal bilgilerinin daha iyi bir kesitleme performansı için temel karar verme mekanizmasına dahil edildiği, uzlamsal olarak duyarlı bir DGL testi sunulmuştur. Önerdiğimiz yöntemin, algoritmik ya da hesaplama karmaşıklığını arttırmadan, basit ve muntazam bir şekilde temel yönteme dahil edilebildiği gösterilmiştir. Berkeley BSDS500 görüntü veri tabanında yaptığımız betimlemeler önerilen yöntemin faydalarını göstermekte olup; performans betimlemeleri, temel yönteme göre %3 oranında kesitlemede iyileştirme elde edilebileceğini göstermektedir.

Kaynakça

  • 1. Boykov, Y.Y., Jolly, M.P., 2001. Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D Images, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, 1, 105-112.
  • 2. Rother, C., Kolmogorov, V., Blake, A., 2004. Grabcut: Interactive Foreground Extraction Using Iterated Graph Cuts, ACM Transactions on Graphics, 23(3), 309–314.
  • 3. Grady, L., 2006. Random Walks for Image Segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(11), 1768-1783.
  • 4. Ramadan, H., Lachqar, C., Tairi, H., 2020. A Survey of Recent Interactive Image Segmentation Methods. Comp. Visual Media 6, 355–384.
  • 5. Devroye, L., Gyorfi, L., Lugosi, G. A., 2002. A Note on Robust Hypothesis Testing. IEEE Trans. Inform. Theory, 48(7), 2111-2014.
  • 6. Biglieri, E., Gyorfi, L., 2014. Some Remarks on Robust Binary Hypothesis Testing. IEEE Inter. Symp. on Inform. Theory, 566-570.
  • 7. Afşer, H., 2021. Statistical Classification via Robust Hypothesis Testing: Non-Asymptotic and Simple Bounds. IEEE Signal Processing Letters, 28, 2112-2116.
  • 8. Afşer, H., 2022. A Baseline Statistical Method for Robust User-assisted Multiple Segmentation. IEEE Signal Processing Letters, 29, 737-741.
  • 9. Arbelaez, P., Maire, M., Fowlkes, C., Malik, J., 2011. Contour Detection and Hierarchical Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5), 898-916.
  • 10. Junmo, Kim, Fisher, J.W., Yezzi, A., Cetin, M., Willsky, A.S., 2005. A Nonparametric Statistical Method for Image Segmentation Using Information Theory and Curve Evolution. IEEE Transactions on Image Processing, 14(10), 1486-1502.
  • 11. Nieuwenhuis, C., Cremers, D., 2013. Spatially Varying Color Distributions for Interactive Multilabel Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(5), 1234-1247.
  • 12. Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Susstrunk, S., 2012. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2274-2282.

Spatially Adaptive DGL Test for Robust User-Assisted Multilabel Segmentation

Yıl 2022, Cilt: 37 Sayı: 2, 569 - 576, 30.06.2022
https://doi.org/10.21605/cukurovaumfd.1146610

Öz

Recently, the DGL test has been successfully applied to the user-assisted image segmentation problem where different types of user inputs, e.g. labeled pixels from ground truth masks, bounding boxes and pixel seeds, can be robustly leveraged to assist the segmentation process in a simple and effective way. However, in the baseline method the spatial information of the user inputs is not utilized and the test is implemented in the color domain. In this work, we propose a spatially adaptive version of the DGL test where the spatial information of the user-input regions is incorporated into the decision making process of the original test for an improved segmentation performance. We show that the proposed approach can be simply and seamlessly integrated into the baseline method without increasing its computational and algorithmic complexity. We demonstrate simulations on the Berkeley’s BSDS500 image database that validate the effectiveness of the proposed method. We also present benchmarking results which indicate that the accuracy can be improved by about 3% compared to the baseline method.

Kaynakça

  • 1. Boykov, Y.Y., Jolly, M.P., 2001. Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D Images, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, 1, 105-112.
  • 2. Rother, C., Kolmogorov, V., Blake, A., 2004. Grabcut: Interactive Foreground Extraction Using Iterated Graph Cuts, ACM Transactions on Graphics, 23(3), 309–314.
  • 3. Grady, L., 2006. Random Walks for Image Segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(11), 1768-1783.
  • 4. Ramadan, H., Lachqar, C., Tairi, H., 2020. A Survey of Recent Interactive Image Segmentation Methods. Comp. Visual Media 6, 355–384.
  • 5. Devroye, L., Gyorfi, L., Lugosi, G. A., 2002. A Note on Robust Hypothesis Testing. IEEE Trans. Inform. Theory, 48(7), 2111-2014.
  • 6. Biglieri, E., Gyorfi, L., 2014. Some Remarks on Robust Binary Hypothesis Testing. IEEE Inter. Symp. on Inform. Theory, 566-570.
  • 7. Afşer, H., 2021. Statistical Classification via Robust Hypothesis Testing: Non-Asymptotic and Simple Bounds. IEEE Signal Processing Letters, 28, 2112-2116.
  • 8. Afşer, H., 2022. A Baseline Statistical Method for Robust User-assisted Multiple Segmentation. IEEE Signal Processing Letters, 29, 737-741.
  • 9. Arbelaez, P., Maire, M., Fowlkes, C., Malik, J., 2011. Contour Detection and Hierarchical Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5), 898-916.
  • 10. Junmo, Kim, Fisher, J.W., Yezzi, A., Cetin, M., Willsky, A.S., 2005. A Nonparametric Statistical Method for Image Segmentation Using Information Theory and Curve Evolution. IEEE Transactions on Image Processing, 14(10), 1486-1502.
  • 11. Nieuwenhuis, C., Cremers, D., 2013. Spatially Varying Color Distributions for Interactive Multilabel Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(5), 1234-1247.
  • 12. Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Susstrunk, S., 2012. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2274-2282.
Toplam 12 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Mühendislik
Bölüm Makaleler
Yazarlar

Hüseyin Afşer Bu kişi benim 0000-0002-6302-4558

Yayımlanma Tarihi 30 Haziran 2022
Yayımlandığı Sayı Yıl 2022 Cilt: 37 Sayı: 2

Kaynak Göster

APA Afşer, H. (2022). Spatially Adaptive DGL Test for Robust User-Assisted Multilabel Segmentation. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 37(2), 569-576. https://doi.org/10.21605/cukurovaumfd.1146610