A Comparative Study of Different Color Space Models Using FCM-Based Automatic GrabCut for Image Segmentation

作者: Dina Khattab , Hala Mousher Ebied , Ashraf Saad Hussein , Mohamed Fahmy Tolba , None

DOI: 10.1007/978-3-319-21404-7_36

关键词: GrabCutComputer scienceImage segmentationCluster analysisComputer visionRGB color modelArtificial intelligenceSegmentationScale-space segmentationHSL and HSVColor space

摘要: GrabCut is one of the powerful color image segmentation techniques. One main disadvantage need for initial user interaction to initialize process which classifies it as a semi-automatic technique. The paper presents use Fuzzy C-means clustering replacement automation. Several researchers concluded that no single space model can produce best results every problem. This comparative study different models using automatic problem segmentation. includes test five models; RGB, HSV, XYZ, YUV and CMY. A dataset 30 images are used evaluation. Experimental show generating accuracy images.

参考文章(30)
Yi Hu, Human Body Region Extraction from Photos Journal of Machine Vision and Applications. pp. 473- 476 ,(2007)
Claas Bontus, Thomas Köhler, Reconstruction Algorithms for Computed Tomography Advances in Imaging and Electron Physics. ,vol. 151, pp. 1- 63 ,(2009) , 10.1016/S1076-5670(07)00401-6
Dina Khattab, Hala M. Ebied, Ashraf S. Hussein, Mohamed F. Tolba, Automatic GrabCut for Bi-label Image Segmentation Using SOFM IEEE Conf. on Intelligent Systems (2). pp. 579- 592 ,(2015) , 10.1007/978-3-319-11310-4_50
Laurent Busin, Nicolas Vandenbroucke, Ludovic Macaire, Color Spaces and Image Segmentation Advances in Imaging and Electron Physics. ,vol. 151, pp. 65- 168 ,(2008) , 10.1016/S1076-5670(07)00402-8
Aranzazu Jurio, Miguel Pagola, Mikel Galar, Carlos Lopez-Molina, Daniel Paternain, A Comparison Study of Different Color Spaces in Clustering Based Image Segmentation international conference information processing. pp. 532- 541 ,(2010) , 10.1007/978-3-642-14058-7_55
G. Ruiz-Ruiz, J. Gómez-Gil, L.M. Navas-Gracia, Testing different color spaces based on hue for the environmentally adaptive segmentation algorithm (EASA) Computers and Electronics in Agriculture. ,vol. 68, pp. 88- 96 ,(2009) , 10.1016/J.COMPAG.2009.04.009
Miguel Pagola, Rubén Ortiz, Ignacio Irigoyen, Humberto Bustince, Edurne Barrenechea, Pedro Aparicio-Tejo, Carmen Lamsfus, Berta Lasa, New method to assess barley nitrogen nutrition status based on image colour analysis Computers and Electronics in Agriculture. ,vol. 65, pp. 213- 218 ,(2009) , 10.1016/J.COMPAG.2008.10.003