Contour-Based Object Extraction and Clutter Removal for Semantic Vision

详细信息    查看全文

• 作者：Mário Antunes (18)
  Luís Seabra Lopes (19)
  
• 关键词：Semantic vision ; contour tracing ; contour aggregation ; object extraction ; clutter removal
• 刊名：Lecture Notes in Computer Science
• 出版年：2013
• 出版时间：2013
• 年：2013
• 卷：7950
• 期：1
• 全文大小：383KB
• 参考文献：1. Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes (VOC) Challenge. Int. J. Computer Vision?88, 303-38 (2010) CrossRef
  2. Seabra Lopes, L., Chauhan, A.: Open-Ended Category Learning for Language Acquisi-tion. Connection Science?20(4), 277-97 (2008) CrossRef
  3. Winn, J., Jojic, N.: LOCUS: learning object classes with unsupervised segmentation. In: Proc. Tenth IEEE Int. Conf. Computer Vision, ICCV 2005, vol.?1, pp. 756-63 (2005)
  4. Kim, S., Park, S., Kim, M.: Central Object Extraction for Object-Based Image Retrieval. In: Bakker, E.M., Lew, M., Huang, T.S., Sebe, N., Zhou, X.S. (eds.) CIVR 2003. LNCS, vol.?2728, pp. 39-9. Springer, Heidelberg (2003) CrossRef
  5. Fu, Y., Cheng, J., Li, Z., Lu, H.: Saliency Cuts: an Automatic Approach to Object Segmentation. In: Proc. 19th International Conference on Pattern Recognition, ICPR 2008 (2008)
  6. Aldavert, D., Ramisa, A., Toledo, R., López de Mántaras, R.: Fast and robust object segmentation with the integral linear classifier. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010 (2010)
  7. Carreira, J., Sminchisescu, C.: Constrained Parametric Min-Cuts for Automatic Object Segmentation. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, CVPR 2010 (2010)
  8. Tamaki, T., Yamamura, T., Ohnishia, N.: Image segmentation and object extraction based on geometric features of regions. In: Proc. SPIE Conf. on Visual Communications and Image Processing, VCIP 1999, vol.?3653, Part II, pp. 937-45 (1999)
  9. Ko, B.C., Nam, J.-Y.: Automatic Object-of-Interest segmentation from natural images. In: Proc. 18th International Conference on Pattern Recognition, ICPR 2006 (2006)
  10. Kim, S., Park, S., Kim, M.: Central Object Extraction for Object-Based Image Retrieval. In: Bakker, E.M., Lew, M., Huang, T.S., Sebe, N., Zhou, X.S. (eds.) CIVR 2003. LNCS, vol.?2728, pp. 39-9. Springer, Heidelberg (2003) CrossRef
  11. Pereira, R., Seabra Lopes, L., Silva, A.: Semantic Image Search and Subset Selection for Classifier Training in Object Recognition. In: Lopes, L.S., Lau, N., Mariano, P., Rocha, L.M. (eds.) EPIA 2009. LNCS (LNAI), vol.?5816, pp. 338-49. Springer, Heidelberg (2009) CrossRef
  12. Ridler, T.W., Calvard, S.: Picture Thresholding using an Iterative Selection Method. IEEE Trans. on Systems, Man and Cybernetics?8(8), 630-32 (1978) CrossRef
  13. Sonka, M., Hlavác, V., Boyle, R.: Image processing, analysis and machine vision, 3rd edn., Thomson (2008)
  14. Antunes, M., Lopes, L.S.: Unsupervised Internet-Based Category Learning for Object Recognition. In: Kamel, M., Campilho, A. (eds.) ICIAR 2013. LNCS, vol.?7950, pp. 766-73. Springer, Heidelberg (2013)
  15. Pereira, R., Seabra Lopes, L.: Learning visual object categories with global descriptors and local features. In: Lopes, L.S., Lau, N., Mariano, P., Rocha, L.M. (eds.) EPIA 2009. LNCS (LNAI), vol.?5816, pp. 225-36. Springer, Heidelberg (2009) CrossRef
  
• 作者单位：Mário Antunes (18)
  Luís Seabra Lopes (19)
  
  18. IT, Universidade de Aveiro, Portugal
  19. IEETA/DETI, Universidade de Aveiro, Portugal
  
• ISSN：1611-3349

文摘

This paper focuses on object extraction from images, a functionality that can be relevant both for category learning and object recognition in diverse applications. The described object extraction approach, which doesn’t take into account any prior knowledge about the target objects, works on the edge-based counterpart of the original image. In a first step, groups of neighboring edge pixels are traced to form contour segments. These contour segments are then coherently aggregated to reconstruct the shapes of the different objects present in the original image. The approach is particularly relevant for extracting objects with few if any distinctive local features, thus objects mainly characterized by their shape. The developed functionalities can be used to segment and extract objects from images with multiple objects, as those obtained from the Internet by searching for a specific object category name. They can also be used to discard clutter from image sub-windows expected to contain a single object, as those delivered by an object detector.