SimLocator: robust locator of similar objects in images
- 507 Downloads
Similar objects commonly appear in natural images, and locating and cutting out these objects can be tedious when using classical interactive image segmentation methods. In this paper, we propose SimLocator, a robust method oriented to locate and cut out similar objects with minimum user interaction. After extracting an arbitrary object template from the input image, candidate locations of similar objects are roughly detected by distinguishing the shape and color features of each image. A novel optimization method is then introduced to select accurate locations from the two sets of candidates. Additionally, a matting-based method is used to improve the results and to ensure that all similar objects are located in the image. Finally, a method based on alpha matting is utilized to extract the precise object contours. To ensure the performance of the matting operation, this work has developed a new method for foreground extraction. Experiments show that SimLocator is more robust and more convenient to use compared to other more advanced repetition detection and interactive image segmentation methods, in terms of locating similar objects in images.
KeywordsSimilar objects Object descriptor Object matching Stable locations Contour extraction
We thank anonymous reviewers for their valuable input. We thank Fuzhang Wu for making some Dual-Bound results. We thank the flickr members who kindly share their images under Creative Commons License: Bestfriend (tea cups), RenateEurope (purple flowers), acaffery (balloons), Luko Gecko (fish school), Bold Huang (petunia), Swami Stream (chocolate cake). We thank the users of 500px.com who have shared their images through public domain: Ricky Marek (pomegranates), Nitin Prabhudesai (dandelions), Joram Huyben (green lanterns). We also thank the users of pinterest.com who have put the media in their spaces: Gus’s Mom (panda cakes), Rhonda E. Peterson (meatballs), Cindy Loo (fried balls). The two fruit cake images are borrowed from . This work is supported by National Natural Science Foundation of China under project Nos. 61172104, 61271430, 61201402 and 61202324, by Beijing Natural Science Foundation (Content Aware Image Synthesis and its Applications, No. 4112061), and by SRF for ROCS, SEM.
- 2.Ahuja, N., Todorovic, S.: Extracting texels in 2.1d natural textures. In: IEEE International Conference on Computer Vision, pp. 1–8. IEEE Computer Society, Los Alamitos (2007) Google Scholar
- 5.Berg, A.C., Berg, T.L., Malik, J.: Shape matching and object recognition using low distortion correspondences. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol. 1, CVPR’05, pp. 26–33. IEEE Computer Society, Washington (2005) CrossRefGoogle Scholar
- 6.Chen, Q., Li, D., Tang, C.K.: KNN matting. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 869–876 (2012) Google Scholar
- 8.Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 886–893. IEEE, New York (2005) Google Scholar
- 9.Forssén, P.E.: Maximally stable colour regions for recognition and matching. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–8 (2007) Google Scholar
- 11.Joulin, A., Bach, F., Ponce, J.: Discriminative clustering for image co-segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR2010), pp. 1943–1950 (2010) Google Scholar
- 12.Kim, E., Li, H., Huang, X.: A hierarchical image clustering cosegmentation framework. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 686–693 (2012) Google Scholar
- 13.Krages, B.: Photography: The Art of Composition. Allworth Press, New York (2005) Google Scholar
- 14.Leung, T.K., Malik, J.: Detecting, localizing and grouping repeated scene elements from an image. In: Proceedings of the 4th European Conference on Computer. ECCV’96, vol. I, pp. 546–555. Springer, London (1996) Google Scholar
- 17.Liu, J., Sun, J., Shum, H.Y.: Paint selection. ACM Trans. Graph. 28(3), 69:1–69:7 (2009) Google Scholar
- 23.Thompson, D.W.: On Growth and Form. Cambridge University Press, Cambridge (1992) Google Scholar