Object Identification Using Weakly Supervised Semantic Segmentation
Main Article Content
Abstract
Image segmentation is referred to as one of the most important processes of image processing. Image segmentation is the technique of dividing or partitioning an image into parts, called segments. It is mostly useful for applications like image compression or object recognition because for these types of applications, it is inefficient to process the whole image. So, image segmentation is used to segment the parts from the image for further processing. Semantic image segmentation is a vast area for computer vision and machine learning researchers. Many vision applications need accurate and efficient image segmentation and segment classification mechanisms for assessing the visual contents and perform real-time decision making. In this paper, we recommend conditional random field (CRF) based framework for weakly supervised semantic segmentation. First merging super pixels into large pieces and use these pieces for further use to identify objects. The pieces from all the training images are gathered and associated with appropriate semantic labels by CRF. In the case of testing, by using the potential energy of each piece merged from super pixels are compare with piece library. For results, we use commonly used the dataset for image segmentation is MSRC-21 and VOC 2012 with state-of-art
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
IJCERT Policy:
The published work presented in this paper is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This means that the content of this paper can be shared, copied, and redistributed in any medium or format, as long as the original author is properly attributed. Additionally, any derivative works based on this paper must also be licensed under the same terms. This licensing agreement allows for broad dissemination and use of the work while maintaining the author's rights and recognition.
By submitting this paper to IJCERT, the author(s) agree to these licensing terms and confirm that the work is original and does not infringe on any third-party copyright or intellectual property rights.
References
L. Ladicky, C. Russell, P. Kohli, and P. H. S. Torr, “Graph cut based inference with co-occurrence statistics,” in Proc. Eur. Conf. Comput.Vis., Heraklion, Greece, 2010, pp. 239–253.
H. Lu, G. Fang, X. Shao, and X. Li, “Segmenting human from photo images based on a coarse-to-fine scheme,” IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 42, no. 3, pp. 889–899, Jun. 2012.
J. Carreira and C. Sminchisescu, “CPMC: Automatic object segmentation using constrained parametric min-cuts,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 7, pp. 1312–1328, Jul. 2012.
Y.-L. Hou and G. K. H. Pang, “Multicue-based crowd segmentation using appearance and motion,” IEEE Trans. Syst., Man, Cybern., Syst., vol. 43, no. 2, pp. 356–369, Mar. 2013.
X. Yuan, J. Guo, X. Hao, and H. Chen, “Traffic sign detection via graphbased ranking and segmentation algorithms,” IEEE Trans. Syst., Man, Cybern., Syst., vol. 45, no. 12, pp. 1509–1521, Dec. 2015.
Y.-T. Chen, X. Liu, and M.-H. Yang, “Multi-instance object segmentation with occlusion handling,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Boston, MA, USA, 2015, pp. 3470–3478.
J. Wang and A. L. Yuille, “Semantic part segmentation using compositional model combining shape and appearance,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Boston, MA, USA, 2015, pp. 1788–1797.
H. Zhang, J. E. Fritts, and S. A. Goldman, “Image segmentation evaluation: A survey of unsupervised methods,” Comput. Vis. Image Understand., vol. 110, no. 2, pp. 260–280, 2008.
G. Csurka and F. Perronnin, “A simple high performance approach to semantic segmentation,” in Proc. Brit. Mach. Vis. Conf., Leeds, U.K., 2008, pp. 1–10.
F. Wang, Q. Huang, M. Ovsjanikov, and L. J. Guibas, “Unsupervised multi-class joint image segmentation,” in Proc. IEEE Conf. Comput. Vis.Pattern Recognit., Columbus, OH, USA, 2014, pp. 3142–3149.
A. Vezhnevets, V. Ferrari, and J. M. Buhmann, “Weakly supervised semantic segmentation with a multiimage model,” in Proc. IEEE Int.Conf. Comput. Vis., Barcelona, Spain, 2011, pp. 643–650.
Y. Liu, J. Liu, Z. Li, J. Tang, and H. Lu, “Weaklysupervised dual clustering for image semantic segmentation,” in Proc. IEEE Conf. Comput.Vis. Pattern Recognit., Portland, OR, USA, 2013, pp. 2075–2082.
L. Zhang et al., “Probabilistic graphlet cut: Exploiting spatial structure cue for weakly supervised image segmentation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Portland, OR, USA, 2013, pp. 1908–1915.
K. Zhang, W. Zhang, Y. Zheng, and X. Xue, “Sparse reconstruction for weakly supervised semantic segmentation,” in Proc. Int. Joint Conf.Artif. Intell., Beijing, China, 2013, pp. 1889–1895.
L. Zhang et al., “A probabilistic associative model for segmenting weakly supervised images,” IEEE Trans. Image Process., vol. 23, no. 9,pp. 4150–4159, Sep. 2014.
P. O. Pinheiro and R. Collobert, “From image-level to pixel-level labeling with convolutional networks,” in Proc. IEEE Conf. Comput. Vis.Pattern Recognit., Boston, MA, USA, 2015, pp. 1713–1721.
J. Dai, K. He, and J. Sun, “Boxsup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentation,” in Proc. IEEE Int. Conf. Comput. Vis., Santiago, Chile, 2015,pp. 1635–1643
Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine S• usstrunk, SLIC Superpixels, EPFL Technical Report 149300, June 2010.
Yi Li, Yanqing Guo, Member, IEEE, Yueying Kao, and Ran He “Image Piece Learning for Weakly Supervised Semantic Segmentation” IEEE transaction on systems, man, and cybernetics: systems, vol. 47, april 2017.