|
Superiority Of Graph-Based Visual Saliency (GVS) Over Other Image Segmentation Methods
[Full Text]
AUTHOR(S)
Umu Lamboi, Issa Fofana, Yahya Labay Kamara
KEYWORDS
computer vision, image segmentation, visual saliency detection, graph-based algorithm.
ABSTRACT
Although inherently tedious, the segmentation of images and the evaluation of segmented images are critical in computer vision processes. One of the main challenges in image segmentation evaluation arises from the basic conflict between generality and objectivity. For general segmentation purposes, the lack of well-defined ground-truth and segmentation accuracy limits the evaluation of specific applications. Subjectivity is the most common method of evaluation of segmentation quality, where segmented images are visually compared. This is daunting task, however, limits the scope of segmentation evaluation to a few predetermined sets of images. As an alternative, supervised evaluation compares segmented images against manually-segmented or pre-processed benchmark images. Not only good evaluation methods allow for different comparisons, but also for integration with target recognition systems for adaptive selection of appropriate segmentation granularity with improved recognition accuracy. Most of the current segmentation methods still lack satisfactory measures of effectiveness. Thus this study proposed a supervised framework which uses visual saliency detection to quantitatively evaluate image segmentation quality. The new benchmark evaluator uses Graph-based Visual Saliency (GVS) to compare boundary outputs for manually segmented images. Using the Berkeley Segmentation Database, the proposed algorithm was tested against 4 other quantitative evaluation methods — Probabilistic Rand Index (PRI), Variation of Information (VOI), Global Consistency Error (GSE) and Boundary Detection Error (BDE). Based on the results, the GVS approach outperformed any of the other 4 independent standard methods in terms of visual saliency detection of images.
REFERENCES
[1] H. Zhang, J. E. Frittsm, & S A. Goldman, “Image segmentation evaluation: A survey of unsupervised methods”, Computer Vision and Image Understanding, vol. 110(2), pp. 260‒280, 2008.
[2] F. Ge, S. Wang, & T. Liu, “New benchmark for image segmentation evaluation”, Journal of Electronic Imaging, vol. 16(3), pp. 011‒033, 2007.
[3] Y. Zhang, “A survey on evaluation methods for image segmentation”, Pattern Recognition, vol. 29(8), pp. 1335‒1346, 1996.
[4] L. Itti, C. Koch, & E. Niebu, “A model of saliency-based visual attention for rapid scene analysis”, Journals & Magazines Pattern Analysis and Machine Intelligence IEEE, vol. 20, pp. 1254‒1259, 1998a.
[5] W. X. Kang, Q. Q. Yang, and R. P. Liang, “The comparative research on image segmentation algorithms”, in: Proceedings of 1st International Workshop on Education Technology and Computer Science, pp. 703‒707, 2009.
[6] B. Popescu, A. Iancu, D. D. Burdescu, M. Brezovan, & E. Ganea, “Evaluation of image segmentation algorithms from the perspective of salient region detection”, ACIVS, vol. 69(15), pp. 183‒194, 2011.
[7] R. Dass, Priyanka, & S. Devi, “Image segmentation techniques”, International Journal of Electronics and Communication Technology (IJECT), vol. 3(1), pp. 66‒70, 2012.
[8] J. Freixenet, X. Muñoz, D. Raba, J. Martí, & X. Cufí, “Yet another survey on image segmentation: region and boundary information integration”, Article ECCV 02 proceedings of the 7th European Conference on Computer Vision, Part III, pp. 408‒422, 2002.
[9] D. Martin, C. Fowlkes, D. Tal, & J. Malik, “A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics”, in: Proceedings of the 8th International Conference Computer Vision, vol. 2, pp. 416‒423, 2004.
[10] Z. Liang, M. Wang, X. Zhou, L. Lin, & W. Li, “Salient object detection based on regions”, Multimedia Tools and Application, DOI 10.1007/s11042-012-1040-1, 2012.
[11] H. Zhang, J. E. Fritts, & S. A. Goldman, “An entropy-based objective evaluation method for image segmentation”, SPIE Proceedings, vol. 5307, pp. 38‒49, 2003.
[12] B. Peng, & L. Zhang, “Evaluation of image segmentation quality by adaptive ground truth composition”, ACM ECCV 12 proceedings of the 12th European Conference on Computer Vision, vol. 3, pp. 287‒300, 2012.
[13] M. Lalitha, M. Kiruthiga, & C. Loganathan, “A survey on image segmentation through clustering algorithm”, International Journal of Science and Research, vol. 2(2), pp. 348‒358, 2013.
[14] B. Peng, L. Zhang, & D. Zhang, “A survey of graph theoretical approaches to image segmentation”, Pattern Recognition, vol. 46(3), pp. 1020‒1038, 2013.
[15] C. Solana-Cipres, G. Fernandez-Escribano, L. Rodriguez-Benitez, J. Moreno-Garcia, & L. Jimenez-Linares. "Real-time moving object segmentation in H.264 compressed domain based on approximate reasoning", International Journal of Approximate Reasoning, vol. 51(1), pp. 99-114, 2009. doi:10.1016/j.ijar.2009.09.002
[16] T. Zuva, O. Olugbara, O. Sunday, & M. S. Ngwira, “Image segmentation”, Available Techniques Developments and Open Issues, vol. 2(3), 2011.
[17] D. Martin, C. Fowlkes, D. Tal, & J. Malik, “A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics”, In Proceedings of 8th IEEE International Conference on Computer Vision (ICCV ’01), Vancouver, BC, Canada, vol. 2, pp. 416–423, 2001.
[18] F. J. Estrada, & A. D. Jepson, “Benchmarking image segmentation algorithms”, International Journal of Computer Vision, Vol. 85(2), pp. 167–181, 2009.
[19] S. Padamavati,.P. Subashini, & A. Sumi,”Empirical Evaluation of suitable segmentation algorithm for IR Images”, International Journal of Advanced”, Computer Science and Applications, vol. 7(4) No.2, 2010.
[20] R. Unnikrishnan, C. Pantofaru, & M. Hebert, “A measure for objective evaluation of image segmentation algorithms”, Proc. CVPR Workshop Empirical Evaluation Methods in Computer Vision, pp. 34, 2005.
[21] J. Prakash, J. M. J. Kezia, & V. VijayaKumar, "Morphological Multiscale Stationary Wavelet Transform based Texture Segmentation", International Journal of Image Graphics and Signal Processing, 2014.
[22] R. Unnikrishnan, C. Pantofaru, & M. Hebert, “Toward objective evaluation of image segmentation algorithms”, IEEE Transactions on pattern analysis and machine intelligence, vol. 29, pp. 929–944, 2007.
[23] O. Muratov, P. Zontone, G. Boato, & F. G. B. De Natale, “A segment-based image saliency detection. ICASSP Publications, vol. 23, pp. 141–381, 2011.
[24] A. Borji, D. N. Sihite, & L Itti, “Salient object detection: A Benchmark Computer Vision ECCV, Part II, LNCS 7573, pp. 414–429, 2012.
[25] G. Yildirim, A. Shaji, & S. S. Usstrunk. “Saliency detection using regression trees on hierarchical images segments”, https://infoscience.epfl.ch/record/201936/files/, last accessed 1st Dec., 2016.
[26] R. Achanta, S. Hemami, F. Estrada, & S. Susstrunk, “Frequency-tuned salient region detection”, Proc. IEEE Conference. Computer Vision and Pattern Recognition, pp. 1597–1604, 2009.
[27] E. D. Gelasca, T. Ebrahimi, M. C. Q. Farias, & M. C. S. K. Mitra, “Towards perceptually driven segmentation evaluation metrics”, Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW04). Vol. 4, pp. 52, 2004.
[28] C. Pantofaru, & M. Hebert, “A comparison of image segmentation algorithms”, Tech. Rep. CMU-RI-TR-05-40, Carnegie Mellon University, 2005.
[29] M. Meila, “Comparing clustering: an axiomatic view”, In: Proceedings of the International Conference on Machine Learning, pp. 577–584, 2005.
[30] J. Lin, B. Peng, T. Li, & Q. Chen, "A learning-based framework for image segmentation evaluation", 2013 5th International Conference on Intelligent Networking and Collaborative Systems, 2013.
[31] N. Bruce & J. Tsotsos, “Saliency based on information maximization”, Advances in Neural Information Processing Systems, vol. 18, pp. 155–162, 2006.
[32] D. Hutchison, T. Kanade, J. Kittler, J. M. Kleinberg, F. Mattern, J. C. Mitchell, M. Naor, C. Pandu-Rangan, B. Steffen, D. Terzopoulos, D. Tygar, G. Weikum, “Lecture notes in computer science, 2012. Springer Publishing, SSN: 0302-9743, http://www.springer.com/series/558.
[33] E. Mohedano, G. Healy, K. McGuinness, X. Giró-i-Nieto, N. E. O'Connor, A. F. Smeaton, “Object segmentation in images using EEG signals”. In: The 22nd ACM International Conference on Multimedia, 3-7, 2014, Orlando, FL. ISBN 978-1-4503-3063-3, http://doras.dcu.ie/20138/.
[34] X. Jiang, C. Marti, C. Irniger, & H. Bunke, “Distance measures for image segmentation evaluation”, EURASIP Journal on Applied Signal Processing, vol. 1, pp. 209–209, 2006.
[35] Q. Huang, & B. Dom, “Quantitative methods of evaluating image segmentation”, Image Processing. Institute of Electrical Electronics Engineering (IEEE). vol. 3, pp. 53–56, 1995.
[36] J. Harel, C. Koch, & P. Perona, “Graph-based visual saliency”, Advances in Neural Information Processing Systems, pp. 545–552, 2007.
[37] L. Itti, J. Braun, D. K. Lee, & C. Koch "Attention Modulation of Human Pattern Discrimination Psychophysics Reproduced by a Quantitative Model", NIPS*1998b
[38] L. Itti, & P. F. Baldi, “Bayesian surprise attracts human attention”, Advances in Neural Information Processing Systems, vol. 19, pp. 547–554, 2006.
[39] J. Malik, & P. Perona, "Pre-attentive texture discrimination with early vision mechanisms", Journal of the Optical Society of America A, vol. 7(5), pp. 923-932, 1990. https://doi.org/10.1364/JOSAA.7.000923.
[40] G. E. Kalliatakis, & G. A. Triantafyllidis, “Image-based monument recognition using graph-based visual saliency”, Electronic Letters on Computer Vision and Image Analysis, Vol. 12(2), 88–97, 2013.
[41] K. Mustafa, "Towards Robust Object Segmentation in Video Sequences and its Applications", Technische Universität Berlin, 2010.
[42] A. X. Falcão, J. K. Udupa, S. Samarasekara, & S. Sharma, “User-steered image segmentation paradigms: live-wire and live-lane”, Graphical Models and Image Processing, vol. 60, pp. 233–260, 1998.
[43] F. P. Felzenszwalb, & D. P. Huttenlocher, “Efficient graph-based image segmentation”, International Journal of Computer Vision, vol. 59(2), pp.167–181, 2004.
|
