شناسایی شی برجسته در پیش بینی تمرکز نگاه با استفاده از یادگیری عمیق

نوع مقاله : مقاله پژوهشی فارسی

نویسندگان

دانشگاه بیرجند

چکیده

شناسایی شی برجسته، توجه محققین در حوزه‌های مختلف را به خود جلب کرده‌است بگونه‌ای که در بسیاری از کاربردهای ماشین بینایی از جمله شناسایی و رهگیری شیء بکار گرفته می‌شود. بیشتر کارهای انجام شده در این حوزه مبتنی بر مدل‌های بصری پائین به بالا می‌باشند و از ویژگی‌های سطح پائین برای استخراج تصویر برجستگی نهایی استفاده می‌کنند که از دقت قابل توجهی در تشخیص شیء چشمگیر برخوردار نمی‌باشند. از طرفی مدل‌های بصری بالا به پائین برای کاربردهای خاصی مورد استفاده قرار می‌گیرند. در این مقاله روش متفاوتی برای استخراج تصویر برجستگی شیء ارائه شده است که از ویژگی‌های سطح پائین به بالا و بالا به پائین برای استخراج تصویر برجستگی استفاده می‌کند و مبتنی بر فرآیند یادگیری می‌باشد. انتخاب همزمان این ویژگی‌ها باعث بهبود الگوریتم پیشنهادی در کاربردهای مختلف می‌شود و باعث افزایش دقت شناسایی شیء چشمگیر می‌شود. فرآیند یادگیری با استفاده از شبکه عصبی کانولوشن انجام می‌گیرد. پس از اینکه تصویر به سوپرپیکسل-های آن تجزیه شد، ویژگی‌های متفاوتی از آن استخراج می‌گردد. سپس ویژگی‌های استخراج شده به میانگین صفر و واریانس واحد نرمالیزه شده و از الگوریتم شبکه عصبی کانولوشن به‌منظور آموزش دادن ویژگی‌ها استفاده می‌شود. دقت روش پیشنهادی با استفاده از 8 تصویر برجستگی و یادگیری عمیق بهبود داده شده است. روش پیشنهادی با بیش از 20 روش دیگر و در 4 پایگاه داده شناخته شده MSRA-1000، ECSSD، MSRA-10k و PASCAL-S مورد ارزیابی و مقایسه قرار گرفته شده است. نتایج حاکی از کارآیی روش پیشنهادی نسبت به سایر روش‌ها در زمینه پیش‌بینی شیء چشمگیر در تعیین تمرکز نگاه می‌باشد.

کلیدواژه‌ها


  [1]     A. Borji, D. Sihite, and L. Itti, “Quantitative analysis of humanmodel agreement in visual saliency modeling: A comparative study,” IEEE TIP, vol. 22, no. 1, pp. 55–69, 2013.
  [2]     A. Borji. Boosting bottom-up and top-down visual features for saliency estimation. In CVPR, 2012.
  [3]     Q. Zhou, “Object-based attention: saliency detection using contrast via background prototypes,” electronics letters, vol. 50, No. 14, pp. 997-999, 2014.
  [4]     L. Itti, C. Koch, and E. Niebur, “A Model of Saliency-Based Visual Attention for Rapid Scene Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp. 1254-1259, 1998.
  [5]     Chenlei Guo and Liming Zhang, “A Novel Multiresolution Spatiotemporal Saliency Detection Model and Its Applications in Image and Video Compression,” IEEE Transactions On Image Processing, Vol. 19, No. 1, pp. 10-25, 2010.
  [6]     N. Sang, L. Wei, and Y. Wang, “A Biologically-inspired Top-down Learning Model Based on Visual Attention,” International conference on pattern recognition, 2010.
  [7]     Tadmeri Narayan Vikram, Marko Tscherepanow, Britta Wrede, “A saliency map based on sampling an image into random rectangular,” Pattern Recognition, 2012.
  [8]     M. Wang, J. Li, T. Huang, Y. Tian, L. Duan, G. Jia, Saliency detection based on 2d log-gabor wavelets and center bias, in: Proceedings of the International Conference on Multimedia, 2010, pp. 979–982.
  [9]     V. Yanulevskaya, J.M. Geusebroek, Significance of the Weibull distribution and its sub-models in natural image statistics, in: Proceedings of the International Conference on Computer Vision Theory and Applications, 2009, pp. 355–362.
[10]     R. Achanta and S. Susstrunk, “Saliency Detection for Contentaware Image Resizing,” in IEEE International Conference on Image Processing, 2009.
[11]     L. Zhang, M. H. Tong, T. K. Marks, H. Shan, and G. W. Cottrell, “SUN: A Bayesian framework for saliency using natural statistics,” Journal of Vision, vol. 8, no. 7, pp. 1–20, 2008.
[12]     T. Avraham, M. Lindenbaum, “Esaliency (extended saliency): meaningful attention using stochastic image modeling, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 4,  pp. 693–708, 2010.
[13]     W. Kienzle, F.A. Wichmann, B. Sch¨ olkopf, M.O. Franz, “A nonparametric approach to bottom-up visual saliency, Advances in Neural Information Processing Systems, 2007, pp. 689–696.
[14]     K. Huang, C. Zhu, and G. Li, “Saliency Detection by Adaptive Channel Fusion,” IEEE Signal Processing Letters, vol. 25, no. 7, pp. 1059–1063, 2018.
[15]     Q. Zhao and C. Koch, Learning visual saliency by combining feature maps in a nonlinear manner using adaboost", Journal of Vision, vol. 12, no. 6, pp. 1-15, 2012.
[16]     T. Judd, K. Ehinger, F. Durand, and A. Torralba, Learning to predict where humans look", in Proceedings of International Conference on Computer Vision, 2009.
[17]     Zhao and C. Koch, Learning a saliency map using _xated locations in natural scenes", Journal of Vision, vol. 11, no. n3, pp. 1-15, 2011.
[18]     B. Jiang, L. Zhang, H. Lu, C. Yang, and M.-H. Yang, “Saliency Detection via Absorbing Markov Chain,” 2013 IEEE International Conference on Computer Vision, Dec. 2013.
[19]     N. Tong, H. Lu, L. Zhang, X. Ruan, "Saliency Detection with Multi-Scale Superpixels", IEEE Signal Processing Letters, Vol. 21, No. 9, pp. 12-19, 2014.
[20]     Wang, H. Lu, X. Li, N. Tong, and W. Liu, “Saliency detection via background and foreground seed selection,” Neurocomputing, vol. 152, pp. 359–368, Mar. 2015.
[21]     C. Aytekin, H. Possegger, T. Mauthner, S. Kiranyaz, H. Bischof, and M. Gabbouj, “Spatiotemporal Saliency Estimation by Spectral Foreground Detection,” IEEE Transactions on Multimedia, vol. 20, no. 1, pp. 82–95, Jan. 2018.
[22]     J. Yang and M.-H. Yang, “Top-Down Visual Saliency via Joint CRF and Dictionary Learning,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 3, pp. 576–588, Mar. 2017.
[23]     H. Farsi, R. Nasiripour, S. Mohammadzadeh, "Eye gaze detection based on learning automata by using SURF descriptor," Information Systems & Telecommunication, vol. 6, no. 1, pp. 41-49, 2018.
[24]     P. F. Felzenszwalb and D. P. Huttenlocher, “Efficient graph-based image segmentation,” IJCV, vol. 59, no. 2, pp. 167–181, 2004.
[25]     O., Csillik, "Fast segmentation and classification of very high resolution remote sensing data using SLIC superpixels," Remote Sensing, vol. 9, no. 3, pp. 243-250, 2017.
[26]     N. Tong, Lu H, R. Xiang, M. Hsuan. "Salient object detection via bootstrap learning", IEEE Conference on Computer Vision and Pattern Recognition, USA, pp. 1884-1892, 2015.
[27]     G., Li, Y., Yu, "Deep contrast learning for salient object detection," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 478-487, 2016.
[28]     E. A. Smirnov, D. M. Timoshenko, and S. N. Andrianov, "Comparison of Regularization Methods for ImageNet Classification with Deep Convolutional Neural Networks," AASRI Procedia, vol. 6, 2014, pp. 89–94.
[29]     R. Achanta, S. S. Hemami, F. J. Estrada, and S. S€usstrunk, “Frequency-tuned salient region detection,” in Proc. IEEE Conf. Computer. Vis. Pattern Recognition, 2009, pp. 1597–160.
[30]     Yan Q, Xu L, Shi J, Jiaya Jia, "Hierarchical saliency detection", IEEE Conference, USA, 2013, pp. 1155-1162.
[31]     http://mmcheng.net/gsal/.
[32]     Y. Li, X. Hou, C. Koch, J. Rehg, and A. Yuille, “The secrets of salient object segmentation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2014, pp. 280–287.
[33]     Cheng M, Mitra NJ, Huang X, Torr PH, Hu S. Global contrast based salient region detection. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 2015; 37(3):569–82.
[34]     F. Perazzi, P. Kr€ahenb€uhl, Y. Pritch, and A. Hornung, “Saliency filters: Contrast based filtering for salient region detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2012, pp. 733–740.
[35]     X. Li, Y. Li, C. Shen, A. R. Dick, and A. van den Hengel,“Contextual hypergraph modeling for salient object detection,” in Proc. IEEE Int. Conf. Comput. Vis., 2013, pp. 3328–3335.
[36]     X. Shen and Y. Wu, “A unified approach to salient object detection via low rank matrix recovery,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2012, pp. 2296–2303.
[37]     C. Lang, G. Liu, J. Yu, and S. Yan, “Saliency detection by multitask sparsity pursuit,” IEEE Trans. Image Process., vol. 21, no. 3, pp. 1327–1338, 2012.
[38]     H. Jiang, J. Wang, Z. Yuan, T. Liu, N. Zheng, and S. Li, “Automatic salient object segmentation based on context and shape prior,” in Proc. Brit. Mach. Vis. Conf., 2011, pp. 1–12.
[39]     S. Goferman, L. Z. Manor, and A. Tal, “Context-aware saliency detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2010, pp. 1915–1926.
[40]     X. Hou, J. Harel, and C. Koch, “Image signature: Highlighting sparse salient regions,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 1, pp. 194–201, 2012.
[41]     E. Rahtu, J. Kannala, M. Salo, and J. Heikkil€a, “Segmenting salient objects from images and videos,” in Proc. Eur. Conf. Comput. Vis., 2010, pp. 366–379.
[42]     R. Achanta, S. Hemami, F. Estrada, and S. S€usstrunk, “Frequencytuned salient region detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2009, pp. 1597–1604.
[43]     X. Hou and L. Zhang, “Saliency detection: A spectral residual approach,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2007, pp. 1–8.
[44]     Y. Zhai and M. Shah, “Visual attention detection in video sequences using spatiotemporal cues,” in Proc. 14th ACM Int. Conf. Multimedia, 2006, pp. 815–824.
[45]     J. Kim, D. Han, Y. Tai, and J. Kim, “Salient region detection via high-dimensional color transform,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2014, pp. 883–890.
[46]     R. Margolin, A. Tal, and L. Zelnik-Manor, “What makes a patch distinct?” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2013, pp. 1139–1146.
[47]     C. Scharfenberger, A. Wong, K. Fergani, J. S. Zelek, and D. A. Clausi, “Statistical textural distinctiveness for salient region detection in natural images,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2013, pp. 979–986.
[48]     K.-Y. Chang, T.-L. Liu, H.-T. Chen, and S.-H. Lai, “Fusing generic objectness and visual saliency for salient object detection,” in Proc. IEEE Int. Conf. Comput. Vis., 2011, pp. 914–921.
[49]     R. Achanta, F. J. Estrada, P. Wils, and S. S€usstrunk, “Salient region detection and segmentation,” in Proc. 6th Int. Conf. Comput. Vis. Syst., 2008, pp. 66–75.
[50]     N.D.B. Bruce, J.K. Tsotsos, Saliency based on information maximization, Advances in Neural Information Processing Systems, 2005, pp. 155–162.
[51]     J. Harel, C. Koch, P. Perona, Graph-based visual saliency, Advances in Neural Information Processing Systems, 2007, pp. 545–552.
[52]     Y. F. Ma and H. J. Zhang, Contrast-based image attention analysis by using fuzzy growing. In ACM International Conference on Multimedia, 2003.
[53]     X. Hou and L. Zhang. Saliency detection: A spectral residual approach. IEEE Conference on Computer Vision and Pattern Recognition, 2007.
[54]     A. Garcia-Diaz, V. Lebor´an, X. R. Fdez-Vidal, and X. M. Pardo. On the relationship between optical variability, visual saliency, and eye fixations: A computational approach. Journal of Vision, Vol. 12, No. 6, 2012.
[55]     X. Hou and L. Zhang. Dynamic visual attention: Searching for coding length increments. In NIPS, pages 681–688, 2008.
[56]     B., Jiang, L., Zhang, H., Lu, Saliency detection via absorbing Markov chain. IEEE Int. Conf. on Computer Vision, Sydney, Australia, 2013.
[57]     X., Hu, L., Zhu, J., Qin, C.W., Fu, P.A. Heng. Recurrently aggregating deep features for salient object detection. In Thirty-Second AAAI Conference on Artificial Intelligence, 2018.
[58]     X., Zhang, T., Wang, J., Qi, H., Lu, G. Wang. Progressive attention guided recurrent network for salient object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 714-722.
[59]     W., Wang, J., Shen, X., Dong, A. Borji. Salient object detection driven by fixation prediction. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 1711-1720.
[60]     S., Fang, J., Li, Y., Tian, T., Huang, X., Chen, Learning discriminative subspaces on random contrasts for image saliency analysis. IEEE transactions on neural networks and learning systems, vol. 28, no. 5, pp.1095-1108, 2018.
[61]     B., Ghariba, M.S., Shehata, P. McGuire. Visual Saliency Prediction Based on Deep Learning. Information, vol. 10, no. 8, 2019.