Abstract
Shadow is a natural phenomenon observed in most natural images. It can reveal information about the objects shape as well as the illumination direction. In computer vision algorithms, shadow can affect negatively image segmentation results, feature extraction, or object tracking. For that, it is necessary to detect and eliminate shadow. Texture remains the best feature used to detect the shadow and photometric information can be used to eliminate it. However, in case of an image with a shadow projected on a complex texture, most of the proposed approaches in literature are useless. In this study, we propose an automatic and data-driven approach for shadow detection and elimination based on the Bidimensional Empirical Mode Decomposition (BEMD). The main idea is to decompose the shaded image into intrinsic components (IMF) that contains only texture and a residue with only objects shape. Then, shadow detection is performed on the IMFs by matching the pair of segmented regions using texture features, while elimination is carried out via a Gaussian approximation applied only on the residue. Finally, the shadow-free image is obtained by adding all the IMFs and the shadow-free residue. The proposed approach is evaluated in comparison with recent approaches on images with the different type of shadow.
Similar content being viewed by others
References
Aqel S, Sabri MA, Aarab A (2015) Background modeling algorithm based on transitions intensities. Int Rev Comput Software 10:387–392. https://doi.org/10.15866/irecos.v10i4.5432
Aqel S, Sabri MA, Aarab A (2016) Simple and efficient approach for shadow removal from a single-image. Int J Imag 16:100–106 https://www.researchgate.net/publication/308395890_Simple_and_efficient_approach_for_shadow_removal_from_a_single-image
Arfia FB, Sabri, MA, Messaoud MB, Abid M (2011) The modified bidimensional empirical mode decomposition for color image decomposition. Proceedings of the World Congress on Engineering, Jul. 6–8, London. http://www.iaeng.org/publication/WCE2011/WCE2011_pp1610-1613.pdf
Cavallaro A, Salvador E, Ebrahimi T (2005) Shadow-aware object-based video processing. I Proc Vis Image Signal Process 152:398–406. https://doi.org/10.1049/ip-vis:20045108
Gong H, Cosker D (2014) Shadow removal dataset and online benchmark for variable scene categories. Proceedings of the British Machine Vision Conference, (MVC’ 14)
Gong H, Cosker D (2016) Interactive removal and ground truth for difficult shadow scenes. J Optic Soc Am A 33:1798–1811. https://doi.org/10.1364/JOSAA.33.001798
Guo R, Dai Q, Hoiem D (2011) Single-image shadow detection and removal using paired regions, CVPR
Guo R, Dai Q, Hoiem D (2012) Paired regions for shadow detection and removal. I Trans Pattern Anal Mach Intell 35:2956–2967. https://doi.org/10.1109/TPAMI.2012.214
Haralick RM, Shanmugan K, Dinstein I (1973) Textural features for image classification. I Trans Syst Man Cybernet 3:610–621. https://doi.org/10.1109/TSMC.1973.4309314
Horprasert T, Harwood D, Davis L (1999) A statistical approach for real-time robust background subtraction and shadow detection. Proceedings of the 7th IEEE international conference on computer vision, (CCV’ 999), Kerkyera, Greece: 1–19
Huang JB, Chen CS (2009) Moving cast shadow detection using physics-based features. Proceedings of the IEEE Conference Computer Vision and Pattern Recognition, Jun. 20–25. IEEE Xplore Press, Miami, FL, USA, pp 2310–2317. https://doi.org/10.1109/CVPR.2009.5206629
Karoud M, Sabri MA, Andaloussi SJ, Tairi H, Aarab A (2006) Block image analysis using empirical mode decomposition. J WSEAS Trans Comput 12:2903–2911
Karoud M, Sabri MA, Andaloussi SJ, Tairi H, Aarab A (2008) Fast bidimensional empirical mode decomposition based on an adaptive block partitioning. Int J Comput Sci Netw Sec 8:357–363 https://pdfs.semanticscholar.org/9167/1e43eede1ce8946efa0c6d008fba5a6b75e0.pdf
Khan SH, Bennamoun H, Sohel M, Togneri FR (2016) Automatic shadow detection and removal from a single image. I Trans Patt Anal Mach Intell 38:431–446. https://doi.org/10.1109/TPAMI.2015.2462355
Leone A, Distante C (2007) Shadow detection for moving objects based on texture analysis. Patt Recog 40:1222–1233. https://doi.org/10.1016/j.patcog.2006.09.017
Mahajan R, Bajpayee A (2015) A survey on shadow detection and removal based on single light source. Proceedings of the 9th international conference intelligent systems control, Jan. 9–10. IEEE Xplore press, Coimbatore, India, pp 1–5. https://doi.org/10.1109/ISCO.2015.7282374
Nunes JC, Bouaoune Y, Delechelle E, Niang O, Bunel P (2003) Image analysis by bidimensional empirical mode decomposition. Image Vis Comput 21:1019–1026. https://doi.org/10.1016/S0262-8856(03)00094-5
Qin R, Liao S, Lei Z, Li S (2010) Moving cast shadow removal based on local descriptors. Proceedings for the 20th international conference pattern recognition, Aug. 23–26. IEEE Xplore press, Istanbul, Turkey, pp 1377–1380. https://doi.org/10.1109/ICPR.2010.340
Sabri A, Karoud M, Tairi H, Aarab A (2008) An efficient image retrieval approach based on spatial correlation of the Extrema points of the IMFs. Int Rev Comput Softw 4:8–15
Sabri A, Karoud M, Tairi H, Aarab A (2009) A robust image watermarking based on the empirical mode decomposition. Int Rev Comput Softw 4:360–365
Sanin A, Sanderson C, Lovell BC (2012) Shadow detection: a survey and comparative evaluation of recent methods. Patt Recog 45:1684–1695. https://doi.org/10.1016/j.patcog.2011.10.001
Sun B, Li S (2010) Moving cast shadow detection of vehicle using combined color models. Chin Conf Pattern Recogn Chongqing Chin : 1–5. doi:https://doi.org/10.1109/CCPR.2010.5659321
Vicente TFY, Hoai M, Samaras D Leave-one-out kernel optimization for shadow detection and removal. IEEE Trans Pattern Anal Mach Intell 40(3):682–695
Wu J, Jiang Z, Yang J, Luo J (2013) Shadow boundaries identification in single natural images via multiple kernels learning. In: Proceedings of the international conference image graphics, Jul. 26–28. IEEE Xplore press, Qingdao, China, pp 348–352
Zhang L, Zhang Q, Xiao C (2015) Shadow remover: image shadow removal based on illumination recovering optimization. Trans Image Proc 24:4623–4636. https://doi.org/10.1109/TIP.2015.2465159
Zhu J, Samuel KG, Masood SZ, Tappen MF (2010) Learning to recognize shadows in monochromatic natural images. Proceedings of the IEEE Conference Computer Vision Pattern Recognition, June 13–18. IEEE Xplore Press, San Francisco, USA, pp 223–230. https://doi.org/10.1109/CVPR.2010.5540209
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sabri, M., Aqel, S. & Aarab, A. A multiscale based approach for automatic shadow detection and removal in natural images. Multimed Tools Appl 78, 11263–11275 (2019). https://doi.org/10.1007/s11042-018-6678-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-6678-x