Abstract
Shadow is inexorable essential in a scene created due to the presence of illumination variation and obstructed object. Shadow depicts information of images such as shape, position, orientation, and camera parameters. But sometimes, shadow degrades the quality of the image while objection segmentation, merging, scene analysis, scene interpretation, object recognition, and tracking. The presented paper aims are to provide a comprehensive technique to detect both indistinct and hard shadows from images. Firstly, a unique combination of ‘luminance (L)’, ‘green-red (a*)’ components, and ‘blue-yellow (b*)’ components of CIELab color space is used to differentiate shadows from objects. After color transformation, shadow regions are differentiated from background and object with an amalgamation of clustering techniques with the help of texture information. According to the extracted regions classification, finally suspected shadow regions are obtained. Experimental results verify that it robustly detects vague and hard shadows in the image.
Similar content being viewed by others
References
Benedek C, Szirányi T (2007) Study on color space selection for detecting cast shadows in video surveillance. Int J Imaging Syst Technol 17(3):190–201
Cavallaro A, Salvador E, Ebrahimi T (2005) Shadow-aware object-based video processing. IEEE Proc Vis Image Signal Proc 152(4):398–406
Dempste AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc 1–38
Fang LZ, Qiong WY, Sheng YZ (2008) A method to segment moving vehicle cast shadow based on wavelet transform. Patt Recognit Lett 29(16):2182–2188
Figov Z, Tal Y, Koppel M (2004) Detecting and removing shadows. In 7th IASTED Int Conf Comput Graph Imaging
Finlayson GD, Hordley SD (2001) Color Constancy at a Pixel. J Opt Soc Am 18(2):253–264
Finlayson GD, Fredembach C (2004) Fast re-integration of shadow-free images. In 12th Color and Imaging Conference, Scottsdale, Arizona, USA 117–122
Garg P, Goyal K (2014) Detection and removal of shadow using chromaticity. Int J Comput Sci Inf Technol 5(4):5745–5747
Glaister J, Wong A, Clausi DA (2014) Segmentation of skin lesions from digital images using joint statistical texture distribution. IEEE Trans Biomed Eng 61(4):1220–1230
Gomes V, Barcellos P, Scharcanski J (2017) Stochastic shadow detection using a hypergraph partitioning approach. Patt Recognit 63:30–44
Gonzalez RC (2011) Woods RE (2011) Digital Image Processing. Prentice-Hall, Pearson Education
Guo R, Dai Q, Hoiem D (2013) Paired regions for shadow detection and removal. IEEE Trans Patt Anal Mach Intell 35(12):2956–2967
Hirai S, Yamanishi K (2013) Efficient computation of normalized maximum likelihood codes for Gaussian mixture models with its applications to clustering. IEEE Trans Inf Theory 59(11):7718–7722
Hsieh JW, Hu WF, Chang CJ, Chen YS (2003) Shadow elimination for effective moving object detection by Gaussian shadow modeling. Image Vis Comput 21(6):505–516
James B, Ehrlich R, Full W (1984) FCM: The Fuzzy c-means clustering algorithm. Comput Geosci 10(2):191–203
Jiang K, Li AH, Cui ZG, Wang T, Su YZ (2013) Adaptive shadow detection using global texture and sampling deduction. IET Comput Vis 7(2):115–122
Jiang K, Li AH, Cui ZG, Wang T, Su YZ (2013) Adaptive shadow detection using global texture and sampling deduction. IET Comput Vis 7(2):115–122
Joshi A, Papanikolopoulos N (2008) Learning to detect moving shadows in dynamic environments. IEEE Trans Patt Anal Mach Intell 30(11):2055–2063
Khan EA, Reinhard E (2004) A survey of color spaces for shadow identification. In Symp Appl Percept Graph Vis 160–160
Khan SH, Bennamoun M, Sohel F, Togneri R (2015) Automatic shadow detection and removal from a single image. IEEE Trans Patt Anal Mach Intell 38(3):431–446
Leng L, Liu G, Li M, Khan MK, Al-Khouri AM (2014) Logical conjunction of triple-perpendicular-directional translation residual for contactless palmprint pre-processing. In 11th IEEE Int Conf Inf Technol New Gener 523–528
Liu P, Zhu Y (2014) An adaptive cast shadow detection with combined texture and color models. Int J Future Comput Commun 3(2):113–118
Martel-Brisson N, Zaccarin A (2007) Learning and removing cast shadows through a multi-distribution approach. IEEE Trans Patt Anal Mach Intell 29(7):1133–1146
Nadimi S, Bhanu B (2004) Physical models for moving shadow and object detection in video. IEEE Trans Patt Anal Mach Intell 26(8):1079–1087
Nguyen V, Vicente TFY, Zhao M, Hoai M, Samaras D (2017) Shadow detection with conditional generative adversarial networks. In IEEE Int Conf Comput Vis 4510–4518
Salvador E, Cavallaro A, Ebrahimi T (2004) Cast shadow segmentation using invariant color features. Comput Vis Image Underst 95(2):238–259
Shen L, Chua TW, Leman K (2015) Shadow optimization from structured deep edge detection. In IEEE Comput Soc Conf Comput Vis Pattern Recognit 2067–2074
Sokolova M, Lapalme G (2009) A systematic analysis of performance measures for classification tasks. Inf Process Manag 45(4):427–437
Sun L, Zhao C, Yan Z, Liu P, Duckett T, Stolkin R (2018) A novel weakly-supervised approach for RGB-D-based nuclear waste object detection. IEEE Sens J 19(9):3487–3500
Vicente TFY, Hoai M, Samaras D (2018) Leave-one-out kernel optimization for shadow detection and removal. IEEE Trans Patt Anal Mach Intell 40(3):682–695
Wang B, Chen CL (2020) Local Water-Filling Algorithm for Shadow Detection and Removal of Document Images. Sensors 20(23):6929
Wang F, Chao H, Leng L (2020) Color Analysis for the Quantitative Aesthetics of Qiong Kiln Ceramics. J Multimed Inf Syst 7(2):97–106
Wu M, Chen R, Tong Y (2020) Shadow elimination algorithm using color and texture features. Comput Intell Neurosci
Yuan X, Ebner M, Wang Z (2015) Single image shadow detection and removal using local color constancy computation. IET Image Process 9(2):118–126
Zhu J, Samuel KG, Masood SZ, Tappen MF (2010) Learning to recognize shadows in monochromatic natural images. In IEEE Conf Comput Vis Pattern Recognit (CVPR) 223–230
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
Dhingra, G., Kumar, V. & Joshi, H.D. Clustering-based shadow detection from images with texture and color analysis. Multimed Tools Appl 80, 33763–33778 (2021). https://doi.org/10.1007/s11042-021-11427-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11427-5