Shadow identification for digital imagery using colour and texture cues

Author(s): R. McFeely ; M. Glavin ; E. Jones
DOI: 10.1049/iet-ipr.2010.0083

For access to this article, please select a purchase option:

Buy article PDF

Buy Knowledge Pack

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership

Recommend Title Publication to library

IET Image Processing — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Author(s): R. McFeely ¹ ; M. Glavin ² ; E. Jones ²
- Affiliations: 1: Hewlett Packard, Galway, Ireland
  2: Connaught Automotive Research Group, Electrical and Electronic Engineering, College of Engineering and Informatics, National University of Ireland Galway, Galway, Ireland
Source: Volume 6, Issue 2, March 2012, p. 148 – 159
DOI: 10.1049/iet-ipr.2010.0083 , Print ISSN 1751-9659, Online ISSN 1751-9667

Shadows cause a significant problem for automated systems which attempt to understand scenes, since shadow boundaries may be incorrectly recognised as a material change, and incorrectly recognised as an object. Shadow identification is therefore an important pre-processing step for applications such as shadow removal, shadow invariant object recognition and shadow invariant object tracking. Many existing shadow identification methods are often limited by the types of shadow boundaries (penumbra) which can be found, by the density (darkness) of the shadows and by the type of surface texture on which the shadows are cast. In addition many of these methods are limited to a specific type of scene, while others result in high levels of false positive (FP) shadow identification. To address these problems, a novel algorithm for automatic shadow identification is proposed, which makes use of a new tree-structured segmentation algorithm for candidate shadow region identification, as well as a combination of colour illumination invariance and texture analysis for shadow verification. The method is tested on a number of indoor and outdoor images exhibiting different types of shadows, surfaces and illumination sources. These results indicate that the proposed method performs well against the state of the art; in particular, the rate of FP identification is reduced from 26 to below 13% when compared with using illumination invariance alone.

References

1. 1)
  - M. Al-Rawi , J. Yang . Using Gabor filter for the illumination invariant recognition of color texture. Math. Comput. Simul , 550 - 555
2. 2)
  - Xu, L., Qi, F., Jiang, R.: `Shadow removal from a single image', Proc. 6th Int. Conf. on Intelligent Systems, Design and Applications, 2006, 2, p. 1049–1054.
3. 3)
  - Wang, H., Suter, D.: `False-peaks-avoiding mean shift method for unsupervised peak-valley sliding image segmentation', Proc. Seventh Digital Image Computing: Techniques and Applications, Macquarie University, 2003, Sydney, Australia, p. 581–590.
4. 4)
  - J. Tian , J. Sun , Y. Tang . Tricolor attenuation model for shadow detection. IEEE Trans. Image Process. , 10 , 2355 - 2363
5. 5)
  - M.D. Levine , J. Bhattacharyya . Removing shadows. Pattern Recognit. Lett. , 3 , 251 - 265
6. 6)
  - N. Otsu . A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cyber. , 62 - 66
7. 7)
  - Massalabi, A., He, D.C., Bénié, G.B., Beaudry, E.: `Restitution of information under shadow in remote sensing high space resolution images', Application to IKONOS data of Sherbrooke city, ISPRS, 2004, Istanbul, Turkey.
8. 8)
  - M. Li , R.C. Staunton . Optimum Gabor filter design and local binary patterns for texture segmentation. Pattern Recognit. Lett. , 0 , 664 - 672
9. 9)
  - Finlayson, G.D., Drew, M.S., Lu, C.: `Intrinsic images by entropy minimization', Proc. Eighth European Conf. on Computer Vision – ECCV 2004, 2004, Prague, Czech Republic, 3023, p. 582–595, Springer Berlin/Heidelberg.
10. 10)
  - G.D. Finlayson , S.D. Hordley , Lum Cheng , M.S. Drew . On the removal of shadows from images. IEEE Trans. Pattern Anal. Mach. Intell. , 1 , 59 - 68
11. 11)
  - C.F. Juang , C.T. Lin . An online self constructing neural fuzzy inference network and its applications. IEEE Trans. Fuzzy Syst. , 1 , 12 - 32
12. 12)
  - Shen, L., Tan, P., Lin, S.: `Intrinsic image decomposition with non-local texture cues', Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008, Anchorage, Alaska, p. 1–7.
13. 13)
  - J.A. Swets , R.M. Dawes , J. Monahan . Psychological science can improve diagnostic decisions. Psychol. Sci. Public Interest , 1 , 1 - 26
14. 14)
  - J. Delon , A. Desolneux , J.L. Lisani , A.B. Petro . Automatic color palette. Inverse Probl. Imag. , 2 , 265 - 287
15. 15)
  - Nielsen, M., Madsen, C.B.: `Segmentation of soft shadows based on a daylight and penumbra model', Computer Vision/Computer Graphics Collaboration Techniques, 2007, 4418, p. 341–352.
16. 16)
  - J. Yao , Z. Zhang . Hierarchical shadow detection for color aerial images. Comp. Vis. Image Underst. , 1 , 60 - 69
17. 17)
  - Pujas, P., Aldon, M.: `Robust colour image segmentation', Seventh Int. Conf. on Advanced Robotics (ICAR'95), 1995, San Filiu de Guixols, Spain.
18. 18)
  - S. Arivazhagan , L. Ganesan , S. Padam Priyal . Texture classification using Gabor wavelets based rotation invariant features. Pattern Recognit. Lett. , 1976 - 1982
19. 19)
  - J.J. Rubio , W. Yu . A new discrete-time sliding-mode control with time-varying gain and neural identification. Int. J. Control , 4 , 338 - 348
20. 20)
  - R.M. Haralick . Statistical and structural approaches to texture. Proc. IEEE , 5 , 786 - 804
21. 21)
  - C.-F. Juang , C.-T. Lin . A recurrent self-organizing neural fuzzy inference network. IEEE Trans. Neural Netw. , 4 , 828 - 845
22. 22)
  - Fredembach, C., Finlayson, G.D.: `Simple shadow removal', 18thInt. Conf. on Pattern Recognition, (ICPR 2006), 2006, Hong Kong, 1, p. 832–835.
23. 23)
  - E. Salvador , A. Cavallaro , T. Ebrahimi . Cast shadow segmentation using invariant color features. Trans. Comput. Vis. Image Underst. , 2 , 238 - 259
24. 24)
  - G.D. Finlayson , M.S. Drew , C. Lu . Entropy minimization for shadow removal. Int. J. Comput. Vis. , 1 , 35 - 57
25. 25)
  - K.H. Zou , A.J. O'Malley , L. Mauri . Receiver-operating characteristic analysis for evaluating diagnostic tests and predictive models. Circulation , 5
26. 26)
  - Y. Shor , D. Lischinski . The shadow meets the mask: pyramid-based shadow removal. Comput. Graph. Forum , 2 , 577 - 586
27. 27)
  - A. Cavallaro , E. Salvador , T. Ebrahimi . Shadow-aware object-based video processing. IEE Proc. Vis., Image Signal Process. , 398 - 406
28. 28)
  - Toth, D., Stuke, I., Wagner, A., Aach, T.: `Detection of moving shadows using mean shift clustering and a significance test', 17thInt. Conf. on Pattern Recognition (ICPR'04), 23–26 August 2004, Cambridge, UK, p. 260–263.
29. 29)
  - Schaffalitzky, F., Zisserman, A.: `Viewpoint invariant texture matching and wide baseline stereo', Proc. Eighth IEEE Int. Conf. on Computer Vision, 2001, 2, p. 636–643, ICCV 2001.
30. 30)
  - Leone, A., Distante, C., Buccolieri, F.: `A texture-based approach for shadow detection', IEEE Conf. on Advanced Video and Signal Based Surveillance, (AVSS 2005), September 2005, p. 371–376.
31. 31)
  - Drew, M.S., Chen, C., Finlayson, G.D.: `Sensor transforms for invariant image enhancement', Tenth Color Imaging Conf.: Color, Science, Systems and Applications Scottsdale, November 2002, Arizona, p. 325–329.
32. 32)
  - T. Gevers , A. Smeulders . Color-based object recognition. Pattern Recognit. , 3 , 453 - 464
33. 33)
  - He, Q., Chu, C.H.H.: `Texture-based shadow removal from a single color image', Proc. Fourth Int. Symp. on Advances in Visual Computing, Part II, 2008, p. 644–650.
34. 34)
  - D. Comaniciu , P. Meer . Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. , 5 , 603 - 619
35. 35)
  - Di, L., Xiangian, H.: `Texture analysis for shadow removing and tracking of vehicle in traffic monitoring system', Int. Symp. on Intelligent Information Technology Application Workshops, 2008, Los Alamitos, CA, p. 836–866.
36. 36)
  - Fredembach, C., Finlayson, G.D.: `Hamiltonian path based shadow removal', 16thBritish Machine Vision Conf., September 2005, Oxford, UK, p. 970–980.
37. 37)
  - Lu, C., Drew, M.S.: `Shadow segmentation and shadow-free chromaticity via Markov random fields', IS&T/SID 13th Color Imaging Conf., November 2005, Scottsdale Arizona.
38. 38)
  - Barnard, K., Finlayson, G.D.: `Shadow identification using color ratios', Proc. Eighth Color Imaging Conf., November 2000, Scottsdale, Arizona, USA, p. 97–101.
39. 39)
  - F. Bianconi , A. Fernández . Evaluation of the effects of Gabor filter parameters on texture classification. Pattern Recognit. , 12 , 3325 - 3335
40. 40)
  - T. Gevers , H. Stokman . Classifying color edges in video into shadow-geometry, highlight, or material transitions. IEEE Trans. Multimedia , 2 , 237 - 243
41. 41)
  - J.G. Daugman . Two-dimensional spectral analysis of cortical receptive field profiles. Vis. Res. , 10 , 847 - 856
42. 42)
  - J.J. Rubio , J. Pacheco . A stable online clustering fuzzy neural network for nonlinear systems identification. Neural Comput. Appl. , 6 , 633 - 641

Shadow identification for digital imagery using colour and texture cues

Shadow identification for digital imagery using colour and texture cues

Buy article PDF

Buy Knowledge Pack

Thank you

References

Related content