REGION HOMOGENEITY IN THE LOGARITHMIC IMAGE PROCESSING FRAMEWORK: APPLICATION TO REGION GROWING ALGORITHMS
DOI:
https://doi.org/10.5566/ias.2038Keywords:
Homogeneity of an image region, Image segmentation, Logarithmic Image Processing, Region Growing, Robustness to lighting changesAbstract
In order to create an image segmentation method robust to lighting changes, two novel homogeneity criteria of an image region were studied. Both were defined using the Logarithmic Image Processing (LIP) framework whose laws model lighting changes. The first criterion estimates the LIP-additive homogeneity and is based on the LIP-additive law. It is theoretically insensitive to lighting changes caused by variations of the camera exposure-time or source intensity. The second, the LIP-multiplicative homogeneity criterion, is based on the LIP-multiplicative law and is insensitive to changes due to variations of the object thickness or opacity. Each criterion is then applied in Revol and Jourlin’s (1997) region growing method which is based on the homogeneity of an image region. The region growing method becomes therefore robust to the lighting changes specific to each criterion. Experiments on simulated and on real images presenting lighting variations prove the robustness of the criteria to those variations. Compared to a state-of the art method based on the image component-tree, ours is more robust. These results open the way to numerous applications where the lighting is uncontrolled or partially controlled.
References
Beucher S, Meyer F (1992). The morphological approach to segmentation: The watershed transformation, vol. 34 of Optical Engineering, chap. 12. Marcel Dekker, New York, 433–481.
Brailean J, Sullivan B, Chen C, Giger M (1991). Evaluating the EM algorithm for image processing using a human visual fidelity criterion. In: Int Conf Acoust Spee, vol. 4.
Butterfly (2010). Butterfly image from the YFCC100M dataset. http://www.flickr.com/photos/45563311@N04/4350683057/. Licence CC BY-NC-SA 2.0.
Carre M, Jourlin M (2014). LIP operators: Simulating exposure variations to perform algorithms independent of lighting conditions. In: 2014 International Conference on Multimedia
Computing and Syst. (ICMCS). IEEE.
Chen T, Yin W, Zhou XS, Comaniciu D, Huang TS (2006). Total variation models for variable lighting face recognition. IEEE T Pattern Anal 28:1519–24.
Cord A, Bach F, Jeulin D (2010). Texture classification by statistical learning from morphological image processing: application to metallic surfaces. J Microsc Oxford UK 239:159–66.
Deshayes V, Guilbert P, Jourlin M (2015). How simulating exposure time variations in the LIP model. Application: moving objects acquisition. In: Acta Stereol., Proc. 14th ICSIA.
Elad M, Kimmel R, Shaked D, Keshet R (2003). Reduced complexity retinex algorithm via the variational approach. J Vis Commun Image R 14:369 – 388.
Foresti GL, Micheloni C, Snidaro L, Remagnino P, Ellis T (2005). Active video-based surveillance system: the low-level image and video processing techniques needed for implementation. IEEE Signal Proc Mag 22:25–37.
GDXray (2015). Database of x-ray images. http://dmery.ing.puc.cl/index.php/material/gdxray/. Set of baggage images no. B0063, image no. 3, 10, 11. Accessed
th October 2018.
Hautière N, Aubert D, Jourlin M (2006). Measurement of local contrast in images, application to the measurement of visibility distance through use of an onboard camera. Trait Signal 23:145–58.
Jourlin M (2016). Logarithmic Image Processing: Theory and Applications, vol. 195 of Adv Imag Elect Phys. Elsevier Science.
Jourlin M, Carré M, Breugnot J, Bouabdellah M (2012). Chapter7-LogarithmicImageProcessing: Additive contrast, multiplicative contrast, and associated metrics. In: Hawkes PW, ed., Adv Imag Elect Phys, vol. 171. Elsevier, 357 – 406.
Jourlin M, Couka E, Abdallah B, Corvo J, Breugnot J (2014). Asplünd’s metric defined in the Logarithmic Image Processing (LIP) framework: A new way to perform double-sided image probing for non-linear grayscale pattern matching. Pattern
Recogn 47:2908 – 2924.
Jourlin M, Noyel G (2018). Homogeneity of a region in the Logarithmic Image Processing framework: application to region growing algorithms. In: Willot F, Forest S, eds., Physics and Mechanics of Random Structures: from Morphology to Material Properties. Ile d’Oléron, France: Presse des Mines.
https://hal.archives-ouvertes.fr/hal-01822522.
Jourlin M, Pinoli J (1988). A model for logarithmic image processing. J Microsc Oxford UK 149:21–35.
Jourlin M, Pinoli J (2001). Logarithmic image processing: The mathematical and physical framework for the representation and processing of transmitted images. In: Hawkes PW, ed., Adv Imag Elect Phys, vol. 115. Elsevier, 129 – 196.
Lu L, Zheng Y, Carneiro G, Yang L, eds. (2017). Deep Learning and Convolutional Neural Networks for Medical Image Computing - Precision Medicine, High Performance and Large-Scale Datasets. Advances in Computer Vision and Pattern
Recognition. Springer.
Matheron G (1967). Eléments pour une théorie des milieux poreux. Masson, Paris.
Mery D, Riffo V, Zscherpel U, Mondragón G, Lillo I, Zuccar I, Lobel H, Carrasco M (2015). GDXray: The database of X-ray images for nondestructive testing. J Nondestruct Eval 34:42.
Minkowski H (1903). Volumen und oberfläche. Mathematische Annalen 57:447–95.
Monasse P, Guichard F (2000). Fast computation of a contrast-invariant image representation. IEEE T Image Process 9:860–72.
Naegel B, Passat N (2014). Interactive Segmentation Based on Component-trees. Image Processing On Line 4:89–97.
Najman L, Talbot H (2013). Mathematical Morphology: From Theory to Applications. Wiley-Blackwell, 1st ed.
Noyel G (2011). Method of monitoring the appearance of the surface of a tire. https://patentscope.wipo.int/search/en/WO2011131410. International PCT patent WO2011131410 (A1). Also published as: US9002093 (B2), FR2959046 (B1), JP5779232 (B2), EP2561479 (A1), CN102844791 (B), BR112012025402 (A2).
Noyel G, Angulo J, Jeulin D (2007). Morphological segmentation of hyperspectral images. Image Anal Stereol 26:101–9.
Noyel G, Angulo J, Jeulin D (2010). A new spatio-spectral morphological segmentation for multi-spectral remote-sensing images. Int J Remote Sens 31:5895–920.
Noyel G, Angulo J, Jeulin D, Balvay D, Cuenod CA (2014). Multivariate mathematical morphology for DCE-MRI image analysis in angiogenesis studies. Image Anal Stereol 34:1–25.
Noyel G, Jeulin D, Parra-Denis E, Bilodeau M (2013). Method of checking the appearance of the surface of a tyre. https://patentscope.wipo.int/search/en/WO2013045593.
International PCT patent WO2013045593 (A1), also published as US9189841 (B2), FR2980735 (B1), EP2761587 (A1), CN103843034 (A).
Noyel G, Jourlin M (2015). Asplund’s metric defined in the logarithmic image processing (LIP) framework for colour and multivariate images. In: 2015 IEEE Int. Conf. on Image Process.
Noyel G, Jourlin M (2017a). Double-sided probing by map of Asplund’s distances using logarithmic image processing in the framework of mathematical morphology. In: Lect Notes Comput Sc. Cham: Springer Int. Publishing.
Noyel G, Jourlin M (2017b). Spatio-colour Asplünd’s metric and logarithmic image processing for colour images (LIPC). In: Lect Notes Comput Sc, vol. 10125. Cham: Springer Int. Publishing.
Noyel G, Thomas R, Bhakta G, Crowder A, Owens D, Boyle P (2017). Superimposition of eye fundus images for longitudinal analysis from large public health databases. Biomed Phys Eng Express 3:045015.
Parra-Denis E, Bilodeau M, Jeulin D (2011). Multistep detection of oriented structure in complex textures. In: International Congress for Stereology. Beijing, China.
Passat N, Naegel B, Rousseau F, Koob M, Dietemann JL (2011). Interactive segmentation based on component-trees. Pattern Recogn 44:2539 – 2554. Semi-Supervised Learning for Visual Content Analysis and Understanding.
Ramaiah NP, Ijjina EP, Mohan CK (2015). Illumination invariant face recognition using convolutional neural networks. In: 2015 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES).
Revol C, Jourlin M (1997). A new minimum variance region growing algorithm for image segmentation. Pattern Recogn Lett 18:249 – 258.
Salembier P, Oliveras A, Garrido L (1998). Antiextensive connected operators for image and sequence processing. IEEE T Image Process 7:555–70.
Serra J, Cressie N (1982). Image analysis and mathematicalmorphology,vol.1. AcademicPress, London.
Shah JH, Sharif M, Raza M, Murtaza M, Saeed-Ur-Rehman (2015). Robust face recognition technique under varying illumination. J Appl Res Technol 13:97 – 105.
Thomee B, Shamma DA, Friedland G, Elizalde B, Ni K, Poland D, Borth D, Li LJ (2016). YFCC100M: The new data in multimedia research. Commun ACM 59:64–73.
Wang H, Li SZ, Wang Y (2004). Face recognition under varying lighting conditions using self quotient image. In: Sixth IEEE International Conference on Automatic Face and Gesture
Recognition, 2004. Proceedings.
Xu Y, Géraud T, Najman L (2016). Connected filtering on tree-based shape-spaces. IEEE T Pattern Anal 38:1126–40.
Yu H, Fan J (2017). A novel segmentation method for uneven lighting image with noise injection based on non-local spatial information and intuitionistic fuzzy entropy. EURASIP J Adv Sig Pr 2017:74.
Zhang W, Zhao X, Morvan J, Chen L (2019). Improving shadow suppression for illumination robust face recognition. IEEE T Pattern Anal 41:611–24.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2019 Image Analysis & Stereology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
