Invariants couleur dédiés à la transparence de l'encre. Application à la segmentation de marquages

Invariants couleur dédiés à la transparence de l'encre. Application à la segmentation de marquages

Color invariants for ink transparency. Application to the segmentation of markings

Michèle Gouiffès Christophe Collewet  Christine Fernandez-Maloigne  Alain Trémeau  Philippe Loisel 

CEMAGREF, Rennes, unité TERE, équipe PAIC, 17 avenue de Cucillé, CS 64-427, 35044 Rennes cedex

Université de Poitiers, laboratoire SIC-CNRS 6615

Université Jean Monnet, St Etienne, laboratoire LIGIV

Corresponding Author Email: 
michele.gouiffes@cemagref.fr
Page: 
439-452
|
Received: 
15 June 2004
|
Accepted: 
N/A
|
Published: 
31 October 2004
| Citation

OPEN ACCESS

Abstract: 

The ink reflectance strongly depends on its opacity and on the color of the body on which it is printed. In this paper, we focus on this problem, which is linked to ink transparency. We propose some attributes, which are invariant to the background color and to the quantity of ink printed. Some experimental results prove the theorical results. Then, these attributes are used to segment inked markings. Finally, the proposed approach is used in an application of traceability control of meat products, where an identifier has to be detected on hams.

Résumé

La réflectance de l'encre dépend fortement de son opacité et de la couleur du support sur lequel elle est imprimée. Dans cet article, nous étudions tout particulièrement ce problème, qui est lié à la notion de transparence. Nous proposons des caractéristiques invariantes à la couleur du support, mais également des attributs invariants par rapport à la quantité d'encre imprimée. Des résultats expérimentaux valident les résultats théoriques obtenus. Ces attributs de constance colorimétrique sont exploités ensuite dans le cadre d'un algorithme de segmentation de marquages effectués à l'encre. Finalement, l'approche proposée est appliquée dans le cadre de la traçabilité de la viande porcine, où un identifiant doit être détecté sur des jambons.

Keywords: 

Image processing, color invariance, transparency, color segmentation, ink, traceability

Mots clés

Traitement d'images, invariance couleur, transparence, segmentation couleur, encre, traçabilité

1. Introduction
2. Étude De La Couleur De L'encre Imprimée Sur Un Support De Couleur Uniforme
3. Application À La Segmentation D'un Marquage À L'encre
4. Application À La Segmentation D'un Identifiant Sur Un Jambon
5. Conclusion
  References

[Bezdek] J.C. BEZDEK, R. EHRLICH, and W. FULL. "FCM: The fuzzy c-mean clustering algorithm." Computers, and Geosciences, 10:191-203, 1984.

[Beck] J. BECK, K. PRAZDNY, and R. IVRY. "The perception of transparency with achromatic colors." Perception and psychophysics, 35(10):407-422, 1984.

[Braddick] O.J. BRADDICK, K.A. WISHART, and W. CURRAN. "Directional performance in motion transparency." Vision Research, 42(10):1237-1248, 2002.

[Carron] T. CARRON. Segmentation d'images couleur dans la base Teinte-Luminance-Saturation : approche numérique et symbolique. PhD thesis, LAMII, - Université de Savoie, Annecy, France, decembre 1995.

[Celenk] M. CELENK. "A color clustering technique for image segmentation". Computer Vision Graphics Image Process, 52:145-170, 1990.

[Chen] T.Q. CHEN, Y. LU. "Color image segmentation - an innovative approach". Pattern Recognition, 35(2):395-405, February 2002.

[Colantoni] P. COLANTONI. "Contribution des structures de données à la segmentation d'images couleur. élaboration d'un outil d'infographie textile." Thèse de doctorat de Université Jean Monnet, St Etienne, Novembre 1998

[DaPos] O. DA POS. "Trasparenze". Padua, Icone, 1989.

[Deriche] R. DERICHE. "Using canny's criteria to derive a recursively implemented optimal edge detector". Internal Journal of Computer Vision, 1(2):167-187, 1987.

[DZmura97] M. D'ZMURA, P. COLANTONI, K. KNOBLAUCH, B. LAGET. "Color transparency". Perception, 26:471-492, 1997.

[DZmura00] M. D'ZMURA, O. RINNER, K.R. GEGENFURTNER. "The colors seen behind transparent filters". Perception, 29:911-926, 2000.

[Faul] F. FAUL and V. EKROLL. "Psychophysical model of chromatic perceptual transparency based on subtractive color mixture." Journal of the optical Society of America A, 19:1084-1095, 2002.

[Ferri] F. FERRI, E. VIDAL. "Colour image segmentation and labeling through multiedit condensing". Pattern Recognition Letters, 13(8):561-568, 1992.

[Fontaine] M. FONTAINE. Segmentation non supervisée d'images couleur par analyse de la connexité des pixels. PhD thesis, Université de Lille I, Décembre 2001.

[Forgy] E. FORGY. "Cluster analysis of multivariate data : efficency versus interpretability of classification". Biometrics, 21:768-780, 1965.

[Gevers90] T. GEVERS, F.C.A. GROEN. "Segmentation of color images". In Proceedings of 7th Scandinavian Conference on Image Analysis, 1991.

[Gevers94] T. GEVERS, V.K. KAJCOVSKI. "Image segmentation by directed region subdivision". In International Conférence on Pattern Recognition, pages A : 342-346, 1994.

[Gouiffès] M. GOUIFFÈS, P. MARTY-MAHÉ, C. FERNANDEZ, A. TRÉMEAU, P.LOISEL, D. BROSSARD. "Comparaison de deux méthodes de segmentation appliquées à l'agro-alimentaire". In 14e congrès AFRIF-RFIA. Reconnaissance de Formes et Intelligence Artificielle, Toulouse, France, Janvier 2004.

[Hartigan] J.A. HARTIGAN. Clustering algorithms. John Wiley and Sons, 1975.

[Horowitz] S.L. HOROWITZ, T. PAVLIDIS. "Picture segmentation by a directed split-and-merge procedure". In Proceedings of the 2nd International Joint Conférence on Pattern Recognition, pages 424-433, 1974.

[Imelinska] C. IMELINSKA, M.S. DOWNES, W. YUAN. "Semiautomated color segmentation of anatomical tissue". Computerized Medical Imaging and Graphics, 3(24):173-180, May-June 2000.

[Koonty] W. KOONTY, P.M. NARENDA, F. FUKUNAYA. "A graph theoric approach to non-parametric cluster analysis". IEEE Trans. on Computer, 25(9):961-973, 1976.

[Lin] X. LIN, S. CHEN. "Color image segmentation using modified HSI system for road following". Proc. IEEE Conf on Robotics and Automation, pages 1998-2003, April 1991.

[Marfil] R. MARFIL, J.A. RODRÍGUEZ, A. BANDERA, and F. SANDOVAL."Bounded irregular pyramid : a new structure for image segmentation." Pattern Recognition, 37:623-626, 2004.

[Matsuoka] H. MATSUOKA, T. TAKEUCHI, H. KITAZAWA, and A. ONOZAWA."Representation of pseudo interreflection and transparency by considering characteristic of human vision." Computer graphics forum, 21(3):503-, 2002.

[Metelli] F. METELLI."An algebric development of the theory of perceptual transparency." Ergonomics, 13:59-66, 1970.

[Moghaddamzadeh] A. MOGHADDAMZADEH, N. BOURBAKIS. "A fuzzy region growing approach for segmentation of color images". Pattern Recognition, 6(30):867-881, June 1997.

[Ohlander] R. OHLANDER, K. PRICE, D.R. REDDY. "Picture segmentation using a recursive region splitting method". Computer Graphics and Image Processing, 8:313-333, 1978.

[Otha] Y.I. OTHA, T. KANADE, T. SAKAI. "Color information for region segmentation". Computer Graphics and Image Processing, 13:222-241, 1980.

[Panjwani] D.K. PANJWANI, G. HEALEY. "Markov random field models for unsupervised segmentation of textured color images". IEEE Trans. on Patterrn Analysis and Machine Intelligence, 17(10):939-954, 1995.

[Raffy] G. RAFFY. Vision numérique couleur appliquée à l'évaluation de la qualité de carcasses de dinde. PhD thesis, Université Blaise Pascal, Clermont Ferrand, France, mars 1999. Cemagref de Rennes.

[Schettini] R. SCHETTINI. "A segmentation algorithm for color images". Pattern Recognition Letters, 14:499-506, 1993.

[Shen&Castan] J. SHEN, S. CASTAN. "An optimal linear operator for edge detection". In Conference on Vision and Pattern Recognition, USA, Juin 1986.

[Takahashi] K. TAKAHASHI, H. NAKATANI, K. ABE. "Color image segmentation using isodata clustering method". Asian Conference on Computer Vision 95, 1:523-527, 1995.

[Tominaga86] S. TOMINAGA. "Color image segmentation using three perceptual attributes". IEEE Computer Vision and Pattern Recognition, pages 628-630, 22-26 June 1986.

[Tominaga92] S. TOMINAGA. "Color classification of natural color images". Color Research and Application, 17(4):230-239, 1992.

[Trémeau] A. TRÉMEAU, N. BOREL. "A region growing and merging algorithm to color segmentation". Pattern Recognition, 30(10):1799-1800, october 1997.

[Vandenbroucke] N. VANDENBROUCKE, L. MACAIRE, and J-G. POSTAIRE."Color image segmentation by pixel classification in an adapted hybrid color space. application to soccer image analysis." Computer Vision and Image Understanding, 90:190-216, 2004.

[DiZenzo] S. DI ZENZO. "A note on the gradient of multiimage". Computer Vision Graphics Image Process, 33:116-125, 1986.

[Zucker] S. ZUCKER. "Region growing : childhood and adolescence". Computer Graphics and Image Processing, 5:382-399, 1976.