A new approach to color person image indexing and retrieval

• Autorzy: Muselet D. , Macaire L. , Postaire J. G.
• Języki publikacji: EN

Abstrakty

EN

In the context if image indexing for the purpose of retrieval, colored object recognition methods tend to fail when the illumination of the objects varies from an image to another. A new approach to indexing image of persons is proposed, which copes with the variations of the lighting conditions. We assume that illumination changes can be described using a simple linear transform. For comparing two images, we transform the color of the target one according to the colors of the query one by means of an original color histogram specification based on color invariant evaluation. For the retrieval purpose, we evaluate invariant color signatures of the query image and the transformed target image through the use of color co-occurrence matrices. Tests on real images are very encouraging, with substantially better results than those obtained with other well--established indexing and retrieval schmes.

Słowa kluczowe

EN

color; illumination; invariant features; indexing; highlights; shadows; color co--occurrence matrices

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2002
• Tom: Vol. 11, No. 2/3
• Strony: 257--283
• Opis fizyczny: Bibliogr. 24 poz.

Twórcy

autor

Muselet D.

• Laboratoire d"Automatique I3 D Universite des Sciences et Technologies de Lille, Cite Scientifique - Batiment P2-59655, Villeneuve d"Ascq - France

autor

Macaire L.

• Laboratoire d"Automatique I3 D Universite des Sciences et Technologies de Lille, Cite Scientifique - Batiment P2-59655, Villeneuve d"Ascq - France

autor

Postaire J. G.

• Laboratoire d"Automatique I3 D Universite des Sciences et Technologies de Lille, Cite Scientifique - Batiment P2-59655, Villeneuve d"Ascq - France

Bibliografia

• [1] Wyszecki G., Stiles W. S.: Color Science: Concept and Methods, Quantitative Data and Formulaes. John Wiley and Sons, NY. 1982.
• [2] Gonzalez R. C., Wintz P.: Digital Image Processing. Addison Wesley. 1987.
• [3] Di Zenzo S.: A note on the gradient of a multi-image. CVGIP, 33(1) , 116-125. 1986.
• [4] Engelson S. P. McDermott D. V.: Image signatures for place recognition and map construction. SPIE Sensor Fusion, IV, 282-293. 1991.
• [5] Swain M. J., Ballard D. H.: Color indexing. Int. J. of Computer Vision , 7(1), 11-32 . 1991.
• [6] Funt B. V. Finlayson G. D.: Color constant color indexing. IEEE Trans. on PAMI, 17(5), 522-529. 1995.
• [7] Kankanhalli M. S., Mehtre B. M., Wu J. K.: Cluster-based color matching for image retrieval. PR, 29(4), 701-708. 1996.
• [8] Nastar C., Ayache N.: Frequency-based nonrigid motion analysis: application to four dimensional medical images. IEEE Trans. on PAMI, 18(11), 1067-1079. 1996.
• [9] Huang J., Ravi Kumar S., Mitra M., Zhu W., Zabih R.: Image indexing using color correlogram. IEEE Conf. CVPR, 762-768. 1997.
• [10] Sharma G., Trussell H. J.: Digital color imaging. IEEE Trans. on Image Processing, 6(7), 901 -932. 1997.
• [1l] Vannoorenberghe P., Motamed C., Blosseville J.-M., Postaire J.-G.: Automatic pedestrian recognition using real-time motion analysis. ICIAP, 2, 493-500. 1997.
• [12] Drew M. S., Wei J., Li Z. N.: On illumination invariance in color object recognition. PR, 31(8), 1077-1087. 1998.
• [13] Gevers T., Smeulders A. W. M.: Content-based image retrieval by viewpoint-invariant color indexing. Image and Vision Computing, 17, 475-488. 1999.
• [14] Gevers T., Smeulders A. W. M.: Color-based object, recognition. PR, 32, 453-464. 1999.
• [15] Park I. K., Yun I. D., Lee S. U.: Color image retrieval using hybrid graph representation. Image and Vision Computing, 17, 465-474. 1999.
• [16] Pass G., Zabih R.: Comparing images using joint histograms. Multimedia Systems, 7(3), 234-240. 2000.
• [17] Botte-Lecocq C., Gillet, A., Macaire L., Postaire J. G.: Color image segmentation based on fuzzy mathematical morphology. IEEE Int. Conf. on Image Processing, Vancouver, 3, 340-343. 2000.
• [18] Schettini R., Ciocca G., Zuffi S.: Color in databases: indexation and similarity. Int. Conf. on Color in Graphics and Image Processing, Saint-Etienne, 1, 244-249. 2000.
• [19] Smeulders A. W. M. Gevers T.: Pictoseek: combining color and shape invariant features for image retrieval. IEEE Trans. on Image Proccsing, 9(l), 102-119. 2000.
• [20] Vandenbroucke N., Macaire L., Postaire J. G.: Unsupervised color texture features extraction and selection for soccer images segmentation. IEEE Int. Conf. on Image Processing, Vancouver, 2, 800-803. 2000.
• [21] Adjehro D. A., Lee M. C.: On ratio-based color indexing. IEEE Trans. on Image Processing, 10(1), 36-48. 2001.
• [22] Cinque L., Ciocca G., Levialdi S., Pellicano A., Schettini R.: Color-based image retrieval using spatial-chromatic histograms. Image and Vision Computing, 19, 979-986. 2001.
• [23] Fuertes J. M., Lucena M., Perez de la Blanca N., Chamorro-Martinez J.: A scheme of colour image retrieval from databases. PRL, 22, 323-337. 2001.
• [24] Kim J. Y., Kim C. Y., Seo Y. S., Kweon I. S.: Color indexing using chromatic invariant. PR, 34, 1189-1197. 2001.