Automatic detection and inpainting of specular reflections for colposcopic images

Abstract

Specular reflections are not wanted in images because they can really reduce the performance of image processing techniques. This is particularly true for medical images and especially for colposcopic images. There are several methods in the literature allowing to extract specular reflections, but only a few methods can perform an automatic extraction. In this paper, we propose a new method to extract and to restore specularities automatically. This method is based on Dichromatic Reflection Model (DRM) and multi-resolution inpainting technique (MIT). The DRM approach will retrieve specularities while the MIT technique re-establish colors in bright zones using local information. The proposed method achieves good results and does not need any a priori knowledge. The efficiency of this method for colposcopic images has been demonstrated through a collaboration with the oncology center of Marrakech University Hospital.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • [1] Armstrong E. P., Prophylaxis of Cervical Cancer and Related Cervical Disease: A Review of the Cost-Effectiveness of Vaccination Against Oncogenic HPV Types, J. Manag. Care. Pharm., 2010, 217–230

  • [2] Spencer J., Cervical Cancer (Deadly Diseases and Epidemics), First Edition, Chelsea House Publications, 2007

  • [3] Markovic N., Markovic O., What Every Woman Should Know about Cervical Cancer, First Edition, Springer, 2008

  • [4] Ferris D., Modern Colposcopy Textbook and Atlas, Second edition, Kendall Hunt Publishing Company, Dubuque, Iowa, 2002

  • [5] Oh J., Hwang S., Lee J., Tavanapong W., Wong J., de Groen P. C., Informative Frame Classification for Endoscopy Video, Med. Image. Anal., 2007, 110–127

  • [6] Arnold M., Ghosh A., Ameling S., Lacey G., Automatic Segmentation and Inpainting of Specular Highlights for Endoscopic Imaging, EURASIP J. Iimage Video Process., 2010

  • [7] St Pierre C.A., Boisvert J., Grimard G., Cheriet F., Detection and Correction of Specular Reflections for Automatic Surgical Tool Segmentation in Thoracoscopic Images, Mach. Vision Appl., 2007, 22, 171–180 http://dx.doi.org/10.1007/s00138-007-0099-6

  • [8] Lange H., Automatic Glare Removal in Reflectance Imagery of the Uterine Cervix, In: SPIE Medical Imaging, (2005, San Diego, USA), SPIE, 2005, 240–250

  • [9] Zimmerman-Morene G., Greenspan H., Automatic Detection of Specular Reflections in Uterine Cervix Images, In: SPIE Medical Imaging, (February 2006, San Diego,USA), SPIE, 2006, 2037–2045

  • [10] Hervet E., Kardouchi M., Segmentation and Histogram Transform of Color Colposcopic Images, In: International Conference on Signal and Image Processing (ICISP), (June 2003, Agadir, Morocco), 2003, 412–420

  • [11] Shafer S.A., Using color to Separate Reflection Components, Color Research and Application, 1985, 210–218

  • [12] Agoston G.A., Color Theory and Its Application in Art and Design, Third Edition, Springer-Verlag, 1987

  • [13] Oliveira M., Bowen B., McKenna, R., Chang Y., Fast Digital Image Inpainting, In: International Conference on Visualization Imaging and Image Processing (VIIP), 2001, 261–266

  • [14] Shih T. K., Chang R. C, Digital Inpainting Survey and Multilayer Image Inpainting Algorithms, In: Information Technology and Applications (ICITA), (July 2005, Sydney, Australia), 2005, 15–24

Journal + Issues

Open Computer Science is an open access, peer-reviewed journal. The journal publishes research results in the following fields: algorithms and complexity theory, artificial intelligence, bioinformatics, networking and security systems,
programming languages, system and software engineering, and theoretical foundations of computer science.

Search