Алгоритмы сегментации, основанные на вейвлет-преобразовании и их реализация в процессоре цифровой обработки сигналов / Wavelet Transform Segmentation Techniques Implemented on Digital Signal Processor

Пономарев В. И. / Ponomaryov, V. I.
National Polytechnic Institute of Mexico, Mexico-city / RUS National Polytechnic Institute of Mexico, Mexico-city
Castillejos H. / Castillejos, H.
National Polytechnic Institute of Mexico, Mexico-city / RUS National Polytechnic Institute of Mexico, Mexico-city
Duchen G. / Duchen, G.
National Polytechnic Institute of Mexico, Mexico-city / RUS National Polytechnic Institute of Mexico, Mexico-city
Выпуск в базе РИНЦ
Пономарев В. И., Castillejos H., Duchen G. Алгоритмы сегментации, основанные на вейвлет-преобразовании и их реализация в процессоре цифровой обработки сигналов // Физические основы приборостроения. 2012. Т. 1. № 3(4). С. 55–67. DOI: 10.25210/jfop-1203-055067
Ponomaryov, V. I., Castillejos, H., Duchen, G. Wavelet Transform Segmentation Techniques Implemented on Digital Signal Processor // Physical Bases of Instrumentation. 2012. Vol. 1. No. 3(4). P. 55–67. DOI: 10.25210/jfop-1203-055067

Аннотация: Рассмотрен новый подход в сегментации дермоско- пических изображений, использующий вейвлет-пре- образования. Разработанные алгоритмы (W-FCM, W-CPSFCM и WK-Means) в результате ROC анализа показали значительно лучшие результаты в процессе сегментации изображений, чем известные. Предло- женная W-CPSFCM процедура позволяет найти чис- ло кластеров без вмешательства специалиста. Пред- ложенные и лучшие из известных алгоритмы реали- зованы а цифровом процессоре DSP TMS320DM642.
Abstract: A novel approach to segmentation of dermoscopic images in wavelet transform space is presented. The designed frameworks (W-FCM, W-CPSFCM and WK-Means) according to ROC curve analysis demonstrate sufficiently good results. The novel W-CPSFCM algorithm estimates a number of clusters in automatic mode without the intervention of a specialist. The implementation of the proposed segmentation algorithms on the Texas Instruments DSP TMS320DM642 demonstrates possible real time processing mode for images of different nature.
Ключевые слова: вейвлеты, дермоскопия, ROC характеристики, цифровая обработка сигналов и изображений, segmentation algorithms, wavelets, dermoscopic images, ROC characteristics, digital image processing, вейвлеты

Литература / References
  1. Vestergaard, M., Macaskill, P., Holt, P., and Menzies, S. Dermoscopy Compared with Naked Eye Examination for the Diagnosis of Primary Melanoma: a Metaanalysis of Studies Performed in a Clinical Setting // British Journal of Dermatology. 2008. Vol. 159. No. 3. P. 669–676.
  2. Argenziano, G., Fabbrocini, G., Carli, P. et al. Epiluminescence Microscopy for the Diagnosis of Doubtful Melanocytic Skin Lesions. Comparison of the Abcd Rule of Dermatoscopy and a New 7-Point Checklist Based on Pattern Analysis // Archives of Dermatology. 1998. Vol. 134, No. 12. 156370. Doi; 100.1001/Archderm.134.12.1563.
  3. Ascierto, P., Palmieri, G., Celentano, E. et al. Sensitivity and Specificity of Epiluminescence Microscopy: Evaluation on a Sample of 2731 Excised Cutaneous Pigmented Lesions // British Journal of Dermatology. Vol.142. No. 5. P. 893.
  4. Celebi, M., Iyatomi, H., Schaefer, G., and Stoecker, W. Lesion Border Detection in Dermoscopy Images // Computerized Medical Imaging and Graphics. 2009, Vol. 33. No. 2. P. 148–153.
  5. Silveira, M., Nascimento, J., Marques, J. et al. Comparison of Segmentation Methods for Melanoma Diagnosis in Dermoscopy Images// IEEE Journal on Selected Topics in Signal Processing. 2009. Vol. 3. No. 1. P. 35–45.
  6. Celebi, M., Kingravi, H., Iyatomi, H. et al. Border Detection in Dermoscopy Images Using Statistical Region Merging// Skin Research and Technology. 2008. Vol. 14. No. 3. P. 347–353.
  7. Zadeh, L. Fuzzy Approach to Color Region Extraction //Information and Control, 1965. Vol. 8. No. 3. P. 338–353.
  8. Celebi, M., Kingravi, H., Uddin, B. et al. A Methodological Approach to the Classification of Dermoscopy Images // Computerized Medical Imaging and Graphics. 2007. Vol. 31. No. 6. P. 362–373.
  9. Abbas, Q., Celebi, M., and García, I. Hair Removal Methods: a Comparative Study for Dermoscopy Images //Biomedical Signal Processing and Control. 2011. Vol. 6. No. 4. P. 395–404.
  10. Abbas, Q., Celebi, M., Fondon-Garcia, I., and Rashid, M. Lesion Border Detection in Dermoscopy Images Using Dynamic Programming // Skin Research and Technology, 2011. Vol. 17. P. 91–100.
  11. Bello, M. A. Combined Markov Random Field and Wave-Packet Transform-Based Approach for Image Segmentation //IEEE Trans. Image Processing. 1994. Vol. 3. No. 6.P. 834–846.
  12. Strickland, R. and Hahn, H. Wavelet Transform Matched Filters for the Detection and Classification of Microcalcifications in Mammography // Proc. Of the Int. Conference on Image Processing, Washington, D. C., USA. 1995. Vol. 1. P. 422–425.
  13. Zhang, X. and Desai, M. Segmentation of Bright Targets Using Wavelets and Adaptive Thresholding // IEEE Trans. Image Processing. 2002. Vol. 10. No. 7. P. 1020–1030.
  14. Mallat, S. Wavelet Tour of Signal Processing. SanDiego, CA: Academic Press, 1998.
  15. Kravchenko, V., Meana, H., and Ponomaryov, V. Adaptive Digital Processing of Multidimensional Signals with Applications. Fizmatlit Edit. Moscow, 2009 (Available in http://www.posgrados.esimecu.ipn.mx/).
  16. The International Atlas of Dermoscopy and Dermatoscopy. www.dermoscopyatlas.com
  17. Alpert, S., Galun, M., Basri, R., and Brandt, A. Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration // Proc. Of the IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN, USA, July 2007, P. 1–8.
  18. Joel, G., Philippe, S., David, G. et al. Validation of Segmentation Techniques for Digital Dermoscopy // Skin Research and Technology. 2002. Vol. 8. No. 4. P. 240–249.
  19. Texas Instruments. TMS320DM642 Evaluation Module with TVP Video Encoders, Technical Reference 507345–0001 Rev. B, December 2004.
  20. Shen, E. Code Composer Studio Texas Instruments //8th Texas Instruments Developer Conference, India, Bangalore, 30 Nov-1Dec. 2005.