IJBTT

Diagnosis and Detection of Automatic Skin Burn Area Color Images Identification of Burn Area Depth in Color Images

	International Journal of Engineering Trends and Technology (IJETT)
	© 2017 by IJETT Journal
	Volume-48 Number-1
	Year of Publication : 2017
	Authors : B.Sabeena, Dr. P.Rajkumar
	DOI :  10.14445/22315381/IJETT-V48P209

Citation 

B.Sabeena, Dr. P.Rajkumar "Diagnosis and Detection of Automatic Skin Burn Area Color Images Identification of Burn Area Depth in Color Images", International Journal of Engineering Trends and Technology (IJETT), V48(1),48-54 June 2017. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group

Abstract
Skin image is in that the burned skin and non- burned images has to be classified. It is a deadly form of burning. Skin burn may appear as malignant or benign form. Skin cancer at its early stages can be cured. But when it is not recognized at its early stages, it begins to spread to other parts of the body and can be deadly. Benign Melanoma is simply appearance of moles on skin. A normal mole is usually an evenly colored brown, tan, or black spot on the skin. It can be either flat or raised. Skin burns are the deadly form of cancers in humans. If skin burns is detected at early stages, it can be cured completely. So an early detection of skin cancer can save the patients. Skin burns are of two types- Benign and Malignant Melanoma. Benign melanoma is not a deadly condition, but malignant melanoma is a deadly form. Both resemble same in appearance at the initial stages. Only an expert dermatologist can classify which one is benign and which one is malignant. The SVM based Classification methodology uses Image processing techniques. Main advantage of this computer based SVM classification is that patient does not need to go to hospitals and undergo various painful diagnosing techniques like Biopsy.

 References

[1] H. L. Haller, M. Giretzlehner, J. Dirnberger, R. Owen, "Medical documentation of burn injuries", in M. G. Jeschke, L.- P. Kamolz, F.Sjöberg, S. E. Wolf editors: Handbook of Burns vol. 1: Acute Burn Care, 2012, pp. 117-129.
[2] A. D. Jaskille, J. W. Shupp, M. H. Jordan, J. C. Jeng, "Critical review of burn depth assessment techniques: Part I. Historical review", J. Burn Care Res., vol. 30, no. 6, 2009, pp. 937-947.
[3] J. Hardwicke, R. Thomson, A. Bamford, and N. Moiemen, "A pilot evaluation study of high resolution digital thermal imaging in the assessment of burn depth", Burns, vol. 39, 2013, pp. 76-81.
[4] M. A. Calin, S. V. Parasca, R. Savastru, D. Manea, "Characterization of burns using hyperspectral imaging technique – A preliminary study". Burns, vol. 41, no. 1, 2015, pp. 118-124.
[5] W. Tylman, M. Janicki, and A. Napieralski, "Computer-aided Approach to Evaluation of Burn Wounds" in Proc. of the 18th International Conference Mixed Design of Integrated Circuits and Systems-MIXDES 2011, pp. 653-656.
[6] W. Tylman, M. Janicki, and A. Napieralski, "Automatisation of computer-aided burn wounds evaluation." in Proc. of the 19th International Conference Mixed Design of Integrated Circuits and Systems-MIXDES 2012, pp. 535-538.
[7] H. Wannous, S. Treuillet, and Y. Lucas, "Robust tissue classification for reproducible wound assessment in telemedicine environments," Journal of Electronic Imaging, vol. 19, no. 2, 2010, pp.023002-023002.
[8] M. Kolesnik, and A. Fexa, "Multi-dimensional color histograms for segmentation of wounds in images." in Proc. of Image Analysis and Recognition 2005, LNCS vol. 3656, pp. 1014-1022.
[9] R. Mukherjee, D. D. Manohar, D.K. Das, A. Achar, A. Mitra, and C. Chakraborty, "Automated tissue classification framework for reproducible chronic wound assessment". BioMed research international, 2014.
[10] K. Wantanajittikul, N. Theera-Umpon, S. Auephanwiriyakul, and T. Koanantakool, "Automatic segmentation and degree identification in burn color images," in Proc. of International Conference on Biomedical Engineering (BMEiCON), 2011, pp.169-173.

Keywords
Skin lesion, Melanoma, Features detection ,Classification, Segmentation.