Treatment for burn injuries depends highly on the type of severity of the burn. Thus, identification of the severity of burns plays a very important role in providing proper treatment to patients suffering from skin burns. With digitization of images using image processing, the treatment becomes easier by properly classifying these skin burn images and identifying the severity of these burns using the some scientific techniques. The color of the skin burn images are represented by Red Green Blue (RGB) histogram. Lot of research has been done in using the RGB histogram to develop different algorithms and methods of classification and also to assess the severity. However, because of the drawbacks in each of the algorithms in one or the other way, there is no single method or algorithm that fits in all the situations. As an alternative, the statistical properties of histograms can be used to assess the severity of burn images by assessing the reliability of burn images, which in turn, helps in providing proper treatment to the patients suffering from burns. The RGB histogram of burn images can be used as a basis for this. The RGB band of burn images have Gaussian distribution and this information can be used in determining the reliability and hence the severity of the burn wounds. Herein, it is intended to assess and analyze the reliability of skin burn images through this Gaussian distribution, using statistical procedure. Some past data obtained through clinical observations have been used for obtaining the same.

Gaussian distribution, Intensity histogram, Reliability analysis, RGB classification, Skin burn

[1] Practical Handbook of Burns Management For National Programme for Prevention, Management and Rehabilitation of Burn Injuries (NPPMRBI) under Ministry of Health and Family Welfare Government of India, pp 17-18, 2015.
[2] Nikoletta Bassiou, Constantine Kotropoulos, “Color image histogram equalization by absolute discounting back-of”, Computer Vision and Image Understanding 107, pp 108–122, 2007.
[3] Hong-yan Li, “Skin Burns Degree Determined by Computer Image Processing Method”, In the proceedings of 2012 International Conference on Medical Physics and Biomedical Engineering, Elsevier Physics Procedia 33, pp 758 – 764, 2012.
[4] Malini Suvarna, Sivakumar, Dr. Kamal Kumar, U C Niranjan, “Diagnosis of Burn Images using Template Matching, k-Nearest Neighbor and Artificial Neural Network”, International Journal of Image Processing (IJIP), Vol. 7, No. 2, pp 191- 202, 2013.
[5] Malini Suvarna, Sivakumar, U C Niranjan, “Classification Methods of Skin Burn Images”, International Journal of Computer Science & Information Technology (IJCSIT) Vol. 5, No. 1, pp 109-118, 2013.
[6] Begon˜a Acha Carmen Serrano Jose´ I. Acha, Laura M. Roa, “Segmentation and classification of burn images by color and texture information”, Journal of Biomedical Optics Vol. 10, No. 3, pp 1-11, 2005.
[7] Hai Son Tran, Thai Hoang Le, Thuy Thanh Nguyen, “The Degree of Skin Burns Images Recognition using Convolutional Neural Network”, Indian Journal of Science and Technology, Vol. 9, No. 45, pp 1-6, 2016.
[8] T.S. Hai, L.M. Triet , L.H. Thai , N.T. Thuy, “Real Time Burning Image Classification Using Support Vector Machine”, EAI Endorsed Transactions on Context-aware Systems and Applications, Vol. 4, No. 12, pp 1-7, 2017.