Artificial Intelligence Based Skin Classification Using GMM
- 125 Downloads
This study describes the usage of neural community based on the texture evaluation of pores and skin a variety of similarities in their signs, inclusive of Measles (rubella), German measles (rubella), and Chickenpox etc. In fashionable, these illnesses have similarities in sample of infection and symptoms along with redness and rash. Various skin problems have similar symptoms. For example, in German measles (rubella), Chicken pox and Measles (rubella) a similarity can be observed in skin rashes and redness. The prognosis of skin problems take a long time as the patient’s previous medical records, physical examination report and the respective laboratory diagnostic reports have to be studied. The recognition and diagnosis get tough due to the complexity involved. Subsequently, a computer aided analysis and recognition gadget would be handy in such cases. Computer algorithm steps include image processing, picture characteristic extraction and categorize facts with the help of a classifier with Artificial Neural Network (ANN). The ANN can analyze the patterns of symptoms of a particular disease and present faster prognosis and reputation than a human doctor. For this reason, the patients can undergo the treatment for the pores and skin problems based totally on the symptoms detected.
KeywordsGaussian mixture model classifier (GMM) Pre-processing Dominant rotated local binary pattern (DRLBP) Gray level co-occurrence matrix (GLCM) Super pixel segmentation Probabilistic neural network (PNN) classification
Compliance with ethical standards
Conflict of interest
The authors have no conflict of interest.
Animals were not involved. This article does not contain any studies with human participants performed by any of the authors. This article does not contain any studies with human participants or animals performed by any of the authors.
- 1.Bono, A., Tomatis, S., and Bartoli, C., The ABCD machine of melanoma detection: A spectrophotometric evaluation of the asymmetry, border, shade, and measurement. Most Cancers 85(1):72–77, 1999.Google Scholar
- 3.Bafounta, M. L., Beauchet, A., and Aegerter, P., Saiag P. Is dermoscopy (epiluminescence microscopy) beneficial for the prognosis of cancer? Results of a meta-evaluation the usage of strategies adapted to the evaluation of diagnostic checks. Arch. Dermatol. 137(13):43–50, 2001.Google Scholar
- 5.Garnavi, R., Computer-aided prognosis of melanoma, Ph.D. dissertation. Australia: College of Melbourne, 2011.Google Scholar
- 6.Celebi, M. E., Iyatomi, H., Schaefer, G., and Stoecker, W. V., Lesion border detection in dermoscopy images. Computerised Scientific Imaging and Portraits 33(2):148–153, 2009.Google Scholar
- 7.Iyatomi, H., Oka, H., Saito, M., Miyake, A., Kimoto, M., Yamagami, J., Kobayashi, S., Tanikawa, A., Hagiwara, M., Ogawa, K., Argenziano, G., Soyer, H. P., and Tanaka, M., Quantitative assessment of tumour extraction from dermoscopy photos and assessment of pc-primarily based extraction strategies for an automatic cancer diagnostic gadget. Melanoma Studies 16(2):183–190, 2006.CrossRefGoogle Scholar
- 12.Ramezani, M., Karimian, A., and Moallem, P., Automatic detection of malignant cancer using macroscopic snap shots. J. Med. alerts Sens. 4(4):281, 2014.Google Scholar
- 13.Di Leo, G., Paolillo, A., Sommella, P., et al., Automatic analysis of cancer: a software machine primarily based at the 7-point test-list. 2010 forty third Hawaii Int. Conf. on gadget Sciences (HICSS), 2010.Google Scholar
- 15.Piccolo, D., Crisman, G., Schoinas, S. et al., Laptop-automated ABCD versus dermatologists with different levels of experience in dermoscopy. Eur. J. Dermatol. 24(4):477–481, 2014.Google Scholar
- 16.Ramteke, N. S., and Jain, S. V., BCD rule based automatic computer-aided skin most cancers detection the use of Matlab®. Int. J. Comput. Technol. Appl. 4(4):691, 2013.Google Scholar
- 17.Smaoui, N., and Bessassi, S., A advanced device for cancer analysis. Int. J. Comput. Vis. Sign Manner. 3(1):10–17, 2013.Google Scholar
- 20.Celebi, M., Kingravi, H., Uddin, B., Iyatomi, H., Aslandogan, Y., Stoecker, W., and Moss, R., A methodological approach to the classification of dermoscopy pics. Automated Medical Imaging and Photographs 31:362–373, 2007.Google Scholar
- 21.Garnavi, R., Aldeen, M., Celebi, M. E., Bhuiyan, A., Dolianitis, C., and Varigos, G., Automatic segmentation of dermoscopy pics using histogram thresholding on finest colour channels. Global Journal of Medicine and Medical Sciences 1(2):126–134, 2010.Google Scholar