MONKEY POX DISEASE DETECTING SYSTEM USING DEEP LEARNING

MONKEY POX DISEASE DETECTING SYSTEM USING DEEP LEARNING

¹Ms. E. Padma, ²Bandar Sai Prasanna, ³Bodagala Padmaja

¹Assistant Professor,²Graduate Students,³ Graduate students

 Dept. of Computer Science Engineering,

SCSVMV (Deemed to be University), Enathur, India

Abstract: Due to the recent monkeypox outbreak's quick spread to more than 40 nations outside of Africa, public health is now at risk. It is difficult to diagnose clinically in its early stages since it resembles both chickenpox and measles. Computer-assisted monkey pox lesion detection may be helpful for surveillance and quick identification of suspected cases when confirmatory Polymerase Chain Reaction (PCR) assays are not accessible. Under the condition there are enough training examples available, deep learning techniques have been demonstrated to be useful in the automated detection of skin lesions. Such databases are not currently accessible for the monkeypox condition. The majority of the photographs came from news websites, blogs, and publicly available case reports. A 3-fold cross-validation experiment is set up, and the sample size is increased through data augmentation. The second phase is categorizing diseases like monkeypox using several pre-trained deep-learning models including VGG-16, CNN, and Mobile Net. It is an ensemble of the three models created. An online method for screening for monkeypox is also being developed as a prototype web application. While the early results on this tiny dataset are promising.

Keywords: Monkeypox image dataset, Skin disease classification, Transfer Learning, image processing, CNN, Mobile Net & VGG19.