Since the beginning of the COVID-19 outbreak, the scientific community
has been making efforts in several areas, either by seeking
vaccines or improving the early diagnosis of the disease to contribute
to the fight against the SARS-CoV-2 virus. The use of X-ray
imaging exams becomes an ally in early diagnosis and has been the
subject of research by the medical image processing and analysis
community. Although the diagnosis of diseases by image is a consolidated
research theme, the proposed approach aims to: a) apply
state-of-the-art machine learning techniques in X-ray images for
the COVID-19 diagnosis; b) identify COVID-19 features in imaging
examination; c) to develop an Artificial Intelligence model to
reduce the disease diagnosis time; in addition to demonstrating the
potential of the Artificial Intelligence area as an incentive for the
formation of critical mass and encouraging research in machine
learning and processing and analysis of medical images in the State
of Mato Grosso, in Brazil. Initial results were obtained from experiments
carried out with the SVM (Support Vector Machine) classifier,
induced on a publicly available image dataset from Kaggle repository.
Six attributes suggested by Haralick, calculated on the gray
level co-occurrence matrix, were used to represent the images. The
prediction model was able to achieve 82.5% accuracy in recognizing
the disease. The next stage of the studies includes the study of deep
learning models.