The COVID-19 pandemic started with the first case from China in December 2019 and continues to pose a major threat to the world's health. COVID-19 spread around the world in a short time and negatively affected people's lives in every aspect. Due to the rapid spread of COVID-19, the healthcare sectors of many countries have been caught off guard. This situation created a very heavy workload for doctors and healthcare professionals. Due to the importance of COVID-19, many studies have been conducted in the literature. These studies have been carried out and continue to be done to help experts to diagnose COVID-19 more accurately and to use appropriate treatment methods for this diagnosis. Computer aided diagnosis systems should be developed to alleviate this workload. Machine Learning Algorithms (MLAs) are of great importance in the development of computer-aided early and accurate diagnosis systems in medicine today. In this study, a method is proposed for more accurate diagnosis of COVID-19 patients using COVID-19 image data. Feature extraction was performed using the RGB values of the images. These features were used in train and test operations for MLAs. Six different MLAs were used in experimental studies (k Nearest Neighbor (k-NN), Decision Tree (DT), Multinominal Logistic Regression (MLR), Naive Bayes (NB) and Support Vector Machine (SVM), Minimum Mean Distance Classifier (MMDC)). The following accuracy rates were obtained in train operations for MLAs, respectively; 1, 1, 1, 0.81159, 0.94927, 0.81884. In test operations, accuracy results were obtained as follows; 0.83673, 0.93877, 0.97959, 0.85714, 0.87142, 0.85714. After the application of the proposed method, the test success rate for MLR increased to 1. The results obtained were given in the experimental studies section in detail. The results proved to be very promising. According to the results, it was seen that the proposed method could be used effectively in future studies.