Abstract:
This study aims to develop a system to classify the X-ray image based on the Convolution Neural Network (CNN) algorithm. The system is integrated with a Graphical User Interface (GUI) to make it easy to use. The algorithm of classification process consists of 3 stages. The preprocessing stage to optimize the image quality as the first stage. The second stage is the training process, which aims to train the CNN system to learn and model the dataset for each class. The last stage is the validation process, which aims to evaluate and validate the test data compare to training data. In the last stage, the training data is used to classify the X-ray image. We used the GUI to display the classification result. We used a 20384 dataset consisting of 5243 COVID cases,11995 normal cases and 3146 Pneumonia cases. We divided the data become 90% data for training and 10% for test Data. The experimental results are evaluated using a confusion matrix to determine the accuracy, precision, F1 score and recall. The experimental results show the successful rate of the performance of our system in image classification with results as follows average of accuracy is 90 %, precision 92%, recall 90% and F1 score 91%. In addition, the deployed GUI successfully displayed the x-ray image with classification result and the accuracy value. The GUI also is equipped with the report of the classification result in the form of the PDF file.