An Improved VGG16 Model for Pneumonia Image Classification

Image recognition has been applied to many fields, but it is relatively rarely medical images. Recent significant deep learning progress for image raised strong research interest in recognition. First of all, we found the prediction result using VGG16 model on failed pneumonia X-ray Thus, this paper proposes IVGG13 (Improved Visual Geometry Group-13), a modified classification X-rays Open-source thoracic images acquired from Kaggle platform were employed recognition, only few data obtained, and datasets unbalanced after classification, either which can extremely poor trained neural network models. Therefore, augmentation pre-processing compensate low volume poorly balanced datasets. The original without proposed some well-known convolutional networks, such as LeNet AlexNet, GoogLeNet VGG16. In experimental results, rates other evaluation criteria, precision, recall f-measure, evaluated each model. This process was repeated augmented datasets, with greatly improved metrics F1-measure. produced superior outcomes F1-measure compared current best practice networks confirming effectively accuracy.