Search

In the last decade, there have been significant developments in Image Caption Generation research to translate images into English descriptions. This task has also been conducted to produce texts in non-English, including Bahasa. However, the references in this study are still limited, so exploration opportunities are open widely. This paper presents comparative research by examining several state-of-the-art Deep Learning algorithms to extract images and generate their descriptions in Bahasa. We extracted images using three pre-trained models, namely InceptionV3, Xception, and EfficientNetV2S. In the language model, we examined four architectures: LSTM, GRU, Bidirectional LSTM, and Bidirectional GRU. The database used was Flickr8k which was translated into Bahasa. Model evaluation was conducted using BLEU and Meteor. The performance results based on the pre-trained model showed that EfficientNetV3S significantly gave the highest score among other models. On the other hand, in the language model, there was only a slight difference in model performance. However, in general, the Bidirectional GRU scored higher. We also found that step size in training affected overfitting. Larger step sizes tended to provide better generalizations. The best model was generated using EfficientNetV3S and Bidirectional GRU with step size=4096, which resulted in an average score of BLEU-1=0,5828 and Meteor=0,4520.

This study provides a review of CNN's ensemble learning method for transfer learning by highlighting sections such as review studies, datasets, pre-trained models, transfer learning, ensemble learning, and performance. The results indicate that the trend of ensemble learning, transfer learning ensemble, and transfer learning is growing every year. In 2022, there will be 35 papers reviewed related to this topic in this study. Some datasets contain apparent information starting from the dataset name, total data points, dataset splitting, target dataset availability, and type classification. ResNet-50, VGG-16, InceptionV3, and VGG-19 are used in most papers as pre-trained models and transfer learning processes. 50 (90.1%) papers use ensemble learning, and 5 (9.1%) do without ensemble learning. The reviewed paper summarizes several performance measurements, including accuracy, precision, recall, f1-score, sensitivity, specificity, training accuracy, validation accuracy, test accuracy, training losses, validation losses, test losses, training time, and AUC, DSC. In the last section, 49 papers produce the best model performance using the proposed model, and 6 other papers use DenseNet, DeQueezeNet, Extended Yager Model, InceptionV3, and ResNet-152.

COVID-19 prevention procedures are executed to support public services and business continuity in a pandemic situation. Manual mask use monitoring is not efficient as it requires resources to monitor people at all times. Therefore, this task can be supported by automated surveillance systems based on Deep Learning. We performed mask detection and face recognition for a real-environment dataset. YOLOV3 as a one-stage detector was implemented to simultaneously generate a bounding box of the face area and class prediction. In face recognition, we compared the performance of three pre-trained models, namely ResNet152V2, InceptionV3, and Xception. The mask detection showed promising results with MAP=0.8960 on training and MAP=0.8957 on validation. We chose the Xception model for face recognition because it has equal quality as ResNet152V2 but has fewer parameters. Xception achieved a minimal loss value in the validation of 0.09157 with perfect accuracy on facial images larger than 100 pixels. Overall the system delivers promising results and can identify faces, even those behind the mask.