Application of YOLO (You Only Look Once) V.4 with Preprocessing Image and Network Experiment

Abstract

In computer science, specifically in the field of image processing, many reliable algorithms have been found. Previously it was introduced that the YOLO (You Only Look Once) V.3 algorithm. In this case, the application of the YOLO algorithm that we carried out was applied experimentally by utilizing image preprocessing techniques. In this study, image preprocessing was carried out. The image of the Microsoft COCO dataset that was preprocessed in this study used the method of image dimension reduction and image quality improvement. The Microsoft COCO dataset image dimension reduction method used is the Principal Component Analysis (PCA) method and to improve the image quality of the Microsoft COCO dataset using Gaussian Smoothing. Then after the fine-tuning process, there is an increase in the mAP value by an average of 8.99% so that the five models can have an mAP above 80%. The highest mAP value is owned by the model using the schema after the fine-tuning process. From the results of experiments carried out in this study, obtained detection results that have fairly good accuracy in the dataset results. Irregular transformations of position, dimension, composition and, direction can still be captured as the same feature. YOLO's ability in feature engineering is an acknowledgment that has been successfully proven in this research. Although not all the results of using this algorithm are perfect on all data, the results tend to be good. This is related to the services available in the form of a convolutional layer on YOLO reducing downsample or reducing image dimensions by using anchor boxes, this algorithm can also improve accuracy