經過實驗後，可得知在兩者相較之下，兩者的可用性相似，並無太大差異，但在時間效率上，使用人臉資料增益的方式，遠比使用人臉生成的方式快上許多。因此，對本研究個案公司而言，使用人臉資料增益的方式產生人臉圖片，是較符合個案需求的方式。 ;Face detection has always been a very popular topic, and in recent years, the rise of machine learning technology has pushed face detection to a higher level. Training through a large amount of data can effectively improve the detection accuracy, so how to collect a larger number of face detection training pictures is an important topic. In response to the research and development plan, the case of A Company in this study adopted a supervised learning method in the face detection project to train the face pictures to generate face detection modules, so there is often a demand for a large number of face pictures. Under long-term demand, the use of data generation and data augmentation is a very suitable way. This study focuses on face data generation and face data augmentation, and explores which of the two methods is more efficient in producing face images, including the time it takes to generate the images and the availability of the generated images. Comparing the two, we can find that the two are similar in terms of usability, but in terms of time efficiency, the way of using face data augmentation is much faster than the way of using face generation. After confirming the efficiency and availability, it will be of great help to the future development of A company in this research case.
