In this session, we will explore the concept of on-device machine learning and its advantages and disadvantages. On-device machine learning refers to running machine learning models directly on a device, such as a smartphone or tablet, rather than relying on a remote server. This approach has several benefits, including improved performance and enhanced privacy. However, it also presents some challenges that need to be considered. We will introduce the Mediapipe framework and demonstrate how it can be used to implement on-device machine learning solutions.