Penerapan Machine Learning dalam Klasifikasi Wajah dan Benda Menggunakan Teachable Machine Berbasis Lovable

Abstract

The rapid advancement of Artificial Intelligence (AI), particularly in the fields of Machine Learning and Computer Vision, has accelerated the development of image classification systems capable of recognizing various objects automatically. One of the platforms that facilitates the development of machine learning models without requiring advanced programming skills is Google Teachable Machine, while Lovable is an AI-based application development platform that simplifies and accelerates web application development. This study aims to implement machine learning in developing a face and object classification system using Google Teachable Machine integrated into a Lovable-based application. The research methodology consists of dataset collection involving face and object images, data preprocessing, model training using Google Teachable Machine, model export in TensorFlow.js format, integration of the trained model into the Lovable application, and system testing using both image and video inputs in real time. The evaluation was conducted to assess the system's ability to classify trained face and object categories under various testing scenarios. The outcome of this research is a web-based application capable of classifying faces and objects through image and video inputs with fast and accurate performance. This study is expected to provide an alternative approach for developing machine learning-based applications that are easy to implement while supporting the broader application of Artificial Intelligence technologies in various fields.