Penerapan Metode Yolov5 dan Teknologi Text-To-Speech dalam Aplikasi Pengenalan Abjad dan Objek Sekitar untuk Anak Usia Dini

Abstract

Technological developments have provided significant benefits for various levels of society, including young children. There are several internal and external factors that can hinder children from remembering the alphabet and objects around them. To overcome these challenges, an innovative and interesting approach is needed to increase children's interest and involvement in learning to recognize alphabets and objects. Research has been carried out to develop an interactive learning media aimed at early childhood using an artificial intelligence approach. The You Only Look Once (YOLO) algorithm will be used to detect letters and surrounding objects in real-time, while Text-to-Speech (TTS) technology is used to convert text into sound. The dataset consists of 2511 images with 36 classes, including alphabets, fruits, animals, and stationery. In this research, the YOLOv5s method obtained a significant level of accuracy, reaching 85% so it could work well in detecting objects.