Treffer: 3D Geometric Shape and Colors Interactive Learning Media using Raspberry Pi, OpenCV, and TensorFlow Lite.

This study aims to create learning media for 3D geometric shapes and colors for early childhood. Early childhood can enter 3D objects into the device. Then, the device will mention and explain the shape and color of the object in question. As a contribution, this research provides a brief introduction and learning related to geometric shapes for early childhood. The method used is experimental. The hardware components of this system are Raspberry Pi 3, RPi Camera, PIR Sensor, 3.5inch LCD, and Speaker. Python, OpenCV, and TensorFlow Lite are used from the software side. OpenCV is used to detect colors. TensorFlow Lite is used to detect the shape of geometric objects. In this study, the model used is a custom model specifically for TensorFlow Lite, which was trained through Google Colab. This media has a learning mode and a question mode. In learning mode, early childhood only needs to insert objects into the learning media and will get information in the form of images and sounds related to the object. In question mode, the learning media will provide instructions and questions to enter objects with a specific color. After that, the learning media will determine whether the answer is right or wrong and give the score. The results of tests that cover both modes reach a success percentage of 100%, where this learning media can recognize and explain every shape and color of objects in both modes. [ABSTRACT FROM AUTHOR]

Copyright of International Journal on Advanced Science, Engineering & Information Technology is the property of INSIGHT - Indonesian Society for Knowledge & Human Development and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)