Integrasi OCR dan Raspberry Pi dalam Sistem Pemindai Otomatis untuk Aksesibilitas Digital

Abstract

Abstract - Persons with disabilities, especially those who are visually impaired, face limitations in accessing printed information such as books, magazines, and brochures, which are generally intended for the sighted public. Although Braille has become the standard solution for blind individuals to read, the limited availability of Braille reading materials, uneven distribution, and the requirement for special learning make it less efficient and not entirely inclusive. According to data from the 2015 Intercensal Population Survey (SUPAS) by Statistics Indonesia, around 6.36% of the Indonesian population has visual impairments, with 0.13% experiencing total blindness. This data highlights the importance of developing alternative technologies that offer easier and more practical access to information for the visually impaired. This study aims to design and implement an Automatic Text and Image Reading Scanner Based on Raspberry Pi. The device works by capturing text and images through a Raspberry Pi camera, then processing them using a Raspberry Pi 3 Model B computing system, and converting them into voice output that can be heard through a speaker. The system is also equipped with an HC-SR04 ultrasonic sensor to maintain the optimal distance for image capture. The expected result is a portable device that helps visually impaired individuals read printed text without the need for Braille, providing the information in audio form. Through the development of this tool, it is expected to offer a more inclusive and efficient solution for visually impaired individuals to access information independently, while also contributing to the advancement of assistive technology.