Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Ida Yusnilawati
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Implementasi Connected Component Labeling untuk Deteksi Objek Penghalang Bagi Penyandang Tunanetra Berbasis Raspberry Pi Ida Yusnilawati; Fitri Utaminingrum; Mochammad Hannats Hanafi Ichsan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 2 (2019): Februari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (414.619 KB)

Abstract

Blind is a condition where the both senses of sight do not work to receive information like the alert person, that's why it needs auxiliary tool like stick to carry out daily activities. However, the stick still has a deficiency too that can only be used to touch objects or obstacles with a limited range. One of technologies that enables blind people in carrying out daily activities is to use computer vision for processing of digital image that can detect a barrier object when a blind person walks in the room. This system uses a webcam camera as a censor attached in front of the user's chest at a height of 110cm and a camera tilt of 41áµ’, so that it can take the image in front of the user up to 125cm. The detection process of this barrier object is done in several steps, such as resizing the image, cropping, then thresholding. This thresholding process utilizes values from the RGB image of floor. To get a blob in the image uses connected component labeling 4 connectify used to label pixels. Pixels that have been labeled will be analyzed to be able to detect barrier object. From the study that has been done by the system, it can detect barrier object with accuracy of 91,66%. The result of study for accuracy of system integration with hardware is 98.33%, and the average time of system computing is 166.15 ms.
Co-Authors Mochammad Hannats Hanafi Ichsan Utaminingrum, Fitri