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
Rizky Haris Risaldi
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 
Deteksi Objek Penghalang secara Real Time berbasis Aplikasi Mobile dengan Metode Gray Level Co-Occurrence Matrix dan K-Nearest Neighbor bagi Penyandang Tunanetra Rizky Haris Risaldi; Fitri Utaminingrum
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 10 (2019): Oktober 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (527.22 KB)

Abstract

Blind people have a condition that their sense of sight is not functioning properly. The condition causes the blind have difficulties in mobility. Solution for these conditions is use a stick. Mobile devices can be a new solution for this problem because mobile devices are capable of many processes. This system was built using a camera from a mobile device as a substitute for the sense of sight. The results of the camera are then extracted features using the GLCM (Gray Level Co-Occurence Matrix). Once the feature is obtained, the classification is done by algorithms KNN (K-Nearest Neighbor). The classification used to determine these features is the floor or obstruction. If the result of the classification is an obstacle, the next process is to turn on the buzzer as a sign to the user that a obstacle has been detected. . This system has good detection accuracy when using a small ROI (120x213 pixels) of 90% compared to ROI (360x640 pixels) of 60%. In real time the system has a 100% accuracy in obstacle detection for white floor objects, 82% for obstacles with wooden door objects, 93% for white obstacles and 93% if detection is done on 2 different objects in 1 video. Integration of hardware and software on this system has an accuracy value of 88.8%. For computing time this system has an average value of 248.8 ms, a minimum value of 183 ms and a maximum value of 582 ms.
Co-Authors Utaminingrum, Fitri