Article Per Year (5 Year)
p-Index From 2020 - 2025
0.61
P-Index
This Author published in this journals
All Journal Jiko (Jurnal Informatika dan komputer) Jurnal Garuda Pengabdian Kepada Masyarakat
Aditia, Risky
Unknown Affiliation
Humanities Computer Science & IT Economics, Econometrics & Finance Education Languange, Linguistic, Communication & Media Social Sciences Other

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
COMPARISON OF ROBUSTNESS TEST RESULTS OF THE EYE ASPECT RATIO METHOD AND IRIS-SCLERA PATTERN ANALYSIS TO DETECT DROWSINESS WHILE DRIVING Aditia, Risky; Sriani, Sriani
JIKO (Jurnal Informatika dan Komputer) Vol 7, No 3 (2024)
Publisher : Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v7i3.9239

Abstract

Traffic accidents caused by driver drowsiness are a leading factor in fatal road incidents. This study introduces a computer vision-based drowsiness detection system utilizing two methods: Eye Aspect Ratio (EAR) and Iris-Sclera Pattern Analysis (ISPA). The EAR method measures the eye aspect ratio to determine whether the eyes are open or closed. This involves calculating the vertical distance between specific landmark points on the eyelids and comparing it to the horizontal distance between points on the eye. A decrease in this ratio serves as an early indicator of drowsiness. The ISPA method employs symmetry analysis between the iris and sclera. This approach relies on the visual pattern formed when the eyes are open, where the sclera appears symmetrically distributed around the iris. During this process, eye images are processed to extract iris and sclera features, which are then analyzed for symmetry to detect signs of drowsiness. The study evaluates the reliability of both methods under varying conditions, such as changes in lighting, viewing distances, head movements, and the use of eyeglasses. The results show that the EAR method achieved an accuracy of 83.33% in distance testing, indicating its effectiveness in stable lighting environments. In contrast, the ISPA method achieved an accuracy of 59.25% under low and variable lighting conditions and proved more reliable for detecting the eyes of users wearing glasses.
Implementasi Opencv Face Recognition Pada Real-Time Deteksi Umur Dan Jenis Kelamin Menggunakan Python Dengan Metode Klasifikasi Aditia, Risky; Arrafiq, Muhammad Sunni; Afandi, Fahrul
Jurnal Garuda Pengabdian Kepada Masyarakat Vol 1 No 2 (2023)
Publisher : Ali Institute of Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/gabdimas.v1i2.820

Abstract

Wajah adalah model visual multidimensi yang dapat menunjukan identitas atau emosi. Skema deteksi wajah ini bertujuan mengenali jenis kelamin dan usia secara real-time. Menggunakan gambar dari kamera atau webcam sebagai input, sistem memberikan output berupa informasi jenis kelamin dan usia subjek saat itu. Dataset berisi 1,940 citra wajah yang telah dipotong dari kaggle.com, dengan jumlah yang sama untuk kelas laki-laki dan perempuan. Data ini mengalami ekstraksi fitur menggunakan model matriks dan dilatih dengan model Caffe, menghasilkan file Caffemodel. File Caffemodel merepresentasikan hasil citra yang dilatih dalam bentuk angka dan huruf. Program deteksi wajah menggunakan Caffemodel untuk mengidentifikasi lokasi wajah pada gambar dengan bingkai berwarna hijau sebagai penanda. Program kemudian menganalisis lebih lanjut untuk mengenali jenis kelamin dan usia dari wajah yang terdeteksi. Output akhir berupa informasi gender dan usia ditampilkan secara real-time melalui webcam pada laptop atau kamera. Skema ini berpotensi dalam pengenalan wajah real-time untuk keamanan, pengawasan, dan hiburan. Dengan model Caffe, sistem cepat dan akurat mengenali jenis kelamin dan usia individu dalam gambar. Integrasi webcam memberikan fleksibilitas implementasi dalam berbagai konteks penggunaan.
COMPARISON OF ROBUSTNESS TEST RESULTS OF THE EYE ASPECT RATIO METHOD AND IRIS-SCLERA PATTERN ANALYSIS TO DETECT DROWSINESS WHILE DRIVING Aditia, Risky; Sriani, Sriani
JIKO (Jurnal Informatika dan Komputer) Vol 7, No 3 (2024)
Publisher : Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v7i3.9239

Abstract

Traffic accidents caused by driver drowsiness are a leading factor in fatal road incidents. This study introduces a computer vision-based drowsiness detection system utilizing two methods: Eye Aspect Ratio (EAR) and Iris-Sclera Pattern Analysis (ISPA). The EAR method measures the eye aspect ratio to determine whether the eyes are open or closed. This involves calculating the vertical distance between specific landmark points on the eyelids and comparing it to the horizontal distance between points on the eye. A decrease in this ratio serves as an early indicator of drowsiness. The ISPA method employs symmetry analysis between the iris and sclera. This approach relies on the visual pattern formed when the eyes are open, where the sclera appears symmetrically distributed around the iris. During this process, eye images are processed to extract iris and sclera features, which are then analyzed for symmetry to detect signs of drowsiness. The study evaluates the reliability of both methods under varying conditions, such as changes in lighting, viewing distances, head movements, and the use of eyeglasses. The results show that the EAR method achieved an accuracy of 83.33% in distance testing, indicating its effectiveness in stable lighting environments. In contrast, the ISPA method achieved an accuracy of 59.25% under low and variable lighting conditions and proved more reliable for detecting the eyes of users wearing glasses.
Co-Authors Afandi, Fahrul Arrafiq, Muhammad Sunni