Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Bulletin of Computer Science Research APPA : Jurnal Pengabdian Kepada Masyarakat
Okky Prasetia
Unknown Affiliation
Computer Science & IT Economics, Econometrics & Finance Education Law, Crime, Criminology & Criminal Justice Medicine & Pharmacology

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Bulletin of Computer Science Research

 1 
Klasifikasi Gender Berbasis Citra Wajah Menggunakan Clustering Dan Deep Learning Okky Prasetia; Syaeful Machfud; Rosyani, Perani; Bobi Agustian
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.581

Abstract

Gender classification based on facial images is a significant challenge in the field of computer vision, especially when dealing with unstructured data sourced from social media platforms. This study proposes an integrated approach combining facial image preprocessing, clustering methods, and deep learning to enhance the accuracy of gender classification. The dataset used was obtained from a Big Data Competition and consists of male and female face images sourced from Instagram. Preprocessing was performed using OpenCV for face detection and cropping. Subsequently, the data were clustered using K-Means and DBSCAN algorithms to reduce noise and redundancy. Gender classification was then conducted using a sequential learning model based on Inception_v3, enhanced with Agglomerative Clustering for feature refinement. The evaluation of the system demonstrated strong performance with an accuracy of 92.97%, F1-score of 0.89556, precision of 0.97727, and recall of 0.83069. These results confirm that the integration of clustering techniques and deep learning significantly improves the effectiveness of gender classification based on facial images, especially for open-source and non-curated datasets.
Co-Authors Bobi Agustian Gigih Amrillah Ibnurhus Perani Rosyani Syaeful Machfud