Investigating Support Vector Machine for Gender Identification
Asty Nabilah'Izzaturrahmah, Rizki Wulandari Muhammadia, Ryan Adeputra Sutopo, Mahmud Dwi Sulistiyo, Donni Richasdy · 2024
In today's digital era, advancements in technology, particularly in image processing and machine learning, have opened new possibilities in gender recognition and facial expression analysis. The ability of computers to recognize the ethnicity and gender of human faces has found critical applications in fields such as surveillance, biometrics, and security. Despite significant progress, gender recognition from facial photos still presents substantial challenges due to variations in facial features, expressions, and environmental conditions. This paper aims to address these challenges by investigating the use of Support Vector Machine (SVM) for gender identification using an image dataset from Kaggle. The primary objective is to enhance the accuracy and reliability of gender classification systems by optimizing SVM parameters and preprocessing techniques. Our proposed method involves a comprehensive analysis of feature extraction, data preprocessing, and SVM parameter tuning to achieve optimal performance. The experimental results demonstrate that the optimized SVM model achieves a notable accuracy of 74% in gender classification. This study contributes to the field of biometrics by providing new insights into the application of image processing and machine learning techniques for gender recognition. Furthermore, the findings can aid in developing more robust and accurate gender identification systems, ultimately advancing the capabilities of biometric applications in real-world scenarios.