Gender identification system using characteristics of the neck  

Oleh:

Iwata, Kengo ; Nakamura, Munehiro ; Kimura, Haruhuko

Jenis: Article from Proceeding
Dalam koleksi: The 14th Asia Pacific Industrial Engineering and Management Systems Conference (APIEMS), 3-6 December 2013 Cebu, Philippines, page 1-8.
Topik: Gender Identification; Ecological Feature; Neck Feature; Profile Image.
Fulltext: 1193.pdf (2.51MB)

Isi artikel

Most gender identification systems are designed to apply to frontal images using characteristics such as clothing, hairstyle, voice, and gait. These characteristics are depended on one’s will and condition. This paper presents a gender identification system for profile images using characteristics of the neck as features. The proposed features are extracted from the curve of the throat and measured from the width of the neck. Experimental results on 90 profile images show that the proposed method has the identification accuracy of 95.0% for female and 96.0% for male.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali