GDL

Journal from gdlhub / 2018-01-15 11:38:09
Oleh : I Nyoman Gede Arya Astawa, I Ketut Gede Darma Putra, I Made Sudarma, Rukmi Sari Hartati, Telkomnika
Dibuat : 2018-01-15, dengan 1 file

Keyword : Intensity, Normalization, Color, Face, Detection
Url : http://journal.uad.ac.id/index.php/TELKOMNIKA/article/view/6718
Sumber pengambilan dokumen : WEB

Study about human face detection has been widely conducted and it is still interesting to be studied. This study proposed the strong impact of color space for face detection. The studied image was a image containing of many faces or multi faces. The utilized color spaces were YIQ, YCbCr, HSV, HSL, CIELAB, and CIELUV. In this experiment, one of the color space channel was added intensity normality method and tested on Android based face detection system. The used face multi image came from different devices; social media, hand phone, and digital camera. Based on the analysis it was found that color space of YCbCr reached the best improvement percentage. The detection score on the beginning of the image before the process for social media, hand phone, and digital camera was 67.15%, 75.00%, and 64.58%, respectively. After normalization process, these scores were increasing to be 83.21%, 87.12%, and 80.21%.

Beri Komentar ?#(0) | Bookmark

Properti	Nilai Properti
ID Publisher	gdlhub
Organisasi	Telkomnika
Nama Kontak	Herti Yani, S.Kom
Alamat	Jln. Jenderal Sudirman
Kota	Jambi
Daerah	Jambi
Negara	Indonesia
Telepon	0741-35095
Fax	0741-35093
E-mail Administrator	elibrarystikom@gmail.com
E-mail CKO	elibrarystikom@gmail.com