Pixel Coordinates for Obtaining 3D Body Measurements from 2D Images

ŞENGÖZ N. G., ZEYBEK F.

Tekstil ve Konfeksiyon, cilt.34, sa.2, ss.127-146, 2024 (SCI-Expanded, Scopus) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 34 Sayı: 2
  • Basım Tarihi: 2024
  • Doi Numarası: 10.32710/tekstilvekonfeksiyon.1201436
  • Dergi Adı: Tekstil ve Konfeksiyon
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.127-146
  • Anahtar Kelimeler: 2D, 3D, Body Measurements, Feature points, Mathematical models, Pixel coordinates
  • Isparta Uygulamalı Bilimler Üniversitesi Adresli: Evet

Özet

In this research, a new method developed with pixel coordinates is presented to obtain 3D body measurements from 2D images, to eliminate the need of the body to take measurements and to solve unfit problem in e-shopping. Front and side photographs are processed with new developed softwares PixelList1.0 and PyNGF-2 for verification. The sharp silhouettes, presented in authors’ another publication, are benefited with algorithms to reach pixel coordinates of feature points. Number of pixels in between feature points are saved, absolute values of differences are calculated consecutively, and 3D body measurements in pixels are obtained with different mathematical models, circle, ellipse, and hippodrome circumference equations. A conversion coefficient is introduced and size of a pixel is calculated accurately, 0.2596 cm/pixel. 3D body measurements in centimeters are obtained by multiplying number of pixels by the size of one pixel. An overall accuracy rate of 91.585 % is concluded with the ellipse circumference equation precisely.