Estimating weight based on 2D image is advantageous especially for contactless and rapid measurement. Several researches used additional thermal camera or Kinect camera, required subjects to do front and side pose and manually extract body measures. This research propose an algorithm to estimate body weight automatically using 2D visual image where subject only do front pose. This research studied 4 features of body measures which are: (F1) height, and width of (F2) shoulder, (F3) abdomen/waist plus arm, (F4) feet. Each feature was simply subtracted based on body proportion where normal body has 8 equal segments. Shoulder is in 2nd segment, abdomen/waist is in 4th segment and feet is in the last segment. Multiple Linear Regression is used to determine weight estimation formula of all combination of 4 features, 15 in total. The highest significance R2 (0.80) and RMSE 2.68 Kg is given when using all 4 features in the estimation formula.

Estimating weight based on 2D image is advantageous especially for contactless and rapid measurement. Several researches used additional thermal camera or Kinect camera, required subjects to do front and side pose and manually extract body measures. This research propose an algorithm to estimate body weight automatically using 2D visual image where subject only do front pose. This research studied 4 features of body measures which are: (F1) height, and width of (F2) shoulder, (F3) abdomen/waist plus arm, (F4) feet. Each feature was simply subtracted based on body proportion where normal body has 8 equal segments. Shoulder is in 2nd segment, abdomen/waist is in 4th segment and feet is in the last segment. Multiple Linear Regression is used to determine weight estimation formula of all combination of 4 features, 15 in total. The highest significance R2 (0.80) and RMSE 2.68 Kg is given when using all 4 features in the estimation formula.