Disciplines using human body surface dimensions require accurate, repeatable measurements. This study presents a design for the analysis of repeatability, precision, and validation of a new anthropometric device. This model enables estimation of the proportion of the total variation attributable to each level of data collection. This model is applied to an analysis of repeatability, precision, and validation of the Cencit Imaging System, a new optical surface scanner. Twenty-seven facial landmarks were marked on 10 men and 10 women at two measurement sessions. Two images were scanned during each session, and each image was digitized twice. The Cencit Imaging System results were compared with a previously validated digitizer. The Cencit Imaging System was found to produce accurate, highly repeatable images. Much of the error in this study is attributable to human error in marking landmarks on the subjects. The new imaging system will prove useful in a variety of anthropometric applications.