Automatic segmenting and measurement on scanned human body

Abstract

Purpose -This paper presents methods and algorithms to automatically segment and measure the human body. Design/methodology/approach -In the segmentation procedure, two different methods are designed to find the crotch point for the situation of non-contacted thigh and contacted thigh, respectively. Three different methods: minimum distance algorithm, minimum inclination angle algorithm, and directional neighbor identification algorithm are introduced to search the branching points or triangle. In the body measurement procedure, a pre-sorted circling method is designed for circumference measurement, and the basic principle of landmark acquisition has been discussed. These techniques are validated via testing over different type of scanned model. Findings -The results of automatic segmentation and body measurement have verified that our methods are efficient and versatile in processing different type of scanned body.Research limitations/implications -The accurate and automatic locating of wrist, ankle and knees contour can be more difficult than it appears to be. Practical implications -The main usage of scanned body in our research is for 3D garment try-on. Originality/value -This paper introduces the methods for crotch identification, and the methods including minimum distance algorithm, minimum inclination angle algorithm, and directional neighbor identification algorithm for human body segmentation. It also explains the fundamental measuring techniques, and outlines the results of using these techniques in segmentation and measurement.

Validation of a 3-Dimensional Laser Body Scanner for Assessment of Waist and Hip Circumference

“…1b. Lines indicate circumferences, including measurements at the umbilicus and hip [24]. Resolution for the device is not adjustable and is set sufficiently high for circumference calculations but low enough to prevent identification of facial features.…”

Geodesic Model of Human Body

“…Wang et al [5] propose a method to extract joints from a human body mesh in standard pose using the statistical anthropometric proportion as a landmark. Zhong and Xu [6] map a proportion value to a vertical coordinate in model segmentation and joint extraction, but that method is not applicable for arbitrary posed human body. Since segment lengths are measured with the Euclidean distance between two joints, direct correspondence between the anatomic proportion and the mesh surface is lacking.…”

Three-dimensional (3D) technologies for apparel and textile design

“…In 3D measurement, the process is more diffi cult because the landmarks can be very subtle, there is high variation in body shape for different people, and the landmarks may be hidden from view (Buxton et al, 2000). Researchers have used various methods to locate landmarks, such as searching for the intersection of angles at points of extremities or vertical locations, or changes in curvature along body crosssections or profi les (Dekker et al, 1999;Kim & Kang, 2002) Researchers have also utilized belts or other markers during image capture to help predefi ne a body landmark that can be easily located by a computer after scanning (Buxton et al, 2000;Dekker et al, 1999;Pargas et al, 1997;Wang et al, 2007;Zhong & Xu, 2006). Some laser scanning systems can record color values, so that landmarks identifi ed with color markers can be extracted after scanning (Paquette, 1996;Wang et al, 2007).…”