الفهرس 
chapter 1: IntroductionOnly 14 pages are availabe for public view
 |  | from | 133 |  |  |
| | | from | 133 | | |
Abstract
This thesis presents new system to predict junior swimmers depending on their anthropometric measurements automatically. This system contains two subsystems; digital processing for weight measurement and image processing for the anthropometric measurements that uses two different algorithms.
In image processing subsection, first algorithm measures the anthropometric measurements by detecting the human body feature points automatically. This algorithm applies three different methods; absolute different, dilation and erosion, to determine body contour. Then Canny edge detector and Freeman’s chain code are applied. Then human feature points are extracted automatically. Absolute difference method is recommended to use. Second algorithm uses fuzzy edge detection instead of Canny to detect silhouette curve.
The system extracts 101 feature points for 36 human body measurements. The system uses 8 measurements and body weight to determine junior swimmers. System database is used for comparing measurements to the standard one. The proposed system can applied in many other sports.