用于纤维增强复合材料纤维取向测量的椭圆检测算法

Algorithm for Ellipse Detection Applied to Measurement of Fiber Orientation in Fiber Reinforced Composites

椭圆检测是模式识别领域的一个热点问题,在工程中具有重要作用。结合纤维增强复合材料截面图中椭圆为实心,并且椭圆之间没有交叉和嵌套的性质,提出了一种基于顺序扫描的椭圆检测算法。该算法首先找出椭圆的中心,然后采用一个快速确定短半轴端点的方法,计算出短半轴的长度和斜率,最后通过计算得出长轴的斜率和长度。实验证明,该算法能准确有效地检测到纤维增强复合材料截面图中的椭圆,因而可以用于复合材料中纤维取向的测量。

Detection of ellipse is one of the most important issues in the field of pattern recognition, which plays an important role in the engineering application. In this paper, a novel algorithm for detecting ellipses is proposed, which is based on a sequential- scanning method of pixels with the consideration that the ellipses are filled and they are not intersectional or nesting. First, the center of the ellipse is searched out, and then the lengtb and the slope coefficient of the minor axis is worked out to decide the endpoint of the minor axis, in this way, the length and slope coefficient of the major axis is calculated from elliptic equation. Experiments shows that this is an efficient algorithm which can accurately detect the ellipses in the picture of the intersection of the fiber reinforced composites, so it can be used to measure the fiber orientation of fiber reinforced composites.