1、 - 1 - 摘 要 图像由于携带丰富的信息得到人们的青睐，而目前获取图像的方法有拍照， 视屏截图，利用计算机产生彩图，激光扫描 1 等等。从图像中获取景物的三维信 息属于一个多学科交叉的研究领域,它涉及到射影几何学、数字图像处理、计算 机图形学、计算机视觉等许多学科的理论,是目前研究的热点之一。三维重建就 是通过二维图像中基元(如点、线、面)来恢复目标的三维空间信息,需要研究三 维空间中点、线、面的三维坐标与二维图像中对应点、线、面的二维坐标之间的 关系,实现定量分析物体的大小和空间物体的相互位置关系。其主要过程是通过 对图像的特征提取、特征匹配、图像关键特征的重建、三角化以及数据融合生成
2、物体完整的三维结构。这种三维信息或三维模型在虚拟植物可视化、数字娱乐、 产品外观设计、虚拟场景的模拟等诸多领域具有广泛的应用价值。本文提出了利 用数字图像处理的方法对图像进行处理以获得目标图像的轮廓， 并得到目标图像 的轮廓关键点上的坐标，这对接下来的三维重建目标十分关键。在本文中图像采 集之后，首先将其数字化。数字化之后，计算机利用数字图像处理技术对图像进 行彩色预处理、去除背景、图像平滑、彩色转灰度、图像锐化、灰度二值化、腐 蚀膨胀、滤波、轮廓提取等处理，并且给出每步处理的图像结果。 关键词关键词： 数字成像； 图像处理； 三维重建； 轮廓； 坐标 - 2 - Abtract Image
3、which due to the rich information to get the favour of people，At present, image acquisition methods are taking pictures, screen shots, and produce images by computer, laser scanning etcThree-dimensional information obtained from two-dimensional images is an interdisciplinary research field, it invol
4、ves many subjects of projective geometry, digital image processing, computer graphics, computer vision theory, is a research hotspot. Three-dimensional reconstruction is through 2D image primitives (such as point, line, surface) three-dimensional spatial information to restore the target, need to st
5、udy three-dimensional point, line, surface 3D coordinate and 2D image corresponding points, lines, surfaces two-dimensional coordinate relationship, relationship between size and space objects to realize quantitative analysis of objects the. The main process is through the feature extraction, featur
6、e of image matching, reconstruction of key characteristics, triangulation and data fusion to generate complete object three-dimensional structure. This 3D information or 3D models have wide applications in virtual plant visualization, digital entertainment, product design, virtual scene simulation etc.This paper proposes the method of digital image processing to deal with the image we have got in order to obtain a target image contour, and get the coordinates of key points on the contour of th
