| 基于神经网络的三维图象恢复与重建新算法 |
| |
| 引用本文： | 袁友伟,贺素良,鄢腊梅. 基于神经网络的三维图象恢复与重建新算法[J]. 计算机工程, 2001, 27(10): 69-70 |
| |
| 作者姓名： | 袁友伟 贺素良 鄢腊梅 |
| |
| 作者单位： | 株洲工学院计算机系 |
| |
| 基金项目： | 湖南省自然科学基金资助项目(00JJY2082) |
| |
| 摘 要： | 简介了兰伯特Lambertian反射模型用于三维图象的恢复与重建的算法，由于其具有很大的局限性，为此，给出了一种基于神经网络与模糊处理相结合的新型反向模型，用于三维图象的恢复与重建，且新算法不需知道光源方向，经实验证明，具有计算快捷且图象识别精度高的特点。
|
| 关 键 词： | 模糊神经网络 三维图象重建 图象恢复 图象处理学 计算机 |
| 文章编号： | 1000-3428(2001)10-0069-02 |
| 修稿时间： | 2001-04-23 |
New Method for Three-dimensional Reconstruction Based on Neural Network |
| |
| YUAN Youwei,HE Suliang,YAN Lamei. New Method for Three-dimensional Reconstruction Based on Neural Network[J]. Computer Engineering, 2001, 27(10): 69-70 |
| |
| Authors: | YUAN Youwei HE Suliang YAN Lamei |
| |
| Abstract: | In this paper, the limitation of the conventional Lambertian reflectance model is addressed and a new neural-based reflectance model is proposed. The new neural learning algorithm is to optimize a proper reflectance model and to recover the object surface by a simple shape-form-shading(SFS) variational method with this neural-based model and fuzzy method model. An example is also given to prove that the SFS technique is robust for most objects, even when the lighting conditions are uncertain. |
| |
| Keywords: | Fuzzy and neural network Three-dimensional image reconstruction Image restoration |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
