Türetken Engin, Blum Christian, González Germán, Fua Pascal
Computer Vision Lab., Ecole Polytechnique Fédérale de Lausanne, Switzerland.
Med Image Comput Comput Assist Interv. 2010;13(Pt 1):291-9. doi: 10.1007/978-3-642-15705-9_36.
We present a novel approach to fully automated reconstruction of tree structures in noisy 2D images. Unlike in earlier approaches, we explicitly handle crossovers and bifurcation points, and impose geometric constraints while optimizing a global cost function. We use manually annotated retinal scans to evaluate our method and demonstrate that it brings about a very substantial improvement.
我们提出了一种全新的方法，用于在有噪声的二维图像中全自动重建树形结构。与早期方法不同的是，我们明确处理交叉点和分支点，并在优化全局成本函数时施加几何约束。我们使用人工标注的视网膜扫描图像来评估我们的方法，并证明它带来了非常显著的改进。
