Mostly, Shape From Focus (SFF) algorithms use local averaging using a fixed rectangle window to enhance the initial focus volume. In this linear filtering, the window size largely affects the accuracy of the depth map. A small window is unable to suppress the noise properly while a large window over smoothes the object shape. Moreover, the use of any window size smoothes focus values uniformly. Consequently, an erroneous depth map is obtained. In this paper, we suggest the use of iterative 3D Anisotropic Nonlinear Diffusion (AND) to enhance the image focus volume. In contrast to the linear filtering, AND utilizes the local structure of the focus values to suppress the noise while preserving edges. The proposed scheme is tested using image sequences of synthetic and real objects and results have demonstrated its effectiveness.
展开▼
