MRT Letter: Guided filtering of image focus volume for 3D shape recovery of microscopic objects |
| |
| Authors: | Muhammad Tariq Mahmood |
| |
| Affiliation: | School of Computer Science and Engineering, Korea University of Technology and Education, Cheonan, Korea |
| |
| Abstract: | In this letter, a shape from focus (SFF) method is proposed that utilizes the guided image filtering to enhance the image focus volume efficiently. First, image focus volume is computed using a conventional focus measure. Then each layer of image focus volume is filtered using guided filtering. In this work, the all‐in‐focus image, which can be obtained from the initial focus volume, is used as guidance image. Finally, improved depth map is obtained from the filtered image focus volume by maximizing the focus measure along the optical axis. The proposed SFF method is efficient and provides better depth maps. The improved performance is highlighted by conducting several experiments using image sequences of simulated and real microscopic objects. The comparative analysis demonstrates the effectiveness of the proposed SFF method. Microsc. Res. Tech. 77:959–963, 2014. © 2014 Wiley Periodicals, Inc. |
| |
| Keywords: | shape from focus focus measure guided filtering 3D shape recovery |
|
|
