Nonlinear Approach for Enhancement of Image Focus Volume in Shape From Focus

Abstract

Mostly, shape-from-focus algorithms use local averaging using a fixed rectangle window to enhance the initial focus volume. In this linear filtering, the window size affects the accuracy of the depth map. A small window is unable to suppress the noise properly, whereas a large window oversmoothes 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 3-D anisotropic nonlinear diffusion filtering (ANDF) to enhance the image focus volume. In contrast to linear filtering, ANDF 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.

A focus fusion framework with anisotropic depth map smoothing

“…Furthermore, we demonstrate the results of our method for data sets from Mahmood and Choi [18] shown in Figures 9 and 10. For the synthetic data we compare the quantitative results in terms of the root mean square error to the method [18] (Table 6). As their result we show their best performance with the modified Laplacian as a focus measure.…”

“…Unfortunately this may also cause smoothing of important image structures such that the resulting images appear blurred and not sharp everywhere. Hence, researchers came up with the idea of not applying the smoothness constraint on the resulting image itself, but on the per-pixel decision of the in-focus areas: In [13,14,15,16,17,18] the authors determine an initial decision map by means of a specific sharpness criterion. Subsequently they segment these maps into regions that belong to the same input frames.…”

“…Mahmood et al [17] propose a combination of different focus measures for constructing the optimal decision map through genetic programming. Mahmood and Choi [18] employ 3-D anisotropic diffusion to enhance the input images, and in turn, to obtain an accurate decision map. Staying with the idea of operating on decision maps, Bae et al [21] apply bilateral filtering to this decision map in a related context.…”

Re-Ranking Based Image Categorization Using Saliency Driven Nonlinear Diffusion Filtering -A Review

“…After this apply Reranking which categorize the image. A nonlinear diffusion [12] which has been widely used in image de-noising, enhancement, etc, can preserve or even enhance the semantically important image structures, such as edges and lines.…”

Robust Depth Estimation and Image Fusion Based on Optimal Area Selection

“…In order to enhance the initial focus volume, usually, all focus values within a fixed window are aggregated [3,14]. However, this summation does not provide an accurate depth map [15–17]. It causes the over-smoothness of the object shape and, more likely, removes the edges.…”