Analysis of focus measure operators for shape-from-focus

@article{Pertuz2013AnalysisOF,
  title={Analysis of focus measure operators for shape-from-focus},
  author={Said Pertuz and Domenec Puig and Miguel {\'A}ngel Garc{\'i}a},
  journal={Pattern Recognit.},
  year={2013},
  volume={46},
  pages={1415-1432}
}
Performance analysis of focus measures in a SFF-inspired approach for sparse scene reconstruction
TLDR
Results of performance evaluation of four different focus measures most commonly used in SFF and auto-focus algorithms are presented, carried out based on two different performance evaluation criteria namely root mean square error and computation time.
Reliability measure for shape-from-focus
Performance Analysis of Laplacian based Focus Measures in a Parallax Affected SFF Scenario
TLDR
This paper presents significant results of performance evaluation of four different focus measures based on the second order image derivative, the Image Laplacian, carried out under various operating conditions such as different spatial resolution, window size, contrast changes, gray level saturation and camera noise.
Optimizing Image Focus for Shape From Focus Through Locally Weighted Non-Parametric Regression
TLDR
A local regression is proposed as a new fitting method for the focus curves, obtained by using one of the focus measure operators, by utilizing the weighted least squares regression as non-parametric regression.
A new focus measure operator for enhancing image focus in 3D shape recovery
TLDR
A new focus measure operator based on the adaptive sum of weighted modified Laplacian, used frequently among various focus measure operators for estimating the focus levels in a sequence of images, is proposed.
All in Focus Image Generation based on New Focusing Measure Operators
TLDR
Two new focusing measure operators are suggested to be used for SFF and it is shown that the suggested operators’ performances are as analogous to that of ST.
Analyzing Image Focus using Deep Neural Network for 3D Shape Recovery
TLDR
Deep Neural Networks (DNN) have been employed to measure the amount of focus in the image stack and the results are compared with commonly used FMs by employing RMSE, Correlation and $Q$ index to establish that the proposed method is not only efficient but more accurate.
Enhancing Shape from Focus-Measure-Fusion and Sparse Representation
TLDR
A novel shape estimation method is proposed which fuses individual shape estimates obtained by multiple focus measures, and reconstructs an improved shape map in a patch-wise manner, within a sparse representation (SR) framework.
Optimal Sampling for Shape from Focus by Using Gaussian Process Regression
TLDR
A Gaussian process regression method is proposed to get 3D shape from the minimum number of 2D images, which is applied to fit focus curves, which are obtained by applying one of focus measure operators.
...
...

References

SHOWING 1-10 OF 88 REFERENCES
Shape from Focus
TLDR
The shape from focus method presented here uses different focus levels to obtain a sequence of object images and suggests shape fromfocus to be an effective approach for a variety of challenging visual inspection tasks.
Shape from Focus through Laplacian Using 3D Window
TLDR
This paper proposes to use 3D windows instead of 2D windows for detecting the high frequency components in the images and shows that the proposed algorithm using 3D window gives better depth map than the previous algorithms using2D windows.
Nonlinear Approach for Enhancement of Image Focus Volume in Shape From Focus
TLDR
This paper suggests the use of iterative 3-D anisotropic nonlinear diffusion filtering (ANDF) to enhance the image focus volume and utilizes the local structure of the focus values to suppress the noise while preserving edges.
Accurate Recovery of Three-Dimensional Shape from Image Focus
TLDR
The shape of the FIS is determined by searching for a shape which maximizes a focus measure, which results in more accurate shape recovery than the traditional methods.
Selecting the Optimal Focus Measure for Autofocusing and Depth-From-Focus
A method is described for selecting the optimal focus measure with respect to gray-level noise from a given set of focus measures in passive autofocusing and depth-from-focus applications. The method
Sampling for Shape from Focus in Optical Microscopy
  • S. M. Mannan, T. Choi
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2012
TLDR
Interframe distance (or sampling step size) criteria for SFF systems have been formulated and light ray focusing is approximated by the use of a Gaussian beam followed by the formulation of a sampling expression using Nyquist sampling, and a fitting function for focus curves is obtained.
3D Shape from Focus and Depth Map Computation Using Steerable Filters
TLDR
Quantitative and qualitative performance analyses validate enhanced performance of the proposed novel technique to compute SFF and depth map using steerable filters.
Adaptive shape from focus with an error estimation in light microscopy
  • F. Helmli, S. Scherer
  • Computer Science
    ISPA 2001. Proceedings of the 2nd International Symposium on Image and Signal Processing and Analysis. In conjunction with 23rd International Conference on Information Technology Interfaces (IEEE Cat.
  • 2001
TLDR
A new adaptive reconstruction scheme for calculating range images as well as sharp images is presented and a new so called focus measures are introduced and are compared to the classic approaches.
...
...