A focus fusion framework with anisotropic depth map smoothing

Boshtayeva, Madina; Hafner, David Zachary; Weickert, Joachim

doi:10.1016/j.patcog.2014.10.008

Cited by 12 publications

(8 citation statements)

References 37 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moeller et al (2015) have implemented a variational framework using total variation regularization. In a similar work related to depth processing, Boshtayeva et al (2015) have enforced depth map smoothing to recover all-in-focus image. Minhas et al (2009) simply applied median filtering to remove noise from the depth map.…”

Section: Related Workmentioning

confidence: 99%

“…For example, the modified-Laplacian FM (Nayar & Nakagawa, 1994) performs poorly in noisy conditions, whereas gray-level variance measure is more robust against noise (Pertuz et al, 2013). Thus, it seems suitable to apply different FM operators to compute the focus quality in the SFF so that if the performance of one operator degrades, another operator can supplement it (Boshtayeva et al, 2015). However, as it is not known in advance which operator is the most suitable for an underlying image sequence, it is hard to find out the most suitable operator for a particular image sequence.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Depth Hypotheses Fusion through 3D Weighted Least Squares in Shape from Focus

Ali

Mahmood

2021

Microsc Microanal

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Depth Hypotheses Fusion through 3D Weighted Least Squares in Shape from Focus

Ali

Mahmood

2021

Microsc Microanal

View full text Add to dashboard Cite

show abstract

“…The aggregation of focus measures is efficient to compute but it may not provide accurate depth map. On the other hand, several optimization and machine learning-based approaches have been proposed for better 3D shapes [10,[14][15][16][17]. Ahmad and Choi [14] proposed the usage of dynamic programming to obtain optimal focus measure.…”

Section: Related Workmentioning

confidence: 99%

“…It improves accuracy and obtains consistent depth maps, but it needs additional computations in local learning process. Recently, in [15], authors suggested anisotropic diffusion process with regularization to obtain better depth map. The above-mentioned approaches provide better depth maps as compared to the focus measure aggregation however, these are also computationally expensive.…”

Section: Related Workmentioning

confidence: 99%

An Efficient Neural Network for Shape from Focus with Weight Passing Method

2018

View full text Add to dashboard Cite

In this paper, we suggest an efficient neural network model for shape from focus along with weight passing (WP) method. The neural network model is simplified by reducing the input data dimensions and eliminating the redundancies in the conventional model. It helps for decreasing computational complexity without compromising on accuracy. In order to increase the convergence rate and efficiency, WP method is suggested. It selects appropriate initial weights for the first pixel randomly from the neighborhood of the reference depth and it chooses the initial weights for the next pixel by passing the updated weights from the present pixel. WP method not only expedites the convergence rate, but also is effective in avoiding the local minimization problem. Moreover, this proposed method may also be applied to neural networks with diverse configurations for better depth maps. The proposed system is evaluated using image sequences of synthetic and real objects. Experimental results demonstrate that the proposed model is considerably efficient and is able to improve the convergence rate significantly while the accuracy is comparable with the existing systems.

show abstract

“…The plane index of maxima of intensity response for each pixel position along z-axis is selected as the decision map from which to create the final composite image. In the literature, several methods have been studied for specific applications and imaging modalities [17,11,5,3]. Most of these fails when presented with very diverse specimen morphologies as they have been over-optimized for specific applications.…”

Section: Introductionmentioning

confidence: 99%

FastSME: Faster and Smoother Manifold Extraction from 3D Stack

Basu

Rexhepaj

Spassky

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

3D image stacks are routinely acquired to capture data that lie on undulating 3D manifolds yet processed in 2D by biologists. Algorithms to reconstruct the specimen morphology into a 2D representation from the 3D image volume are employed in such scenarios. In this paper, we present FastSME, which offers several improvements on the baseline SME algorithm which enables accurate 2D representation of data on a manifold from 3D volumes, however is computationally expensive. The improvements are achieved in terms of processing speed (3X-10X speed-up depending on image size), minimizing sensitivity to initialization, and also increases local smoothness of the recovered manifold resulting in better reconstructed 2D composite image. We compare the proposed FastSME against the baseline SME as well as other accessible state-of-theart tools on synthetic and real microscopy data. Our evaluation on multiple metrics demonstrates the efficiency of the presented method in maintaining fidelity of manifold shape and hence specimen morphology.

show abstract

A focus fusion framework with anisotropic depth map smoothing

Cited by 12 publications

References 37 publications

Depth Hypotheses Fusion through 3D Weighted Least Squares in Shape from Focus

Depth Hypotheses Fusion through 3D Weighted Least Squares in Shape from Focus

An Efficient Neural Network for Shape from Focus with Weight Passing Method

FastSME: Faster and Smoother Manifold Extraction from 3D Stack

Contact Info

Product

Resources

About