A comparative study on the application of SIFT, SURF, BRIEF and ORB for 3D surface reconstruction of electron microscopy images

Tafti, Ahmad P.; Baghaie, Ahmadreza; Kirkpatrick, Andrew B.; Holz, Jessica D.; Owen, Heather A.; D’Souza, Roshan; Yu, Zeyun

doi:10.1080/21681163.2016.1152201

Cited by 21 publications

(14 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This step is necessary for the process of dense matching needed for high quality 3D reconstruction. In sparse feature-based approaches used for 3D reconstruction of microscopic samples [32, 64], computation of fundamental matrix and the subsequent projective transformation is computationally efficient. This is due to small number of matching points in comparison to the total number of pixels in the images.…”

Section: Resultsmentioning

confidence: 99%

“…Sparse feature-based approaches track the movements of distinct feature points in the input images in order to compute the fundamental matrix and projective transformation [32, 64]. To generate a dense disparity map, similar to that of created by our approach for a better comparison of the performance, the sparse disparity values are interpolated employing a Delaunay triangulation-based interpolation method.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Three-dimensional reconstruction of highly complex microscopic samples using scanning electron microscopy and optical flow estimation

et al. 2017

Self Cite

View full text Add to dashboard Cite

Scanning Electron Microscope (SEM) as one of the major research and industrial equipment for imaging of micro-scale samples and surfaces has gained extensive attention from its emerge. However, the acquired micrographs still remain two-dimensional (2D). In the current work a novel and highly accurate approach is proposed to recover the hidden third-dimension by use of multi-view image acquisition of the microscopic samples combined with pre/post-processing steps including sparse feature-based stereo rectification, nonlocal-based optical flow estimation for dense matching and finally depth estimation. Employing the proposed approach, three-dimensional (3D) reconstructions of highly complex microscopic samples were achieved to facilitate the interpretation of topology and geometry of surface/shape attributes of the samples. As a byproduct of the proposed approach, high-definition 3D printed models of the samples can be generated as a tangible means of physical understanding. Extensive comparisons with the state-of-the-art reveal the strength and superiority of the proposed method in uncovering the details of the highly complex microscopic samples.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Three-dimensional reconstruction of highly complex microscopic samples using scanning electron microscopy and optical flow estimation

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Combined (3)(4)(5), (3)(4)(5)(6) and (3-7) we can obtain the derivative between the error E and the weight of the…”

Section: E Bmentioning

confidence: 99%

“…  continuously according to the formula (3)(4)(5) , it can spread the error to the bottom, and the error rate of change l  can be derived from the first layer according to and (3-4):…”

Section: E Bmentioning

confidence: 99%

“…In the aspect of feature extraction, the researchers used the basic characteristics of the image, including color feature, texture feature and shape feature [3]. With the further research, more and more advanced features are applied to image recognition, including SIFT features, SURF features, multi scale sparse features and so on [4]; in the aspect of classification recognition, the early machine learning models have achieved good results, including K nearest neighbor, clustering, support vector machine, artificial neural network, naive Bayesian method and so on [5]. In recent years, with the deepening of research, more and more researchers use in-depth learning model for feature extraction and recognition, which has made great progress in image recognition.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Algorithmic Research for Image Annotation Based on Region Convolution Neural Network

Yuan¹

2016

IJSIP

View full text Add to dashboard Cite

show abstract

An Enhanced Image Fusion Model Based on Fuzzy Transform for 3D Imaging Applications

Hassan

Mesbah

Darwish

2021

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

A comparative study on the application of SIFT, SURF, BRIEF and ORB for 3D surface reconstruction of electron microscopy images

Cited by 21 publications

References 34 publications

Three-dimensional reconstruction of highly complex microscopic samples using scanning electron microscopy and optical flow estimation

Three-dimensional reconstruction of highly complex microscopic samples using scanning electron microscopy and optical flow estimation

Algorithmic Research for Image Annotation Based on Region Convolution Neural Network

An Enhanced Image Fusion Model Based on Fuzzy Transform for 3D Imaging Applications

Contact Info

Product

Resources

About