Segmentation of virus particle candidates in transmission electron microscopy images

Kylberg, Gustaf; Uppström, Mats; Hedlund, Kjell‐Olof; Borgefors, Gunilla; Sintorn, Ida‐Maria

doi:10.1111/j.1365-2818.2011.03556.x

Cited by 46 publications

(24 citation statements)

References 23 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we evaluate the performance of the IDDL scheme on eight computer vision datasets, which are known to benefit from SPD-based descriptors. To this end, we use the following datasets, namely (i) the JHMDB action recognition [24], (ii) the HMDB action recognition [26] (iii) the KTH-TIPS2 dataset [32], (iv) Brodatz textures [35], (v) the Virus dataset [28], (vi) the SHREC 3D shape dataset [30], (vii) the Myometrium cancer dataset [41], and (viii) the Breast cancer dataset [41]. Below, we provide details about all the studied datasets and the way SPD descriptors are obtained on them.…”

Section: Methodsmentioning

confidence: 99%

Learning Discriminative αβ-Divergences for Positive Definite Matrices

Cherian

Stanitsas

Harandi

et al. 2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Symmetric positive definite (SPD) matrices are useful for capturing second-order statistics of visual data. To compare two SPD matrices, several measures are available, such as the affine-invariant Riemannian metric, Jeffreys divergence, Jensen-Bregman logdet divergence, etc.; however, their behaviors may be application dependent, raising the need of manual selection to achieve the best possible performance. Further and as a result of their overwhelming complexity for large-scale problems, computing pairwise similarities by clever embedding of SPD matrices is often preferred to direct use of the aforementioned measures. In this paper, we propose a discriminative metric learning framework, Information Divergence and Dictionary Learning (IDDL), that not only learns application specific measures on SPD matrices automatically, but also embeds them as vectors using a learned dictionary. To learn the similarity measures (which could potentially be distinct for every dictionary atom), we use the recently introduced αβ-logdet divergence, which is known to unify the measures listed above. We propose a novel IDDL objective, that learns the parameters of the divergence and the dictionary atoms jointly in a discriminative setup and is solved efficiently using Riemannian optimization. We showcase extensive experiments on eight computer vision datasets, demonstrating state-of-the-art performances.

show abstract

Section: Methodsmentioning

confidence: 99%

Learning Discriminative αβ-Divergences for Positive Definite Matrices

Cherian

Stanitsas

Harandi

et al. 2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…The virus types range from 25 to 270 nm in diameter and their shapes vary from icosahedral to highly pleomorphic (for example like boiled spaghetti). The image patches are disk shaped cutouts centred on automatically segmented virus particles using the segmentation method presented in [14]. The viruses have been imaged at different magnifications in the TEM with a pixel size ranging from 0.5 to 5 nm.…”

Section: Methodsmentioning

confidence: 99%

Virus Texture Analysis Using Local Binary Patterns and Radial Density Profiles

Kylberg

Uppström

Sintorn

2011

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

We investigate the discriminant power of two local and two global texture measures on virus images. The viruses are imaged using negative stain transmission electron microscopy. Local binary patterns and a multi scale extension are compared to radial density profiles in the spatial domain and in the Fourier domain. To assess the discriminant potential of the texture measures a Random Forest classifier is used. Our analysis shows that the multi scale extension performs better than the standard local binary patterns and that radial density profiles in comparison is a rather poor virus texture discriminating measure. Furthermore, we show that the multi scale extension and the profiles in Fourier domain are both good texture measures and that they complement each other well, that is, they seem to detect different texture properties. Combining the two, hence, improves the discrimination between virus textures.

show abstract

“…PCA was used to ensure both HASC features and φ m (x i ) dimensionalities are compatible. We followed the original evaluation protocol with the provided 10 splits described in [17]. Specifically, for each repetition, one split was used as the test and the rest as training.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

“…Analysis on EFS-DS and EFS-LR -The proposed EFS-DF Table 1. Average recognition accuracies and their standard deviations for the Object recognition (ETH80) [19], Action recognition (HDM05) [21], virus [17] and texture (Kylberg) datasets [16]. CDL, S H -SVM and HASC-SVM extract SPD manifold features, therefore cannot be used for Object Recognition dataset which uses Grassmann manifold.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

Explicit discriminative representation for improved classification of manifold features

Wiliem

Vemulapalli

Lovell

2016

Pattern Recognition Letters

View full text Add to dashboard Cite

This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. Research Highlights (Required) To create your highlights, please type the highlights against each \item command. • We study the problem of extracting Euclidean features for Riemannian manifolds • We propose two max-margin learning approaches to extract the features representation • The proposed methods outperform recent state-of-the-arts in various tasks

show abstract

Segmentation of virus particle candidates in transmission electron microscopy images

Cited by 46 publications

References 23 publications

Learning Discriminative αβ-Divergences for Positive Definite Matrices

Learning Discriminative αβ-Divergences for Positive Definite Matrices

Virus Texture Analysis Using Local Binary Patterns and Radial Density Profiles

Explicit discriminative representation for improved classification of manifold features

Contact Info

Product

Resources

About