Papers by Maja Temerinac-Ott
This paper presents the results of the SHREC'10 Protein Models Classification Track. The aim of t... more This paper presents the results of the SHREC'10 Protein Models Classification Track. The aim of this track is to evaluate how well 3D shape recognition algorithms can classify protein structures according to the CATH [CSL * 08] superfamily classification. Five groups participated in this track, using a total of six methods, and for each method a set of ranked predictions was submitted for each classification task. The evaluation of each method is based on the nearest neighbour and area under the curve(AUC) metrics.
2009 Conference Record of the Forty-Third Asilomar Conference on Signals, Systems and Computers, 2009
In this paper a framework for multichannel image restoration based on optimization of the structu... more In this paper a framework for multichannel image restoration based on optimization of the structural similarity (SSIM) index is presented. The SSIM index describes the similarity of images more appropriately for the human visual system than the mean square error (MSE). It has not yet been explored for the multi channel restoration task. The construction of an optimization algorithm is difficult due to the non-linearity of the SSIM measure. The existing solution based on a quasi-convex problem formulation is successfully extended for the multichannel image restoration. The correctness of the algorithm is verified on sample images and it is shown that multi-view information can significantly improve the restoration results.
2010 20th International Conference on Pattern Recognition, 2010
Registration of point clouds is required in the processing of large biological data sets. The tra... more Registration of point clouds is required in the processing of large biological data sets. The tradeoff between computation time and accuracy of the registration is the main challenge in this task.
2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2011
A framework for fast multiview fusion of Single Plane Illumination Microscopy (SPIM) images based... more A framework for fast multiview fusion of Single Plane Illumination Microscopy (SPIM) images based on a spatiallyvariant point spread function (PSF) model is presented. For the multiview fusion a new algorithm based on the regularized Lucy-Richardson deconvolution and the Overlap-Save method is developed and tested on SPIM images. In the algorithm the image is decomposed into small blocks which are processed separately thus saving memory space and allowing for parallel processing.
2012 9th IEEE International Symposium on Biomedical Imaging (ISBI), 2012
We propose to use a kernel intensity penalizer (KIP) in the blind maximum likelihood expectation ... more We propose to use a kernel intensity penalizer (KIP) in the blind maximum likelihood expectation maximization (MLEM) deconvolution scheme. With this very general kernel regularization term, we can stabilize the blind MLEM scheme even for the deconvolution of wide-field microscopic recordings. No complex prior point spread function models are needed. We combine state of the art optimization schemes using Tikhonov-Miller and TV regularization with our new kernel regularization. The proposed method improves the conventional deconvolution methods in terms of SNR on real and simulated datasets.
2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013
With volumetric data from widefield fluorescence microscopy, many emerging questions in biologica... more With volumetric data from widefield fluorescence microscopy, many emerging questions in biological and biomedical research are being investigated. Data can be recorded with high temporal resolution while the specimen is only exposed to a low amount of phototoxicity. These advantages come at the cost of strong recording blur caused by the infinitely extended point spread function (PSF). For widefield microscopy, its magnitude only decays with the square of the distance to the focal point and consists of an airy bessel pattern which is intricate to describe in the spatial domain. However, the Fourier transform of the incoherent PSF (denoted as Optical Transfer Function (OTF)) is well localized and smooth. In this paper, we present a blind deconvolution method that improves results of state-of-theart deconvolution methods on widefield data by exploiting the properties of the widefield OTF.
International Journal of Computer Mathematics, 2007
The tremendous growth of 3D data models available on the internet requires more skills for fast r... more The tremendous growth of 3D data models available on the internet requires more skills for fast retrieval and classification algorithms. Especially, the problem of finding structural similarities between proteins automatically, in order to predict their functional similarity is a challenging task. In this paper a new algebraic method for structural comparison between proteins based on invariant features computed by group integration with spherical harmonics and D-Wigner matrices is proposed. Our goal is to achieve good classification without alignment by using intrinsic, pose invariant features. We compare our method to DALI, PRIDE and the Gauss Integral-method in a classification and search task. Additionally we provide a web interface to test the proposed method.
IEEE Transactions on Image Processing, 2000
We propose an algorithm for 3-D multiview deblurring using spatially variant point spread functio... more We propose an algorithm for 3-D multiview deblurring using spatially variant point spread functions (PSFs). The algorithm is applied to multiview reconstruction of volumetric microscopy images. It includes registration and estimation of the PSFs using irregularly placed point markers (beads). We formulate multiview deblurring as an energy minimization problem subject to L1-regularization. Optimization is based on the regularized Lucy-Richardson algorithm, which we extend to deal with our more general model. The model parameters are chosen in a profound way by optimizing them on a realistic training set. We quantitatively and qualitatively compare with existing methods and show that our method provides better signal-to-noise ratio and increases the resolution of the reconstructed images.
This paper presents the results of the SHREC'10 Protein Models Classification Track. The aim of t... more This paper presents the results of the SHREC'10 Protein Models Classification Track. The aim of this track is to evaluate how well 3D shape recognition algorithms can classify protein structures according to the CATH [CSL * 08] superfamily classification. Five groups participated in this track, using a total of six methods, and for each method a set of ranked predictions was submitted for each classification task. The evaluation of each method is based on the nearest neighbour and area under the curve(AUC) metrics.
Uploads
Papers by Maja Temerinac-Ott