1. |
- Chanda, Sukalpa, et al.
(author)
-
Face Recognition - A One-Shot Learning Perspective
- 2019
-
In: 15th IEEE Conference on Signal Image Technology and Internet based Systems. - 9781728156866 ; , s. 113-119
-
Conference paper (peer-reviewed)abstract
- Ability to learn from a single instance is something unique to the human species and One-shot learning algorithms try to mimic this special capability. On the other hand, despite the fantastic performance of Deep Learning-based methods on various image classification problems, performance often depends having on a huge number of annotated training samples per class. This fact is certainly a hindrance in deploying deep neural network-based systems in many real-life applications like face recognition. Furthermore, an addition of a new class to the system will require the need to re-train the whole system from scratch. Nevertheless, the prowess of deep learned features could also not be ignored. This research aims to combine the best of deep learned features with a traditional One-Shot learning framework. Results obtained on 2 publicly available datasets are very encouraging achieving over 90% accuracy on 5-way One-Shot tasks, and 84% on 50-way One-Shot problems.
|
|
2. |
- Chanda, Sukalpa, et al.
(author)
-
Finding Logo and Seal in Historical Document Images - : An Object Detection based Approach
- 2019
-
In: The 5th Asian Conference on Pattern Recognition (ACPR 2019). ; , s. 821-834
-
Conference paper (peer-reviewed)abstract
- Logo and Seal serves the purpose of authenticating and referring to the source of a document. This strategy was also prevalent in the medieval period. Different algorithm exists for detection of logo and seal in document images. A close look into the present state-of-the-art methods reveals that those methods were focused toward detection of logo and seal in contemporary document images. However, such methods are likely to underperform while dealing with historical documents. This is due to the fact that historical documents are attributed with additional challenges like extra noise, bleed-through effect, blurred foreground elements and low contrast. The proposed method frames the problem of the logo and seals detection in an object detection framework. Using a deep-learning technique it counters earlier mentioned problems and evades the need for any pre-processing stage like layout analysis and/or binarization in the system pipeline. The experiments were conducted on historical images from 12th to the 16th century and the results obtained were very encouraging for detecting logo in historical document images. To the best of our knowledge, this is the first attempt on logo detection in historical document images using an object-detection based approach.
|
|
3. |
- Ohlsson, Henrik, 1981-, et al.
(author)
-
Enabling Bio-Feedback using Real-Time fMRI
- 2008
-
In: 47th IEEE Conference on Decision and Control, 2008, CDC 2008. - Linköping : IEEE. - 9781424431236 ; , s. 3336-3341
-
Conference paper (peer-reviewed)abstract
- Despite the enormous complexity of the human mind, fMRI techniques are able to partially observe the state of a brain in action. In this paper we describe an experimental setup for real-time fMRI in a bio-feedback loop. One of the main challenges in the project is to reach a detection speed, accuracy and spatial resolution necessary to attain sufficient bandwidth of communication to close the bio-feedback loop. To this end we have banked on our previous work on real-time filtering for fMRI and system identification, which has been tailored for use in the experiment setup. In the experiments presented the system is trained to estimate where a person in the MRI scanner is looking from signals derived from the visual cortex only. We have been able to demonstrate that the user can induce an action and perform simple tasks with her mind sensed using real-time fMRI. The technique may have several clinical applications, for instance to allow paralyzed and "locked in" people to communicate with the outside world. In the meanwhile, the need for improved fMRI performance and brain state detection poses a challenge to the signal processing community. We also expect that the setup will serve as an invaluable tool for neuro science research in general.
|
|
4. |
- Ayyalasomayajula, Kalyan Ram, 1980-, et al.
(author)
-
CalligraphyNet: Augmenting handwriting generation with quill based stroke width
- 2019
-
Other publication (other academic/artistic)abstract
- Realistic handwritten document generation garners a lot ofinterest from the document research community for its abilityto generate annotated data. In the current approach we haveused GAN-based stroke width enrichment and style transferbased refinement over generated data which result in realisticlooking handwritten document images. The GAN part of dataaugmentation transfers the stroke variation introduced by awriting instrument onto images rendered from trajectories cre-ated by tracking coordinates along the stylus movement. Thecoordinates from stylus movement are augmented with thelearned stroke width variations during the data augmentationblock. An RNN model is then trained to learn the variationalong the movement of the stylus along with the stroke varia-tions corresponding to an input sequence of characters. Thismodel is then used to generate images of words or sentencesgiven an input character string. A document image thus cre-ated is used as a mask to transfer the style variations of the inkand the parchment. The generated image can capture the colorcontent of the ink and parchment useful for creating annotated data.
|
|
5. |
- Ayyalasomayajula, Kalyan Ram, 1980-
(author)
-
Learning based segmentation and generation methods for handwritten document images
- 2019
-
Doctoral thesis (other academic/artistic)abstract
- Computerized analysis of handwritten documents is an active research area in image analysis and computer vision. The goal is to create tools that can be available for use at university libraries and for researchers in the humanities. Working with large collections of handwritten documents is very time consuming and many old books and letters remain unread for centuries. Efficient computerized methods could help researchers in history, philology and computer linguistics to cost-effectively conduct a whole new type of research based on large collections of documents. The thesis makes a contribution to this area through the development of methods based on machine learning. The passage of time degrades historical documents. Humidity, stains, heat, mold and natural aging of the materials for hundreds of years make the documents increasingly difficult to interpret. The first half of the dissertation is therefore focused on cleaning the visual information in these documents by image segmentation methods based on energy minimization and machine learning. However, machine learning algorithms learn by imitating what is expected of them. One prerequisite for these methods to work is that ground truth is available. This causes a problem for historical documents because there is a shortage of experts who can help to interpret and interpret them. The second part of the thesis is therefore about automatically creating synthetic documents that are similar to handwritten historical documents. Because they are generated from a known text, they have a given facet. The visual content of the generated historical documents includes variation in the writing style and also imitates degradation factors to make the images realistic. When machine learning is trained on synthetic images of handwritten text, with a known facet, in many cases they can even give an even better result for real historical documents.
|
|
6. |
|
|
7. |
|
|
8. |
- Brun, Anders, 1976-, et al.
(author)
-
A tensor-like representation for averaging, filtering and interpolation of 3D object orientation data
- 2005
-
In: Image Processing, 2005. ICIP 2005. IEEE International Conference on (Volume:3 ). - 0780391349 ; , s. 1092-1095
-
Conference paper (peer-reviewed)abstract
- Averaging, filtering and interpolation of 3-D object orientation data is important in both computer vision and computer graphics, for instance to smooth estimates of object orientation and interpolate between keyframes in computer animation. In this paper we present a novel framework in which the non-linear nature of these problems is avoided by embedding the manifold of 3-D orientations into a 16-dimensional Euclidean space. Linear operations performed in the new representation can be shown to be rotation invariant, and defining a projection back to the orientation manifold results in optimal estimates with respect to the Euclidean metric. In other words, standard linear filters, interpolators and estimators may be applied to orientation data, without the need for an additional machinery to handle the non-linear nature of the problems. This novel representation also provides a way to express uncertainty in 3-D orientation, analogous to the well known tensor representation for lines and hyperplanes.
|
|
9. |
- Brun, Anders, 1976-, et al.
(author)
-
Clustering Fiber Traces Using Normalized Cuts
- 2004
-
In: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2004. - Berlin, Heidelberg : Springer Berlin/Heidelberg. - 9783540229766 - 9783540301356 ; , s. 368-375
-
Conference paper (peer-reviewed)abstract
- In this paper we present a framework for unsupervised segmentation of white matter fiber traces obtained from diffusion weighted MRI data. Fiber traces are compared pairwise to create a weighted undirected graph which is partitioned into coherent sets using the normalized cut (Ncut) criterion. A simple and yet effective method for pairwise comparison of fiber traces is presented which in combination with the Ncut criterion is shown to produce plausible segmentations of both synthetic and real fiber trace data. Segmentations are visualized as colored stream-tubes or transformed to a segmentation of voxel space, revealing structures in a way that looks promising for future explorative studies of diffusion weighted MRI data.
|
|
10. |
- Brun, Anders, 1976-, et al.
(author)
-
Coloring of DT-MRI fiber traces using Laplacian Eigenmaps
- 2003
-
In: Computer Aided Systems Theory - EUROCAST 2003. - Berlin, Heidelberg : Springer Berlin/Heidelberg. - 9783540202219 - 9783540452102 ; , s. 518-529
-
Conference paper (peer-reviewed)abstract
- We propose a novel post processing method for visualization of fiber traces from DT-MRI data. Using a recently proposed non-linear dimensionality reduction technique, Laplacian eigenmaps [3], we create a mapping from a set of fiber traces to a low dimensional Euclidean space. Laplacian eigenmaps constructs this mapping so that similar traces are mapped to similar points, given a custom made pairwise similarity measure for fiber traces. We demonstrate that when the low-dimensional space is the RGB color space, this can be used to visualize fiber traces in a way which enhances the perception of fiber bundles and connectivity in the human brain.
|
|
11. |
- Brun, Anders, 1976-
(author)
-
Extending Distance Computation - Propagating Derivatives
- 2010
-
In: Proceedings SSBA 2010. - Uppsala : Centre for Image Analysis. ; , s. 39-42
-
Conference paper (other academic/artistic)abstract
- In this paper we present a technique to extend distance computation algorithms that compute global distances from a series of local updates. This includes algorithms such as the fast marching method (FMM) and the chamfering algorithm for weighted distances. In addition to the value of a distance function or distance map, we derive formulas to compute the gradient and higher order partial derivatives of the distance function within the same framework. The approach is based on symbolic differentiation of the update scheme, which makes it general and straight forward to apply to almost any distance computation scheme. The main result is a novel set of ``derivative maps'' that are computed along with the ordinary distance maps. Apart from the theory itself, these maps and this technique may be used to compute skeletons and parameterizations such as Riemannian Normal Coordinates and Gauss Normal Coordinates.
|
|
12. |
- Brun, Anders, 1976-, et al.
(author)
-
Fast manifold learning based on Riemannian normal coordinates
- 2005
-
In: Image Analysis. - Berlin, Heidelberg : Springer Berlin/Heidelberg. - 9783540263203 - 9783540315667 ; , s. 920-
-
Conference paper (peer-reviewed)abstract
- We present a novel method for manifold learning, i.e. identification of the low-dimensional manifold-like structure present in a set of data points in a possibly high-dimensional space. The main idea is derived from the concept of Riemannian normal coordinates. This coordinate system is in a way a generalization of Cartesian coordinates in Euclidean space. We translate this idea to a cloud of data points in order to perform dimension reduction. Our implementation currently uses Dijkstra’s algorithm for shortest paths in graphs and some basic concepts from differential geometry. We expect this approach to open up new possibilities for analysis of e.g. shape in medical imaging and signal processing of manifold-valued signals, where the coordinate system is “learned” from experimental high-dimensional data rather than defined analytically using e.g. models based on Lie-groups.
|
|
13. |
|
|
14. |
- Brun, Anders, 1976-, et al.
(author)
-
Intrinsic and Extrinsic Means on the Circle -- a Maximum Likelihood Interpretation
- 2007
-
In: ICASSP 2007. IEEE International Conference on Acoustics, Speech and Signal Processing, 2007. - New York, USA : IEEE. - 1424407273 ; , s. III-1053-III-1056
-
Conference paper (peer-reviewed)abstract
- For data samples in Rn, the mean is a well known estimator. When the data set belongs to an embedded manifold M in Rn, e.g. the unit circle in R2, the definition of a mean can be extended and constrained to M by choosing either the intrinsic Riemannian metric of the manifold or the extrinsic metric of the embedding space. A common view has been that extrinsic means are approximate solutions to the intrinsic mean problem. This paper study both means on the unit circle and reveal how they are related to the ML estimate of independent samples generated from a Brownian distribution. The conclusion is that on the circle, intrinsic and extrinsic means are maximum likelihood estimators in the limits of high SNR and low SNR respectively
|
|
15. |
|
|
16. |
- Brun, Anders, 1976-
(author)
-
Manifold learning and representations for image analysis and visualization
- 2006
-
Licentiate thesis (other academic/artistic)abstract
- We present a novel method for manifold learning, i.e. identification of the low-dimensional manifold-like structure present in a set of data points in a possibly high-dimensional space. The main idea is derived from the concept of Riemannian normal coordinates. This coordinate system is in a way a generalization of Cartesian coordinates in Euclidean space. We translate this idea to a cloud of data points in order to perform dimension reduction. Our implementation currently uses Dijkstra's algorithm for shortest paths in graphs and some basic concepts from differential geometry. We expect this approach to open up new possibilities for analysis of e.g. shape in medical imaging and signal processing of manifold-valued signals, where the coordinate system is learned from experimental high-dimensional data rather than defined analytically using e.g. models based on Lie-groups.We propose a novel post processing method for visualization of fiber traces from DT-MRI data. Using a recently proposed non-linear dimensionality reduction technique, Laplacian eigenmaps (Belkin and Niyogi, 2002), we create a mapping from a set of fiber traces to a low dimensional Euclidean space. Laplacian eigenmaps constructs this mapping so that similar traces are mapped to similar points, given a custom made pairwise similarity measure for fiber traces. We demonstrate that when the low-dimensional space is the RGB color space, this can be used to visualize fiber traces in a way which enhances the perception of fiber bundles and connectivity in the human brain.
|
|
17. |
- Brun, Anders, 1976-
(author)
-
Manifolds in Image Science and Visualization
- 2007
-
Doctoral thesis (other academic/artistic)abstract
- A Riemannian manifold is a mathematical concept that generalizes curved surfaces to higher dimensions, giving a precise meaning to concepts like angle, length, area, volume and curvature. A glimpse of the consequences of a non-flat geometry is given on the sphere, where the shortest path between two points – a geodesic – is along a great circle. Different from Euclidean space, the angle sum of geodesic triangles on the sphere is always larger than 180 degrees.Signals and data found in applied research are sometimes naturally described by such curved spaces. This dissertation presents basic research and tools for the analysis, processing and visualization of such manifold-valued data, with a particular emphasis on future applications in medical imaging and visualization.Two-dimensional manifolds, i.e. surfaces, enter naturally into the geometric modelling of anatomical entities, such as the human brain cortex and the colon. In advanced algorithms for processing of images obtained from computed tomography (CT) and ultrasound imaging (US), images themselves and derived local structure tensor fields may be interpreted as two- or three-dimensional manifolds. In diffusion tensor magnetic resonance imaging (DT-MRI), the natural description of diffusion in the human body is a second-order tensor field, which can be related to the metric of a manifold. A final example is the analysis of shape variations of anatomical entities, e.g. the lateral ventricles in the brain, within a population by describing the set of all possible shapes as a manifold.Work presented in this dissertation include: Probabilistic interpretation of intrinsic and extrinsic means in manifolds. A Bayesian approach to filtering of vector data, removing noise from sampled manifolds and signals. Principles for the storage of tensor field data and learning a natural metric for empirical data.The main contribution is a novel class of algorithms called LogMaps, for the numerical estimation of logp (x) from empirical data sampled from a low-dimensional manifold or geometric model embedded in Euclidean space. The logp (x) function has been used extensively in the literature for processing data in manifolds, including applications in medical imaging such as shape analysis. However, previous approaches have been limited to manifolds where closed form expressions of logp (x) have been known. The introduction of the LogMap framework allows for a generalization of the previous methods. The application of LogMaps to texture mapping, tensor field visualization, medial locus estimation and exploratory data analysis is also presented.
|
|
18. |
|
|
19. |
- Brun, Anders, 1976-, et al.
(author)
-
Similar Tensor Arrays : A Framework for Storage of Tensor Array Data
- 2009. - 1
-
In: Tensors in Image Processing and Computer Vision. - London : Springer. - 9781848822986 - 9781848822993 ; , s. 407-428
-
Book chapter (other academic/artistic)abstract
- Abstract This chapter describes a framework for storage of tensor array data, useful to describe regularly sampled tensor fields. The main component of the framework, called Similar Tensor Array Core (STAC), is the result of a collaboration between research groups within the SIMILAR network of excellence. It aims to capture the essence of regularly sampled tensor fields using a minimal set of attributes and can therefore be used as a “greatest common divisor” and interface between tensor array processing algorithms. This is potentially useful in applied fields like medical image analysis, in particular in Diffusion Tensor MRI, where misinterpretation of tensor array data is a common source of errors. By promoting a strictly geometric perspective on tensor arrays, with a close resemblance to the terminology used in differential geometry, (STAC) removes ambiguities and guides the user to define all necessary information. In contrast to existing tensor array file formats, it is minimalistic and based on an intrinsic and geometric interpretation of the array itself, without references to other coordinate systems.
|
|
20. |
- Brun, Anders, 1976-, et al.
(author)
-
Tensor Glyph Warping : Visualizing Metric Tensor Fields using Riemannian Exponential Maps
- 2009. - XVII
-
In: Visualization and Processing of Tensor Fields. - Berlin Heidelberg : Springer. - 9783540883777 - 9783540883784 ; , s. 139-160
-
Book chapter (other academic/artistic)abstract
- The Riemannian exponential map, and its inverse the Riemannian logarithm map, can be used to visualize metric tensor fields. In this chapter we first derive the well-known metric sphere glyph from the geodesic equation, where the tensor field to be visualized is regarded as the metric of a manifold. These glyphs capture the appearance of the tensors relative to the coordinate system of the human observer. We then introduce two new concepts for metric tensor field visualization: geodesic spheres and geodesically warped glyphs. These extensions make it possible not only to visualize tensor anisotropy, but also the curvature and change in tensor-shape in a local neighborhood. The framework is based on the exp p (v i ) and log p (q) maps, which can be computed by solving a second-order ordinary differential equation (ODE) or by manipulating the geodesic distance function. The latter can be found by solving the eikonal equation, a nonlinear partial differential equation (PDE), or it can be derived analytically for some manifolds. To avoid heavy calculations, we also include first- and second-order Taylor approximations to exp and log. In our experiments, these are shown to be sufficiently accurate to produce glyphs that visually characterize anisotropy, curvature, and shape-derivatives in sufficiently smooth tensor fields where most glyphs are relatively similar in size.
|
|
21. |
- Brun, Anders, 1976-, et al.
(author)
-
Using Importance Sampling for Bayesian Feature Space Filtering
- 2007
-
In: Proceedings of the 15th Scandinavian conference on image analysis. - Berlin, Heidelberg : Springer-Verlag. - 9783540730392 ; , s. 818-827
-
Conference paper (peer-reviewed)abstract
- We present a one-pass framework for filtering vector-valued images and unordered sets of data points in an N-dimensional feature space. It is based on a local Bayesian framework, previously developed for scalar images, where estimates are computed using expectation values and histograms. In this paper we extended this framework to handle N-dimensional data. To avoid the curse of dimensionality, it uses importance sampling instead of histograms to represent probability density functions. In this novel computational framework we are able to efficiently filter both vector-valued images and data, similar to e.g. the well-known bilateral, median and mean shift filters.
|
|
22. |
|
|
23. |
- Brun, Laurent, 1976-
(author)
-
Le Miroir historial de Jean de Vignay : Édition critique du livre I (Prologue) et du livre 5 (Histoire d'Alexandre le Grand)
- 2010
-
Doctoral thesis (other academic/artistic)abstract
- In the mid-thirteenth century, the Dominican friar Vincent of Beauvais compiled the largest encyclopedia ever during the Middle Ages: the fourfold Speculum maius, whose Latin Speculum historiale became by far its most copied and widespread volume. During the 1320's and early 1330's, Jean de Vignay translated the whole Speculum historiale into French and dedicated the work to the French queen Joan of Burgundy, wife of Philip of Valois. This dissertation consists in a partial critical edition of this French translation, the Miroir historial. Two books have been selected: Book I, which contains Vincent's prologue to the whole encyclopedia, and Book V, featuring one of the longest medieval histories of Alexander the Great. Book I's obvious interest lies in that it is the most detailed account of an encyclopedist's work, providing us with one of the most valuable insights into a compiler's mind and philosophy. Book V is certainly one the most influential histories of the Macedonian emperor, which inspired many late medieval and Renaissance authors, although very few scholars have looked into it and thoroughly examined its structure, contents and sources. This dissertation features two previously unpublished books in addition to giving access to the most extensive extract from the Miroir historial that has ever appeared in print. The edition includes a thorough examination and identification of every source used by the translator but also by Vincent de Beauvais. The investigation shows, among other things, that nearly three quarters of the history of Alexander are in fact an abridged version of the account found in Helinand of Froidmont's Chronicon (Books XVII and XVIII), to which Vincent added additional sources, mainly theological and philosophical. The edition is based on three fourteenth-century manuscripts and includes a detailed analysis of the translator's life and works, a glossary as well as an index of all the proper nouns.
|
|
24. |
- Cammoun, Leila, et al.
(author)
-
A Review of Tensors and Tensor Signal Processing
- 2009. - 1
-
In: Tensors in Image Processing and Computer Vision. - London : Springer. - 9781848822986 ; , s. 1-32
-
Book chapter (other academic/artistic)abstract
- Tensors have been broadly used in mathematics and physics, since they are a generalization of scalars or vectors and allow to represent more complex properties. In this chapter we present an overview of some tensor applications, especially those focused on the image processing field. From a mathematical point of view, a lot of work has been developed about tensor calculus, which obviously is more complex than scalar or vectorial calculus. Moreover, tensors can represent the metric of a vector space, which is very useful in the field of differential geometry. In physics, tensors have been used to describe several magnitudes, such as the strain or stress of materials. In solid mechanics, tensors are used to define the generalized Hooke’s law, where a fourth order tensor relates the strain and stress tensors. In fluid dynamics, the velocity gradient tensor provides information about the vorticity and the strain of the fluids. Also an electromagnetic tensor is defined, that simplifies the notation of the Maxwell equations. But tensors are not constrained to physics and mathematics. They have been used, for instance, in medical imaging, where we can highlight two applications: the diffusion tensor image, which represents how molecules diffuse inside the tissues and is broadly used for brain imaging; and the tensorial elastography, which computes the strain and vorticity tensor to analyze the tissues properties. Tensors have also been used in computer vision to provide information about the local structure or to define anisotropic image filters.
|
|
25. |
- Herberthson, Magnus, 1963-, et al.
(author)
-
Pairs of orientation in the plane
- 2006
-
In: SSBA Symposium on Image Analysis,2006. ; , s. 97-100
-
Conference paper (other academic/artistic)
|
|