| 1. |
- Granlund, Gösta, 1941-, et al.
(författare)
-
HiperLearn : A High Performance Learning Architecture
- 2002
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- A new architecture for learning systems has been developed. A number of particular design features in combination result in a very high performance and excellent robustness. The architecture uses a monopolar channel information representation. The channel representation implies a partially overlapping mapping of signals into a higher-dimensional space, such that a flexible but continuous restructuring mapping can be made. The high-dimensional mapping introduces locality in the information representation, which is directly available in wavelets or filter outputs. Single level maps using this representation can produce closed decision regions, thereby eliminating the need for costly back-propagation. The monopolar property implies that data only utilizes one polarity, say positive values, in addition to zero, allowing zero to represent no information. This leads to an efficient sparse representation.The processing mode of the architecture is association where the mapping of feature inputs onto desired state outputs is learned from a representative training set. The sparse monopolar representation together with locality, using individual learning rates, allows a fast optimization, as the system exhibits linear complexity. Mapping into multiple channels gives a strategy to use confidence statements in data, leading to a low sensitivity to noise in features. The result is an architecture allowing systems with a complexity of some hundred thousand features described by some hundred thousand samples to be trained in typically less than an hour. Experiments that demonstrate functionality and noise immunity are presented. The architecture has been applied to the design of hyper complex operations for view centered object recognition in robot vision.
|
|
| 2. |
- Johansson, Björn, 1971-, et al.
(författare)
-
A Repeatability Test for Two Orientation Based Interest Point Detectors
- 2004
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This report evaluates the stability of two image interest point detectors, star-pattern points and points based on the fourth order tensor. The Harris operator is also included for comparison. Different image transformations are applied and the repeatability of points between a reference image and each of the transformed images are computed. The transforms are plane rotation, change in scale, change in view, and change in lightning conditions. We conclude that the result largely depends on the image content. The star-pattern points and the fourth order tensor models the image as locally straight lines, while the Harris operator is based on simple/non-simple signals. The two methods evaluated here perform equally well or better than the Harris operator if the model is valid, and perform worse otherwise.
|
|
| 3. |
- Johansson, Björn, 1971-
(författare)
-
A Survey on : Contents Based Search in Image Databases
- 2000
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This survey contains links and facts to a number of projects on content based search in image databases around the world today. The main focus is on what kind of image features is used but also the user interface and the users possibility to interact with the system (i.e. what 'visual language' is used).
|
|
| 4. |
- Johansson, Björn, 1971-
(författare)
-
Backprojection of Some Image Symmetries Based on a Local Orientation Description
- 2000
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Some image patterns, e.g. circles, hyperbolic curves, star patterns etc., can be described in a compact way using local orientation. The features mentioned above is part of a family of patterns called rotational symmetries. This theory can be used to detect image patterns from the local orientation in double angle representation of an images. Some of the rotational symmetries are described originally from the local orientation without being designed to detect a certain feature. The question is then: given a description in double angle representation, what kind of image features does this description correspond to? This 'inverse', or backprojection, is not unambiguous - many patterns has the same local orientation description. This report answers this question for the case of rotational symmetries and also for some other descriptions.
|
|
| 5. |
- Johansson, Björn, 1971-, et al.
(författare)
-
Object Recognition in 3D Laser Radar Data using Plane triplets
- 2005
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This report describes a method to detect and recognize objects from 3D laser radar data. The method is based on local descriptors computed from triplets of planes that are estimated from the data set. Each descriptor that is computed on query data is compared with descriptors computed on object model data to get a hypothesis of object class and pose. An hypothesis is either verified or rejected using a similarity measure between the model data set and the query data set.
|
|
| 6. |
- Johansson, Björn, 1971-
(författare)
-
On Classification: Simultaneously Reducing Dimensionality and Finding Automatic Representation using Canonical Correlation
- 2001
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This report describes an idea based on the work in [1], where an algorithm for learning automatic representation of visual operators is presented. The algorithm in [1] uses canonical correlation to find a suitable subspace in which the signal is invariant to some desired properties. This report presents a related approach specially designed for classification problems. The goal is to find a subspace in which the signal is invariant within each class, and at the same time compute the class representation in that subspace. This algorithm is closely related to the one in [1], but less computationally demanding, and it is shown that the two algorithms are equivalent if we have equal number of training samples for each class. Even though the new algorithm is designed for pure classification problems it can still be used to learn visual operators as will be shown in the experiment section. [1] M. Borga. Learning Multidimensional Signal Processing. PhD thesis, Linköping University, Sweden, SE-581 83 Linköping, 1998. Dissertation No 531, ISBN 91-7219-202-X.
|
|
| 7. |
- Johansson, Björn, 1971-
(författare)
-
On Sparse Associative Networks : A Least Squares Formulation
- 2001
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This report is a complement to the working document [1], where a sparse associative network is described. This report shows that the net learning rule in [1] can be viewed as the solution to a weighted least squares problem. This means that we can apply the theory framework of least squares problems, and compare the net rule with some other iterative algorithms that solve the same problem. The learning rule is compared with the gradient search algorithm and the RPROP algorithm in a simple synthetic experiment. The gradient rule has the slowest convergence while the associative and the RPROP rules have similar convergence. The associative learning rule has a smaller initial error than the RPROP rule though.It is also shown in the same experiment that we get a faster convergence if we have a monopolar constraint on the solution, i.e. if the solution is constrained to be non-negative. The least squares error is a bit higher but the norm of the solution is smaller, which gives a smaller interpolation error.The report also discusses a generalization of the least squares model, which include other known function approximation models.[1] G Granlund. Paralell Learning in Artificial Vision Systems: Working Document. Dept. EE, Linköping University, 2000
|
|
| 8. |
- Johansson, Björn, 1971-, et al.
(författare)
-
Patch-Duplets for Object Recognition and Pose Estimation
- 2003
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This report describes a view-based method for object recognition and estimation of object pose in still images. The method is based on feature vector matching and clustering. A set of interest points, in this case star-patterns, is detected and combined into pairs. A pair of patches, centered around each point in the pair, is extracted from a local orientation image. The patch orientation and size depends on the relative positions of the points, which make them invariant to translation, rotation, and scale. Each pair of patches constitutes a feature vector. The method is demonstrated on a number of real images.
|
|
| 9. |
- Johansson, Björn, 1971-
(författare)
-
Representing Multiple Orientations in 2D with Orientation Channel Histograms
- 2002
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- The channel representation is a simple yet powerful representation of scalars and vectors. It is especially suited for representation of several scalars at the same time without mixing them up.This report is partly intended to serve as a simple illustration of the channel representation. The report shows how the channels can be used to represent multiple orientations in two dimensions. The idea is to make a channel representation of the local orientation angle computed from the image gradient. The representation basically becomes an orientation histogram with overlapping bins.The channel histogram is compared with the orientation tensor, which is another representation of orientation. The performance comparable to tensors in the simple signal case, but decreases slightly for increasing number of channels. The channel histogram outperforms the tensors on non-simple signals.
|
|
| 10. |
- Johansson, Björn, 1971-, et al.
(författare)
-
The Application of an Oblique-Projected Landweber Method to a Model of Supervised Learning
- 2004
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This report brings together a novel approach to some computer vision problems and a particular algorithmic development of the Landweber iterative algorithm. The algorithm solves a class of high-dimensional, sparse, and constrained least-squares problems, which arise in various computer vision learning tasks, such as object recognition and object pose estimation. The algorithm has recently been applied to these problems, but it has been used rather heuristically. In this report we describe the method and put it on firm mathematical ground. We consider a convexly constrained weighted least-squares problem and propose for its solution a projected Landweber method which employs oblique projections onto the closed convex constraint set. We formulate the problem, present the algorithm and work out its convergence properties, including a rate-of-convergence result. The results are put in perspective of currently available projected Landweber methods. The application to supervised learning is described, and the method is evaluated in a function approximation experiment.
|
|
