Feature Detection with Automatic Scale Selection
International Journal of Computer Vision
Branch Points in One-Dimensional Gaussian Scale Space
Journal of Mathematical Imaging and Vision
Space Scale Localization, Blur, and Contour-Based Image Coding
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Equivalence of Julesz and Gibbs Texture Ensembles
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
Minimax Entropy Principle and Its Application to Texture Modeling
Neural Computation
Maximum Entropy Image Reconstruction
IEEE Transactions on Computers
Toward a Full Probability Model of Edges in Natural Images
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
The Nonlinear Statistics of High-Contrast Patches in Natural Images
International Journal of Computer Vision - Special Issue on Computational Vision at Brown University
A Linear Image Reconstruction Framework Based on Sobolev Type Inner Products
International Journal of Computer Vision
Linear Image Reconstruction by Sobolev Norms on the Bounded Domain
International Journal of Computer Vision
SSVM '09 Proceedings of the Second International Conference on Scale Space and Variational Methods in Computer Vision
The Representation and Matching of Images Using Top Points
Journal of Mathematical Imaging and Vision
Content based image retrieval using multiscale top points a feasibility study
Scale Space'03 Proceedings of the 4th international conference on Scale space methods in computer vision
Real-time scale selection in hybrid multi-scale representations
Scale Space'03 Proceedings of the 4th international conference on Scale space methods in computer vision
Properties of Brownian image models in scale-space
Scale Space'03 Proceedings of the 4th international conference on Scale space methods in computer vision
Image reconstruction from multiscale critical points
Scale Space'03 Proceedings of the 4th international conference on Scale space methods in computer vision
Linear image reconstruction by Sobolev norms on the bounded domain
SSVM'07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision
Combining different types of scale space interest points using canonical sets
SSVM'07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision
Towards a new paradigm for motion extraction
ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part I
Optic flow from multi-scale dynamic anchor point attributes
ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part I
DSSCV'05 Proceedings of the First international conference on Deep Structure, Singularities, and Computer Vision
Discrete representation of top points via scale space tessellation
Scale-Space'05 Proceedings of the 5th international conference on Scale Space and PDE Methods in Computer Vision
A linear image reconstruction framework based on sobolev type inner products
Scale-Space'05 Proceedings of the 5th international conference on Scale Space and PDE Methods in Computer Vision
On image reconstruction from multiscale top points
Scale-Space'05 Proceedings of the 5th international conference on Scale Space and PDE Methods in Computer Vision
International Journal of Computer Vision
Good match exploration using triangle constraint
Pattern Recognition Letters
Uniqueness Results for Image Reconstruction from Features on Curves in α-Scale Spaces
Journal of Mathematical Imaging and Vision
| Hi-index | 0.00 |
According to the Marr paradigm [10], visual processing is performed by low-level feature detection followed by higher level task dependent processing. In this case, any two images exhibiting identical features will yield the same result of the visual processing. The set of images exhibiting identical features form an equivalence class: a metameric class [7]. We choose from this class the (in some precise sense) simplest image as a representative. The complexity of this simplest image may in turn be used for analyzing the information content of features. We show examples of images reconstructed from various scale-space features, and show that a low number of simple differential features carries suficient information for reconstructing images close to identical to the human observer. The paper presents direct methods for reconstruction of minimal variance representatives, and variational methods for computation of maximum entropy and maximum a posteriori representatives based on priors for natural images. Finally, conclusions on the information content in blobs and edges are indicated.