Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
AFPAC '00 Proceedings of the Second International Workshop on Algebraic Frames for the Perception-Action Cycle
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Fast Multiple Object Tracking via a Hierarchical Particle Filter
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
P-Channels: Robust Multivariate M-Estimation of Large Datasets
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Accurate interpolation in appearance-based pose estimation
SCIA'07 Proceedings of the 15th Scandinavian conference on Image analysis
SSVM '09 Proceedings of the Second International Conference on Scale Space and Variational Methods in Computer Vision
Exploratory learning structures in artificial cognitive systems
Image and Vision Computing
Incremental computation of feature hierarchies
Proceedings of the 32nd DAGM conference on Pattern recognition
Hi-index | 0.00 |
Channel-coded feature maps (CCFMs) represent arbitrary image features using multi-dimensional histograms with soft and overlapping bins. This representation can be seen as a generalization of the SIFT descriptor, where one advantage is that it is better suited for computing derivatives with respect to image transformations. Using these derivatives, a local optimization of image scale, rotation and position relative to a reference view can be computed. If piecewise polynomial bin functions are used, e.g. B-splines, these histograms can be computed by first encoding the data set into a histogram-like representation with non-overlapping multi-dimensional monomials as bin functions. This representation can then be processed using multi-dimensional convolutions to obtain the desired representation. This allows to reuse much of the computations for the derivatives. By comparing the complexity of this method to direct encoding, it is found that the piecewise method is preferable for large images and smaller patches with few channels, which makes it useful, e.g. in early steps of coarse-to-fine approaches.