Representation of local geometry in the visual system
Biological Cybernetics
The Design and Use of Steerable Filters
IEEE Transactions on Pattern Analysis and Machine Intelligence
Local Grayvalue Invariants for Image Retrieval
IEEE Transactions on Pattern Analysis and Machine Intelligence
Feature Detection with Automatic Scale Selection
International Journal of Computer Vision
Recursive Gaussian Derivative Filters
ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
A representation for visual information with application to machine vision
A representation for visual information with application to machine vision
Measuring visual motion from image sequences
Measuring visual motion from image sequences
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Hi-index | 0.00 |
The characteristic (or intrinsic) scale of a local image pattern is the scale parameter at which the Laplacian provides a local maximum. Nearly every position in an image will exhibit a small number of such characteristic scales. Computing a vector of Gaussian derivatives (a Gaussian jet) at a characteristic scale provides a scale invariant feature vector for tracking, matching, indexing and recognition. However, the computational cost of directly searching the scale axis for the characteristic scale at each image position can be prohibitively expensive. We describe a fast method for computing a vector of Gaussian derivatives that are normalised to the characteristic scale at each pixel. This method is based on a scale equivariant half-octave binomial pyramid. The characteristic scale for each pixel is determined by an interpolated maximum in the Difference of Gaussian as a function of scale. We show that interpolation between pixels across scales can be used to provide an accurate estimate of the intrinsic scale at each image point. We present an experimental evaluation that compares the scale invariance of this method to direct computation using FIR filters, and to an implementation using recursive filters. With this method we obtain a scale normalised Gaussian Jet at video rate for a 1/4 size PAL image on a standard 1.5 Ghz Pentium workstation.