Improving Deriche-style Recursive Gaussian Filters
Journal of Mathematical Imaging and Vision
Robust fusion of irregularly sampled data using adaptive normalized convolution
EURASIP Journal on Applied Signal Processing
Facial Action Unit Recognition by Exploiting Their Dynamic and Semantic Relationships
IEEE Transactions on Pattern Analysis and Machine Intelligence
Improving the SIFT descriptor with smooth derivative filters
Pattern Recognition Letters
ISCGAV'08 Proceedings of the 8th conference on Signal processing, computational geometry and artificial vision
An Analysis of Gabor Detection
ICIAR '09 Proceedings of the 6th International Conference on Image Analysis and Recognition
Text area detection in digital documents images using textural features
CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
Local invariant object localization based on a reduced color space
SSIP'05 Proceedings of the 5th WSEAS international conference on Signal, speech and image processing
Improving accuracy of optical flow of heeger's original method on biomedical images
ICIAR'10 Proceedings of the 7th international conference on Image Analysis and Recognition - Volume Part I
A real-time gabor primal sketch for visual attention
IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part I
Efficient denoising of piecewise-smooth signals with forward-backward FIR smoothers
AMERICAN-MATH'12/CEA'12 Proceedings of the 6th WSEAS international conference on Computer Engineering and Applications, and Proceedings of the 2012 American conference on Applied Mathematics
SIFER: Scale-Invariant Feature Detector with Error Resilience
International Journal of Computer Vision
Hi-index | 35.68 |
We present a stable, recursive algorithm for the Gabor (1946) filter that achieves-to within a multiplicative constant-the fastest possible implementation. For a signal consisting of N samples, our implementation requires O(N) multiply-and-add (MADD) operations, that is, the number of computations per input sample is constant. Further, the complexity is independent of the values of σ, and ω in the Gabor kernel, and the coefficients of the recursive equation have a simple, closed-form solution given σ and ω. Our implementation admits not only a "forward" Gabor filter but an inverse filter that is also O(N) complexity.