Dense Gradient-based Features (DeGraF) for Computationally Efficient and Invariant Feature Extraction in Real-time Applications
(2016)
Presentation / Conference Contribution
Katramados, I., & Breckon, T. (2016). Dense Gradient-based Features (DeGraF) for Computationally Efficient and Invariant Feature Extraction in Real-time Applications. In Proc. Int. Conf. on Image Processing (300-304). https://doi.org/10.1109/ICIP.2016.7532367
We propose a computationally efficient approach for the extraction of dense gradient-based features based on the use of localized intensity-weighted centroids within the image. Whilst prior work concentrates on sparse feature derivations or computati... Read More about Dense Gradient-based Features (DeGraF) for Computationally Efficient and Invariant Feature Extraction in Real-time Applications.