Trainable COSFIRE Filters for Keypoint Detection and Pattern Recognition

@article{Azzopardi2013TrainableCF,
  title={Trainable COSFIRE Filters for Keypoint Detection and Pattern Recognition},
  author={G. Azzopardi and N. Azzopardi},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2013},
  volume={35},
  pages={490-503}
}
  • G. Azzopardi, N. Azzopardi
  • Published 2013
  • Medicine, Computer Science
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Background: Keypoint detection is important for many computer vision applications. Existing methods suffer from insufficient selectivity regarding the shape properties of features and are vulnerable to contrast variations and to the presence of noise or texture. Methods: We propose a trainable filter which we call Combination Of Shifted FIlter REsponses (COSFIRE) and use for keypoint detection and pattern recognition. It is automatically configured to be selective for a local contour pattern… CONTINUE READING
    Inhibition-augmented trainable COSFIRE filters for keypoint detection and object recognition
    5
    Combination filter for keypoint detection and pattern recognition in traffic visual surveillance
    Color-blob-based COSFIRE filters for object recognition
    27
    Pattern Recognition Using Combination ofShifted Filter Response
    Place and Object Recognition by CNN-Based COSFIRE Filters
    2
    Pattern Recognition Using Combination of Shifted Filter Response
    COSFIRE: A Brain-Inspired Approach to Visual Pattern Recognition
    2

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 55 REFERENCES
    Nonlinear operator for oriented texture
    226
    Contour detection based on nonclassical receptive field inhibition
    348
    Biologically motivated computationally intensive approaches to image pattern recognition
    109
    Object recognition from local scale-invariant features
    14529
    The Role of Non-CRF Inhibition in Contour Detection
    6