Efficiently Scaling Edge Detectors

Edge features within an image may be present at many scales, therefore application of edge detectors at multiple scales improves the accuracy of the detected edges. However, the computational complexity of application of the edge detection filter increases as the size of the filter increases. Using the finite element method in conjunction with integral images weillustrate a method of efficiently applying edge detection operators over an image at varying scales.

[1]  Bryan W. Scotney,et al.  Device Space Design for Efficient Scale-Space Edge Detection , 2002, International Conference on Computational Science.

[2]  Derek Bradley,et al.  Adaptive Thresholding using the Integral Image , 2007, J. Graph. Tools.

[3]  B. S. Manjunath,et al.  Multi-scale edge detection and image segmentation , 2005, 2005 13th European Signal Processing Conference.

[4]  Irwin Edward Sobel,et al.  Camera Models and Machine Perception , 1970 .

[5]  Horst Bischof,et al.  Fast Approximated SIFT , 2006, ACCV.

[6]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.

[7]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[8]  Hongbin Zha,et al.  Coarse-to-fine vision-based localization by indexing scale-Invariant features , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[9]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.