Corner detection, matching and transformed image identification      

 

We have proposed three contour-based corner detectors so far. The first one is on curvature scale-space (CSS)-based technique and we parameterize the planar curves with the affine-length. The improved detector is known as ARCSS (affine-resilient CSS) detector and offers better performance under affine transformations than the original CSS detector by Mokhtarian & Suomela (PAMI 1998).

 

The second detector is a new detector that uses chord scale-space and estimate the discrete curvature using the chord-to-point distance accumulation technique (CPDA). The proposed CPDA corner detector offers the best effectiveness (robustness) under both geometric and signal processing attacks.

 

As the CPDA detector is slow, we recently proposed its faster version and hopefully its code will be available soon. We also proposed a geometric corner matching algorithm. The corner detection and matching algorithms are then applied to identify the transformed images for a given test image.

 

The MATLAB implementations of detection and matching algorithms are available at Mathworks site.

Data set is available for research purposes only.

 

Publications:

1. M. Awrangjeb, G. Lu and C. S. Fraser, “Performance comparisons of contour-based detectors,” IEEE Trans. On Image Processing, Revised and Resubmitted (RQ), February 2012.

2. M. Awrangjeb and G. Lu, “Techniques for Efficient and Effective Transformed Image Identification,” Journal of Visual Communication and Image Representation, 20(8), 511-520, 2009.

3. M. Awrangjeb and G. Lu, “Robust Image Corner Detection Based on the Chord-to-Point Distance Accumulation Technique,” IEEE Transactions on Multimedia, 10(6), 1059–1072, 2008. [ABSTRACT] [PDF]

4. M. Awrangjeb and G. Lu, “An Improved Curvature Scale-Space Corner Detector and a Robust Corner Matching Approach for Transformed Image Identification,” IEEE Transactions on Image Processing, 17(12), 2425–2441, 2008. [ABSTRACT] [PDF]

5. M. Awrangjeb, G. Lu and C. S. Fraser, “A Comparative Study on Contour-based Corner Detectors,” Digital Image Computing: Techniques and Applications (DICTA 2010), 1-3 Dec 2010, Sydney, Australia.

6. M. Awrangjeb, G. Lu and C. S. Fraser, “A Fast Corner Detector Based on the Chord-to-Point Distance Accumulation Technique,” Digital Image Computing: Techniques and Applications (DICTA 2009), 519-525, 2009, Melbourne, Australia.

7. M. Awrangjeb and G. Lu, “Efficient and Effective Transformed Image Identification,” IEEE International Conference on Multimedia Signal Processing (MMSP 2008), Cairns, Australia, 563–568, 2008. [ABSTRACT] [PDF]

8. M. Awrangjeb and G. Lu, “Effective Corner Matching for Transformed Image Identification,” Pacific-Rim Conference on Multimedia 2007 (PCM'07), Hong Kong, 765–774, 2007. [ABSTRACT] [PDF]

9. M. Awrangjeb, G. Lu, and M. M. Murshed, “An Affine Resilient Curvature Scale-Space Corner Detector,” 32nd IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2007), Hawaii, USA, 1233–1236, 2007. [ABSTRACT] [PDF]

10. M. Awrangjeb and G. Lu, “A Robust Corner Matching Technique,” International Conference on Multimedia and Expo (ICME 2007), Beijing, China, 1483–1486, 2007. [ABSTRACT] [PDF]