Multiscale Nonlinear Decomposition: The Sieve Decomposition Theorem
IEEE Transactions on Pattern Analysis and Machine Intelligence
On the Handling of Spatial and Temporal Scales in Feature Tracking
SCALE-SPACE '97 Proceedings of the First International Conference on Scale-Space Theory in Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
A Comparison of Affine Region Detectors
International Journal of Computer Vision
IJCAI'83 Proceedings of the Eighth international joint conference on Artificial intelligence - Volume 2
ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing
Computer assisted diagnosis of microcalcifications in mammograms: a scale-space approach
MICAI'11 Proceedings of the 10th Mexican international conference on Advances in Artificial Intelligence - Volume Part I
| Hi-index | 0.00 |
Finding correspondence regions between images is fundamental to recovering three dimensional information from multiple frames of the same scene and content based image retrieval. To be good, correspondence regions should be easily found, richly characterised and have a good trade-off between density and uniqueness. Maximally stable extremal regions (MSER's) are amongst the best known methods to tackle this problem. Here, we present an implementation of the sieve algorithm that not only generates MSER's but can also generate stable salient contours (SSC's) in different ways. The sieve decomposes the image according to local grayscale intensities and produces a tree in nearly O(N) where N is the number of pixels. The exact shape of the tree depends on the criteria used to control the merging of extremal regions with less extreme neighbours. We call the resulting data structure a 'structured image'. Here, a structured image in which MSER's are embedded is compared with those associated with two types of SSC's. The correspondence rate generated by each of these methods is compared using the standard evaluation method due to Mikalajczyk and the results show that SSC's identified using colour and texture moments are generally better than the others.