We consider various algorithmic solutions to image registration based on the alignment of a set of feature points. We present a number of enhancements to a branch-and-bound algorithm introduced by Mount, Netanyahu, and Le Moigne (Pattern Recognition, Vol. 32, 1999, pp. 17-38), which presented a registration algorithm based on the partial Hausdorff distance. Our enhancements include a new distance measure, the discrete Gaussian mismatch, and a number of improvements and extensions to the above search algorithm. Both distance measures are robust to the presence of outliers, that is, data points from either set that do not match any point of the other set. We present experimental studies, which show that the new distance measure considered can provide significant improvements over the partial Hausdorff distance in instances where the number of outliers is not known in advance. These experiments also show that our other algorithmic improvements can offer tangible improvements. We demonstrate the algorithm's efficacy by considering images involving different sensors and different spectral bands, both in a traditional framework and in a multiresolution framework.
The new approach to apply psychoacoustic models to the wavelet based audio digital watermarking is proposed in this paper. In the scheme, the additive watermarking technique is used to embed a unique pseudorandom sequence, considered as a watermark, into the transformed domain of audio signal. The watermark strength is properly adjusted based on weighting factors derived from the proposed psychoacoustic models. The results show that at the equivalent quality of the watermarked audio, judged by the human hearing system, the robustness of the embedded watermark was increased by up to 97.1 % and 21.3 %, compared to the results obtained from the scheme with nonpsychoacoustic model and the previous psychoacoustic model, respectively.
We present in this paper a number of new enhancements to a branch-and-bound algorithm given by Mount, Netanyahu, and Le Moigne [8] for feature matching. We introduce a new distance measure, which is more robust to the presence of outliers than the previously used measure, as well as a new variant of the search algorithm and a new search strategy. We also present experimental results, which show that these enhancements offer significant tangible improvements in performance.
Abstract. Most of the feature point matching techniques considers only the number of matches. The higher number of matches is, the better results are. However, reliability and quality of the matching is addressed in a few techniques. So, finding the good matches of the pairs of points from the two given point sets is one of the main issue of feature point matching. This paper presents new approach to obtain reliable and good matches. The high quality of matching can be achieved when the matches are spread all over the entire point set. Therefore, we proposed to use the distribution of the matches to verify the quality of the matching. The preliminary results show that our proposed algorithm significantly outperform SIFT even when the results of SIFT are enhanced using RANSAC.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.