Image Registration Using Mexican-Hat Wavelets and Invariant Moments

Sarvaiya, Jignesh N.; Patnaik, Suprava; Goklani, Hemant S.

doi:10.1007/978-3-642-19542-6_112

Cited by 2 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this technique is not very efficient when searching for identical point-pairs and eliminating mismatching. Furthermore, this method suffers from shifting that results from down sampling in the space scale extrema detection stage; in contrast NSCT [5] is fully shift-invariant and robust to noise. Based on the aforementioned issues, we propose a new approach combining SIFT and NSCT.…”

Section: Introductionmentioning

confidence: 99%

NSCT edge Enhancement for SIFT key points extraction

2014

View full text Add to dashboard Cite

International audienceImage registration is a key step for matching or mosaicing two or more images taken at different times, and/or with different sensors, hence the need for automatic methods arises. In this work, we present an efficient registration method based on the Non-Subsampled Contourlet Transform (NSCT) combined with the Scale Invariant Feature transform (SIFT) to extract robust local control points. Because NSCT is a shift-invariant multidirectional transform, it is used to extract edges at both spatial and directional resolutions. A comparative study is established between SIFT and NSCT-SIFT and experimental results show clearly that the proposed method (NSCT-SIFT) improves the registration accuracy

show abstract

Section: Introductionmentioning

confidence: 99%

NSCT edge Enhancement for SIFT key points extraction

2014

View full text Add to dashboard Cite

show abstract

Non-Contact Fingerprint Template Protection Using DFT Combined Random Projection

Zannou

Djara

Vianou

2022

International Journal of Security and Privacy in Pervasive Computing

View full text Add to dashboard Cite

In view of the different dangers to which users of contactless biometric systems are exposed, we have developed a contactless secure revocable model based on random projection and DFT (Discret Fourier Tansformation) to enhance contactless fingerprint authentication. Two matrices emerge, namely that corresponding to the terminations and that corresponding to the bifurcations. These matrices are then transformed in a first time thanks to the random projection. In a second time we apply to them the Discret Fourier Transformation called the DFT.This proposed non-contact revocable fingerprint model meets the requirements of revocability, diversity, security and non-reversibility. The evaluation of our model through its results gives the most promising results compared to those existing. The equal error rate (EER) obtained are respectively equal to 0.19% for FVC2002 DB1, 1% for FVC2002 DB2, 4.29% for FVC2002 DB3 and 9.01% for FVC2004 DB2.

show abstract

Image Registration Using Mexican-Hat Wavelets and Invariant Moments

Cited by 2 publications

References 8 publications

NSCT edge Enhancement for SIFT key points extraction

NSCT edge Enhancement for SIFT key points extraction

Non-Contact Fingerprint Template Protection Using DFT Combined Random Projection

Contact Info

Product

Resources

About