T
Tanuja Sarode
Researcher at University of Mumbai
Publications - 140
Citations - 1346
Tanuja Sarode is an academic researcher from University of Mumbai. The author has contributed to research in topics: Wavelet transform & Vector quantization. The author has an hindex of 18, co-authored 140 publications receiving 1264 citations. Previous affiliations of Tanuja Sarode include Narsee Monjee Institute of Management Studies & Thadomal Shahani Engineering College.
Papers
More filters
Proceedings ArticleDOI
Identification of multi-spectral palmprints using energy compaction by Hybrid wavelet
TL;DR: A Hybrid wavelet, generated by using Kronecker product of two existing orthogonal transforms, Walsh and DCT to identify multi-spectral palmprints, can significantly improve the identification rates for palmprint images.
Journal ArticleDOI
Exemplar based Image Inpainting with Reduced Search Region
Jayesh A. Patel,Tanuja Sarode +1 more
TL;DR: This paper presents an algorithm which improves and extends the previously proposed algorithm and uses exemplar based image inpainting techniques for removing objects and cracks from the image.
Journal ArticleDOI
Performance Comparison of Speaker Identification Using DCT, Walsh, Haar on Full and Row Mean of Spectrogram
TL;DR: Comparison of all three transformation techniques on spectrograms shows that numbers of mathematical computations required for Walsh transform is much lesser than number of mathematical computation required in case of DCT on spectrogram, whereas, use of Haar transform drastically reduces the number of Mathematical computation with almost equal identification rate.
Hybrid watermarking of color images using dct- wavelet, dct and svd
TL;DR: DCT wavelet transform performs better than the previously proposed DWT-DCT-SVD based watermarking scheme wherein Haar functions are used as basis functions for wavelets transform.
Journal ArticleDOI
Fingerprint Identification using Sectorized Cepstrum Complex Plane
TL;DR: This paper proposes a simple yet effective technique for fingerprint identification that is image-based in which feature vectors of a fingerprint are extracted after sectorization of the cepstrum of a fingerprints and matched with those stored in the database.