Dictionary redundancy elimination

Rebollo-Neira, Laura

doi:10.1049/ip-vis:20040294

Cited by 14 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For constructingP W ⊥ there are a number of possibilities. In the example we present here the set {η i } n i=1 is linearly dependent and we have used the technique for dictionary redundancy elimination proposed in [14]. MATLAB code for its implementation is available at [15].…”

Section: Implementation Details and Numerical Examplementioning

confidence: 99%

Oblique Matching Pursuit

Rebollo-Neira

2007

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

A method for selecting a suitable subspace for discriminating signal components through an oblique projection is proposed. The selection criterion is based on the consistency principle introduced by M. Unser and A. Aldroubi and extended by Y. Elder. An effective implementation of this principle for the purpose of subspace selection is achieved by updating of the dual vectors yielding the corresponding oblique projector.Comment: Last version- as it will appear in IEEE SPL. IEEE Signal Processing Letters (in press

show abstract

Section: Implementation Details and Numerical Examplementioning

confidence: 99%

Oblique Matching Pursuit

Rebollo-Neira

2007

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

show abstract

“…As discussed in [4], in order to reduce numerical errors the vectors |ψ k are conveniently computed by Modified Gram Schmidt procedure or Modified Gram Schmidt with pivoting [4,6].…”

Section: Notation Background and Motivation To The Approachmentioning

confidence: 99%

“…, N (and therefore the coefficients c N n ) depend on the number N of total waveforms, they should be recalculated when this number is enlarged or reduced. This feature of non-orthogonal expansions is discussed in [2,3,4], where a recursive methodology is introduced for transforming the reciprocal set αN n ; n = 1, . .…”

Section: Introductionmentioning

confidence: 99%

Backward adaptive biorthogonalization

Rebollo-Neira

2004

International Journal of Mathematics and Mathematical Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, in practice the learned dictionaries are shown to be superior in various applications of signal and image processing domains [1,2]. The learning algorithms often result much fine-tuned dictionaries and provide significantly better performance.…”

Section: Introductionmentioning

confidence: 99%

Optimizing visual dictionaries for effective image retrieval

Arun

Govindan

2015

Int J Multimed Info Retr

View full text Add to dashboard Cite

Characterizing images by high-level concepts from a learned visual dictionary is extensively used in image classification and retrieval. This paper deals with inferring discriminative visual dictionaries for effective image retrieval and examines a non-negative visual dictionary learning scheme towards this direction. More specifically, a nonnegative matrix factorization framework with 0 -sparseness constraint on the coefficient matrix for optimizing the dictionary is proposed. It is a two-step iterative process composed of sparse encoding and dictionary enhancement stages. An initial estimate of the visual dictionary is updated in each iteration with the proposed 0 -constraint gradient projection algorithm. A desirable attribute of this formulation is an adaptive sequential dictionary initialization procedure. This leads to a sharp drop down of the approximation error and a faster convergence. Finally, the proposed dictionary optimization scheme is used to derive a compact image representation for the retrieval task. A new image signature is obtained by projecting local descriptors on to the basis elements of the optimized visual dictionary and then aggregating the resulting sparse encodings in to a single feature vector. Experimental results on various benchmark datasets show that the proposed system can infer enhanced visual dictionaries and the derived image feature vector can achieve better retrieval results as compared to state-of-the-art techniques.

show abstract

Dictionary redundancy elimination

Cited by 14 publications

References 13 publications

Oblique Matching Pursuit

Oblique Matching Pursuit

Backward adaptive biorthogonalization

Optimizing visual dictionaries for effective image retrieval

Contact Info

Product

Resources

About