Multi-Level Discrete Cosine Transform for Content-Based Image Retrieval by Support Vector Machines

Li, Yong; Chen, Xiujuan; Fu, Xuezheng; Belkasim, Saeid

doi:10.1109/icip.2007.4379510

Cited by 5 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the recent years, support vector machines (Vapnik 1995;Scholkopf and Smola 2002;Shawe-Taylor and Cristianini 2004) have been successfully used in many application domains (Camps-Valls et al 2007;Sebald and Bucklew 2000;Melgani and Bruzzone 2004). The applicability of SVMs has been also demonstrated for content-based image classification (Tzotsos 2006;Li et al 2007). Although the SVM approach has a number of properties that make it attractive, it also has drawbacks.…”

Section: Introductionmentioning

confidence: 96%

Content-based image classification with wavelet relevance vector machines

2009

View full text Add to dashboard Cite

This paper introduces the use of relevance vector machines (RVMs) for content-based image classification and compares it with the conventional support vector machine (SVM) approach. Different wavelet kernels are included in the formulation of the RVM. We also propose a new wavelet-based feature extraction method that extracts lesser number of features as compared to other wavelet-based feature extraction methods. Experimental results confirm the superiority of RVM over SVM in terms of the trade-off between slightly reduced accuracy but substantially enhanced sparseness of the solution, and also the ease of free parameters tuning.

show abstract

Section: Introductionmentioning

confidence: 96%

Content-based image classification with wavelet relevance vector machines

2009

View full text Add to dashboard Cite

show abstract

“…In contrast, spectral methods of texture analysis are more tolerable and robust to noise. The common spectral techniques are Fourier transform (FT) [28,29], discrete cosine transform (DCT) [30], wavelet transform [31][32][33] and Gabor filters [4,5,13,28]. Recent researchers are analysing textures using curvelet transform, which represents the latest research result on multi-resolution analysis [5,6,34,35].…”

Section: Introductionmentioning

confidence: 99%