Effect of wavelet bases in texture classification using a tree-structured wavelet transform

DeBrunner, V.; Kadiyala, Madhavi

doi:10.1109/acssc.1999.831915

Cited by 7 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A pyramid-structured wavelet transform always decomposes the low frequency channel [8]. The tree-structured wavelet transform is a good analytical tool for hyperspectral image fusion and analysis.…”

Section: Introductionmentioning

confidence: 99%

Effects of Wavelets Selection on Performances of Hyperspectral Image Fusion

Wang

Shen

2006

2006 IEEE Instrumentation and Measurement Technology Conference Proceedings

View full text Add to dashboard Cite

Wavelet Transform (WT) based image fusion techniques have been widely studied and applied in hyperspectral data processing research. Generally, image decomposition, sub-image fusion, and image reconstruction are the main steps for a WT based image fusion. The performances of fusion methods are basically dependent on the fusion scheme and its related transform. In this paper, we mainly discuss the effects of wavelets on the image fusion process. The choice of wavelet bases for the wavelet transform approach is also discussed from a standpoint of fusion performances and computation cost.

show abstract

Section: Introductionmentioning

confidence: 99%

Effects of Wavelets Selection on Performances of Hyperspectral Image Fusion

Wang

Shen

2006

2006 IEEE Instrumentation and Measurement Technology Conference Proceedings

View full text Add to dashboard Cite

show abstract

“…According to Grzesik and Brol (2009), CWT can be useful to analyse roughness profiles generated by cutting processes. However, de Brunner and Kadiyala (1999) show that the choice of wavelet basis has a considerable effect on multi-scale surface decomposition. Among the various methods of numerical characterisation, the use of multi-scale analysis of the surface roughness data seems to be preferable because of its ability to characterise surface properties in a simple and efficient way (Stachowiak and Podsiadlo, 2001).…”

Section: Introductionmentioning

confidence: 99%

Multi-scale analysis of high precision surfaces by Stylus Profiler, Scanning White-Light Interferometry and Atomic Force Microscopy

et al. 2009

View full text Add to dashboard Cite

The relevance of three different techniques (Stylus Profiler (SP), Scanning White-Light Interferometry (SWLI) and Atomic Force Microscopy (AFM)) to characterise the topography of aluminium and hard steel surfaces, was investigated. Evolution of roughness parameters (Ra and Rt) was analysed according to the evaluation length. Asymptotic Ra values showed good agreement between data measured by SP and by AFM. SWLI data show important discrepancies with the other instruments due to their sensitivity to surface morphologies. AFM is the best instrument to detect micro-roughness but is limited by its maximum evaluation length. SP (2D measures) is, therefore, a good compromise to characterise surface morphologies over a wide spatial range.

show abstract

Wavelet frame-based feature extraction technique for improving classification accuracy

Raja¹,

Anand

Maithani

et al. 2009

J Indian Soc Remote Sens

View full text Add to dashboard Cite

Classification of textures in remotelysensed data has received considerable attention during the past decades. One difficulty of texture analysis in the past was lack of adequate tools to characterize different scales of textures effectively.Recent space-frequency analytical tools like the wavelet transform can effectively characterize the coupling of different scales in texture and helps to overcome the difficulty. This paper presents a wavelet-based texture classification technique that was applied to a Multi-Spectral Scanner (MSS) image of Madurai City, Tamil Nadu, India The feature extraction stage of the technique uses Lemarie-Battle orthogonal wavelets to derive a texture feature vector and this vector is input to a fuzzy-c means classifier, an unsupervised classification procedure. Four indices (user's accuracy, producer's accuracy, overall accuracy and Kappa co-efficient) are used to assess the accuracy of the classified data. The experiment results show that the performance of the presented technique is superior to the classical techniques.

show abstract

Effect of wavelet bases in texture classification using a tree-structured wavelet transform

Cited by 7 publications

References 1 publication

Effects of Wavelets Selection on Performances of Hyperspectral Image Fusion

Effects of Wavelets Selection on Performances of Hyperspectral Image Fusion

Multi-scale analysis of high precision surfaces by Stylus Profiler, Scanning White-Light Interferometry and Atomic Force Microscopy

Wavelet frame-based feature extraction technique for improving classification accuracy

Contact Info

Product

Resources

About