Contourlet

About: Contourlet is a research topic. Over the lifetime, 3533 publications have been published within this topic receiving 38980 citations.

Speckle Noise Removal Using Contourlets

Abstract: Speckle noise affects all coherent imaging systems including medical ultrasound. In medical images, noise suppression is a particularly delicate and difficult task. A trade off between noise reduction and the preservation of actual image features has to be made in a way that enhances the diagnostically relevant image content. Even though wavelets have been extensively used for denoising speckle images, we found that denoising using Contourlets gives much better performance in terms of SNR. It is shown that the proposed speckle noise removal using contourlets has superior performance in both the speckle reduction and edge preservation. We compare our technique with current state-of-the-art wavelet thresholding method applied on actual ultrasound medical images and we quantify the achieved performance improvement.

Medical Image Denoising using X-lets

Abstract: Wavelets are proved to be well adapted for 1-D signal but can only capture limited directional information in 2D due to its poor orientation selectivity Transforms like Curvelets and Contourlets have very high degree of directional specificity which is necessary for medical images These transforms are based on certain anisotropic scaling principle which is quite different from the isotropic scaling of wavelets Simulation test carried out on medical images like Ultrasound images, Magnetic Resonance images and Computerized Tomography scan images, show that better denoising results were obtained by Curvelets and Contourlets, than with wavelets, in terms of Mean Square Error, Signal to Noise Ratio and Visual Evaluation

Face recognition method based on optics nonsubsampled Contourlet conversion

Abstract: The invention relates to a face recognition method based on optics nonsubsampled Contourlet conversion; the device for the method comprises an optics nonsubsampled Contourlet conversion module, a feature extraction module and a pattern classification module; firstly, nonsubsampled Contourlet conversion is realized for face picture by the optics nonsubsampled Contourlet conversion module to obtainthe numerical result of face picture nonsubsampled Contourlet conversion; then, the feature extraction module extracts the features such as outline and posture of the face, and organs such as eyes, noses, mouth and the like from the numerical result of face picture nonsubsampled Contourlet conversion; finally, the pattern classification module carries out similarity comparison between the extracted face features and features of standard face picture to obtain face recognition result. The face recognition method provided by the invention can be used in numerous fields such as secret informationaccess control, registered residence and identity card management, entrance guard control system and the like. Compared with traditional face recognition method, the invention can improve face recognition speed.

Efficient pan-sharpening of satellite images with the contourlet transform

Abstract: Recent studies show that hybrid panchromatic sharpening (pan-sharpening) methods using the non-sub-sampled contourlet transform (NSCT) and classical pan-sharpening methods such as intensity, hue and saturation (IHS), principal component analysis (PCA), and adaptive principal component analysis (APCA) reduce spectral distortion in pan-sharpened images. The NSCT is a shift-invariant multi-resolution decomposition. It is based on non-sub-sampled pyramid (NSP) decomposition and non-sub-sampled directional filter banks (NSDFBs). We compare the performance of the APCA–NSCT using different NSP filters, NSDFB filters, number of decomposition levels, and number of orientations in each level on SPOT 4 data with a spatial resolution ratio of 1:2, and Quickbird data with a spatial resolution ratio of 1:4. Experimental results show that the quality of pan-sharpening of remote-sensing images of different spatial resolution ratios using the APCA–NSCT method is affected by NSCT parameters. For the NSP, the ‘maxflat’ filt...

Image fusion for synthetic aperture radar and multispectral images based on sub-band-modulated non-subsampled contourlet transform and pulse coupled neural network methods

Abstract: Fusion of synthetic aperture radar (SAR) and multispectral (MS) images can contribute to a better visual perception of the objects observed. Unfortunately, many classical approaches have been proven to be unsuitable for this task due to their intrinsic differences in imaging mechanism. In the non-subsampled contourlet transform domain, an alternative fusion method based on pulse coupled neural networks is proposed. To control the amount of SAR features to be integrated into MS image, a gradient-threshold combined modulation is designed for modulating the SAR sub-band coefficients. Experiments demonstrate that the proposed method outperforms its counterparts in spectral preservation and feature enhancement.