Article history: Available online xxxx Blocking effect caused by coefficient quantification during image compression is an annoying problem. The main effect of quantification is to eliminate high frequency component in the image. Therefore, it will lead to noticeable discontinuous leaps which causes block effect and degrade the image. A deblocking method based on Curvelet transform is proposed ...

this paper presents a new three-dimensional curvelet transform based dictionary learning for automatic segmentation of intraretinalcysts, most relevant prognostic biomarker in neovascular age-related macular degeneration, from 3d spectral-domain optical coherencetomography (sd-oct) images. in particular, we focus on the spectralis sd-oct (heidelberg engineering, heidelberg, germany) system, and...

Multimodal medical image fusion approaches have been commonly used to diagnose diseases and involve merging multiple images of different modes achieve superior quality reduce uncertainty redundancy in order increase the clinical applicability. In this paper, we proposed a new algorithm based on convolutional neural network (CNN) obtain weight map for multiscale transform (curvelet/ non-subsampl...

Abstract Shallow geological imaging structures often play an essential role in the field of environmental and engineering geophysics. Early arrival waveform inversion (EWI) is high-resolution method to near-surface structures. We proposed a joint envelope based on curvelet transform (CJWEI) build shallow By taking advantage their complementary sensitivities structure, we can constrain both low-...

Current image representation schemes have limited capability of representing 2D singularities (e.g., edges in an image). Wavelet transform has better performance in representing 1D singularities than Fourier transform. Recently invented ridgelet and curvelet transform achieve better performance in resolving 2D singularities than wavelet transform. To further improve the capability of representi...

In this paper, a new bivariate shrinkage denoising method is proposed to model statistics of shearlet coefficients of images. Using Bayesian estimation theory we derive from this model a simple non-linear shrinkage function for shearlet denoising, which generalizes the soft threshold approach. Experimental results show that the proposed method can remove Gaussian white noise while effectively p...

In this article, a new color feature extraction algorithm and a new hybrid color space is proposed in order to further enhance the color face recognition performance. First, it is searched the best combination way of color component images of the YIQ, the YCbCr, and the HSV color spaces transformed from RGB color space. Secondly it is decomposed by applying curvelet transform to each of color c...

– We use a new approach to combine magnetic and electrical geophysical data from two different archaeological areas in Greece (Europos & Doriskos). Using the curvelet transform we express feature of images as function spatial coordinates, scale, orientation. A combined image is created domain through objective selection most salient features. The results show several potential structures.