Topic
Contourlet
About: Contourlet is a research topic. Over the lifetime, 3533 publications have been published within this topic receiving 38980 citations.
Papers published on a yearly basis
Papers
More filters
TL;DR: Experimental results show that the fusion results of the algorithm can improve the image fusion quality significantly and it has certain advantages in both visual effects and objective evaluation indexes, which provides a more reliable basis for clinical diagnosis and treatment of diseases.
Abstract: In order to improve the contrast of image fusion and highlight the unique characteristics of medical images, a multi-modal medical image fusion algorithm in the framework of non-subsampled contourlet transform (NSCT) is proposed in this paper. Firstly, the computed tomography images and magnetic resonance image are decomposed into low- and high-frequency sub-bands through the NSCT of multi-scale geometric transformation; secondly, for the low-frequency sub-band, the local area standard deviation method is selected or the fusion, while for the high-frequency sub-band, an adaptive pulse coupling neural network model is constructed and the fusion rules are set by the cumulative ignition times of iterative operation in the network; finally, the fusion image is obtained through image reconstruction. Experimental results show that the fusion results of the algorithm in this paper can improve the image fusion quality significantly and it has certain advantages in both visual effects and objective evaluation indexes, which provides a more reliable basis for clinical diagnosis and treatment of diseases.
14 citations
TL;DR: Experimental results show the proposed method can outperform principal component analysis, linear discriminant analysis and neural network, and effectively improve the classification accuracy of multi-spectral images; this method provides a new perspective for land-use classification.
Abstract: It is of great significance and practical application value to extract land-cover type accurately. However, the input data usually used in classification such as reflectance data or vegetation index are very simple and quantitative remote sensing products are rarely used. In this paper, a multi-spectral land-cover classification method based on deep learning is proposed. Using the excellent detail capture ability of contourlet transform to obtain the potential information to supplement the spectral feature space, combined with deep learning for feature selection and feature extraction, a spectral–texture classification model is constructed. The multi-spectral sensing remote data and field measurement data in Dadukou District of Chongqing, northern Negev, and Changping region of Beijing were used for evaluation. Experiment results show the proposed method can outperform principal component analysis, linear discriminant analysis and neural network, and effectively improve the classification accuracy of multi-spectral images; this method provides a new perspective for land-use classification.
14 citations
01 Jan 2007
TL;DR: The experimental results show that, with the proposed color fusion method, the fused image produced by the contourlet transform is of better quality than that obtained through the wavelet transform and obviously improves fusion performance over the traditional IHS transform fusion method.
Abstract: With the particular research on thermal and visual images,a color image fusion algorithm using the contourlet transform is presented.Firstly,through the IHS(Intensity-Hue-Saturation) transform,the color visual image is converted from RGB color space to IHS space.Next,with the contourlet transform and weighted average fusion rule,the intensity component and thermal image are merged into a grayscale image,which is then linearly stretched to have the same mean and variance as the intensity component.Finally,the stretched grayscale fused image replaces the original intensity component,and the final RGB color fused image is achieved by the inverse IHS transform with the H,S and replacement component.On the one hand,with the proposed scheme,the contourlet transform as a new mathematical tool is introduced to image fusion area.On the other hand,the algorithm provided a new color image fusion strategy of thermal and visual images.The experimental results show that,with the proposed color fusion method,the fused image produced by the contourlet transform is of better quality than that obtained through the wavelet transform.Moreover,the color fusion approach obviously improves fusion performance over the traditional IHS transform fusion method.
14 citations
13 Jan 2014
TL;DR: An automatic approach for image segmentation based on neutrosophic set and nonsubsampled contourlet transformation for natural images is proposed and shows that the proposed method automatically segments image better than traditional methods.
Abstract: In this paper, an automatic approach for image segmentation based on neutrosophic set and nonsubsampled contourlet transformation for natural images is proposed. This method uses both color and texture features for segmentation. Input image is transformed into LUV color model for extracting the color features. Texture features are extracted from the grayscale image. Image is then transformed into Neutrosophic domain. Finally, image segmentation is performed using Fuzzy C-means clustering. Clusters are adaptively calculated based on a cluster validity analysis. This method is tested in natural image database. The result analysis shows that the proposed method automatically segments image better than traditional methods.
14 citations
TL;DR: The experimental results depict that the proposed medical image fusion system based on multi scale decomposition with convolutional neural network and sparse representation yields better results than the current methodologies in terms of both visual consistency and quantitative analysis.
14 citations