Contourlet

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

Efficient IRIS Recognition Through Improvement of Feature Extraction and subset Selection

Abstract: the selection of the optimal feature subset and the classification has become an important issue in the field of iris recognition. In this paper we propose several methods for iris feature subset selection and vector creation. The deterministic feature sequence is extracted from the iris image by using the contourlet transform technique. Contourlet transform captures the intrinsic geometrical structures of iris image. It decomposes the iris image into a set of directional sub-bands with texture details captured in different orientations at various scales so for reducing the feature vector dimensions we use the method for extract only significant bit and information from normalized iris images. In this method we ignore fragile bits. And finally we use SVM (Support Vector Machine) classifier for approximating the amount of people identification in our proposed system. Experimental result show that most proposed method reduces processing time and increase the classification accuracy and also the iris feature vector length is much smaller versus the other methods.

Medical image denoising using adaptive threshold based on contourlet transform

Abstract: Image denoising has become an essential exercise in medical imaging especially the Magnetic Resonance Imaging (MRI). This paper proposes a medical image denoising algorithm using contourlet transform. Numerical results show that the proposed algorithm can obtained higher peak signal to noise ratio (PSNR) than wavelet based denoising algorithms using MR Images in the presence of AWGN.

Compressed sensing MRI with combined sparsifying transforms and smoothed l 0 norm minimization

Abstract: Undersampling the k-space is an efficient way to speed up the magnetic resonance imaging (MRI). Recently emerged compressed sensing MRI shows promising results. However, most of them only enforce the sparsity of images in single transform, e.g. total variation, wavelet, etc. In this paper, based on the principle of basis pursuit, we propose a new framework to combine sparsifying transforms in compressed sensing MRI. Each transform can efficiently represent specific feature that the other can not. This framework is implemented via the state-of-art smoothed l 0 norm in overcomplete sparse decomposition. Simulation results demonstrate that the proposed method can improve image quality when comparing to single sparsifying transform.

Content Based Medical Image Retrieval by Combining Rotation Invariant Contourlet Features and Fourier Descriptors

Abstract: Designing and modeling methods for medical image search is a challenging task. Content based medical image retrieval, which aims at searching the image database using invariant features, is an important research area for manipulating large amount of medical image databases. This paper focuses on the problem of texture and shape feature extraction. A novel approach by successfully combining rotation invariant contourlet transform and Fourier descriptors is proposed. Rotation invariant contourlet transform is used for texture feature extraction and Fourier descriptor extracts shape features. The retrieval performance of this method is tested using a large medical image database and measured using commonly used performance measurement. Index Terms—CBIR, Rotation invariant contourlet transform, Fourier descriptor, Feature extraction, Similarity measure.

Adaptive watermarking schemes based on a redundant contourlet transform

Abstract: We are interested in the adaptive watermarking approaches and in directional multiresolution image transforms. In this paper, a novel watermarking technique based on a redundant contourlet transform is presented. In contrast to the wavelet transform widely used for image watermarking, to our best knowledge, this is the first time contourlets are applied to this field. The goal of this work is to investigate whether the contourlet with their extra feature of directionality and the explicit introduction of redundancy would provide any significant advantages over the wavelets in terms of watermark robustness and invisibility. Our approach uses directional subbands to generate weighing masks that identify significant image features. The redundancy being introduced brings simplicity and accuracy for mask processing. To prove the validity of our approach, we give experimental results, compare our algorithm to a wavelet-based adaptive watermarking technique and assess watermarking performance in terms of robustness and invisibility.