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
9 citations
01 Dec 2012
TL;DR: A Content Based Medical Image Retrieval (CBMIR) system for diverse collection of radiographic images using non-Subsampled Contourlet Transform and Fuzzy C-Means technique to construct the image signature which is used as the image representative feature vector.
Abstract: This paper presents a Content Based Medical Image Retrieval (CBMIR) system for diverse collection of radiographic images. Non-Subsampled Contourlet Transform (NSCT) and Fuzzy C-Means (FCM) technique is used to construct the image signature which is used as the image representative feature vector. Least Square-Support Vector Machine (LS-SVM) and Earth Mover's Distance (EMD) is used to classify the images. Preliminary studies on a radiographic image Database (DB) consisting 1550 images of 31 different modalities show promising result.
9 citations
TL;DR: A new method for fusion of millimeter wave images with their visible images with theirs with contourlet transform and a new method in thresholding is presented so that the output image includes visual information very close to visible image which contains object hidden from millimeters wave image.
Abstract: Passive millimeter wave (PMMW) imaging system forms images through passive detection of millimeter wave radiations emitted from the objects. This system allows detection of invisible characteristics of a scene. The important characteristic of these waves is their penetration into cloth fibers and bad climatic conditions such as mist, rain and smoke. These waves are able to detect objects (particularly metal objects) hidden in cloths. For this reason, imaging system is applied in security section of the airports. This system has also abundant applications in military, meteorology, navigation industries in low vision and medical industries. In airports and generally the places where there is need for physical inspection of people, millimeter wave scanners are used. These devices are able to detect weapon and other objects hanging on body of the person or hidden in clothes. Due to limitation of dimensions of lens and antenna and limitation of light refraction, images obtained from this system have low resolution. Imaging in this system acts as a low-pass filter. For this reason, high-frequency information of these images is removed; therefore, set of actions is necessary for improving quality of these images. Different methods have been presented for increasing quality of these images which are divided into two classes of retrieval and combination or fusion of image (for example, fusion of PMMW image with visible image). Target of this paper is to present a new method for fusion of millimeter wave images with their visible images with their visible images with contourlet transform and a new method in thresholding; so that the output image includes visual information very close to visible image which contains object hidden from millimeter wave image.
9 citations
01 Jan 2011
TL;DR: Experimental results shows that the contourlet features when classify by using AdaBoost (α-Type) classifier are very suitable for invariant palmprint verification.
Abstract: Biometrics-based personal verification is a powerful security features in technology era. Palmprint is an important complement and reliable biometric that can be used for identity verification because it is stable and unique for every individual. This paper presents a new palmprint verification method by using the contourlet features and AdaBoost classification. The contourlet transform is a new two dimensional extension of the wavelet transform using multi-scale and directional filter banks. It can effectively capture smooth contours that are the dominant features in palmprint images. AdaBoost is used as a classifier in the experiments. Experimental results shows that the contourlet features when classify by using AdaBoost (α-Type) classifier are very suitable for invariant palmprint verification. The experimental results illustrate the effectiveness of the method proposed. (Eisa Rezazadeh Ardabili, Keivan Maghooli, Emad Fatemizadeh. Contourlet features extraction and AdaBoost classification for palmprint verification. Journal of American Science 2011;7(7):353-362). (ISSN: 1545-1003). http://www.americanscience.org.
9 citations
06 Oct 2010
TL;DR: The Sequential Float Feature Selection (SFFS) algorithm with a k-NN classifier has been applied in order to investigate the most representative set of CT features, showing that CT based texture features can be successfully applied for the representation of different types of texture in US thyroid images.
Abstract: Texture representation of ultrasound (US) images is currently considered a major issue in medical image analysis. This paper investigates the texture representation of thyroid tissue via features based on the Contourlet Transform (CT) using different types of filter banks. A variety of statistical texture features based on CT coefficients, have been considered through a selection schema. The Sequential Float Feature Selection (SFFS) algorithm with a k-NN classifier has been applied in order to investigate the most representative set of CT features. For the experimental evaluation a set of normal and nodular ultrasound thyroid textures have been utilized. The maximum classification accuracy was 93%, showing that CT based texture features can be successfully applied for the representation of different types of texture in US thyroid images.
9 citations