Christine Toumoulin

Quaternion Zernike moments and their invariants for color image analysis and object recognition

Moments and moment invariants have become a powerful tool in pattern recognition and image analysis. Conventional methods to deal with color images are based on RGB decomposition or graying, which may lose some significant color information. In this paper, by using the algebra of quaternions, we introduce the quaternion Zernike moments (QZMs) to deal with the color images in a holistic manner. It is shown that the QZMs can be obtained from the conventional Zernike moments of each channel. We also provide the theoretical framework to construct a set of combined invariants with respect to rotation, scaling and translation (RST) transformation. Experimental results are provided to illustrate the efficiency of the proposed descriptors.

A novel algorithm for fast computation of Zernike moments

Abstract Zernike moments (ZMs) have been successfully used in pattern recognition and image analysis due to their good properties of orthogonality and rotation invariance. However, their computation by a direct method is too expensive, which limits the application of ZMs. In this paper, we present a novel algorithm for fast computation of Zernike moments. By using the recursive property of Zernike polynomials, the inter-relationship of the Zernike moments can be established. As a result, the Zernike moment of order n with repetition m, Znm, can be expressed as a combination of Zn−2,m and Zn−4,m. Based on this relationship, the Zernike moment Znm, for n>m, can be deduced from Zmm. To reduce the computational complexity, we adopt an algorithm known as systolic array for computing these latter moments. Using such a strategy, the multiplication number required in the moment calculation of Zmm can be decreased significantly. Comparison with known methods shows that our algorithm is as accurate as the existing methods, but is more efficient.

Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing

In abdomen computed tomography (CT), repeated radiation exposures are often inevitable for cancer patients who receive surgery or radiotherapy guided by CT images. Low-dose scans should thus be considered in order to avoid the harm of accumulative x-ray radiation. This work is aimed at improving abdomen tumor CT images from low-dose scans by using a fast dictionary learning (DL) based processing. Stemming from sparse representation theory, the proposed patch-based DL approach allows effective suppression of both mottled noise and streak artifacts. The experiments carried out on clinical data show that the proposed method brings encouraging improvements in abdomen low-dose CT images with tumors.

Image analysis by discrete orthogonal hahn moments

Orthogonal moments are recognized as useful tools for object representation and image analysis. It has been shown that the recently developed discrete orthogonal moments have better performance than the conventional continuous orthogonal moments. In this paper, a new set of discrete orthogonal polynomials, namely Hahn polynomials, are introduced. The related Hahn moment functions defined on this orthogonal basis set are investigated and applied to image reconstruction. In experiments, the Hahn moments are compared with the other two discrete orthogonal moments: Chebyshev and Krawtchouk moments. The simulation results show that the Hahn moment-based reconstruction method is superior to the other two discrete orthogonal moment-based methods.

Fast detection and characterization of vessels in very large 3-D data sets using geometrical moments

An improved and very fast algorithm dealing with the extraction of vessels in three-dimensional imaging is described. The approach is based on geometrical moments and a local cylindrical approximation. A robust estimation of vessel and background intensity levels, position, orientation, and diameter of the vessels with adaptive control of key parameters, is provided during vessel tracking. Experimental results are presented for lower limb arteries in multidetector computed tomography scanner.

Evaluation of a 3D segmentation software for the coronary characterization in multi-slice computed tomography

A new generation of sub-second multi-slices computed tomography (MSCT) scanners, which allow a complete coronary coverage, is becoming widely available. Nevertheless, they need to be associated with 3D processing tools to quantify the coronary diseases. This study proposes to evaluate a new 3D moment-based method for the extraction of the coronary network and the calcification localization in MSCT. We called on two medical experts respectively in coronarography and radiology to carry out this evaluation. It was based on a comparison between extracted vessels and original scan data with objective and subjective criteria. This preliminary study has been performed on a set of six data sets, which included pathological patterns such as dense and scattered calcifications. These results confirm the good performances of the method with high scores of sensitivity and constitute a first step toward the detection of coronary networks in MSCT data.

L0 constrained sparse reconstruction for multi-slice helical CT reconstruction

In this paper, we present a Bayesian maximum a posteriori method for multi-slice helical CT reconstruction based on an L0-norm prior. It makes use of a very low number of projections. A set of surrogate potential functions is used to successively approximate the L0-norm function while generating the prior and to accelerate the convergence speed. Simulation results show that the proposed method provides high quality reconstructions with highly sparse sampled noise-free projections. In the presence of noise, the reconstruction quality is still significantly better than the reconstructions obtained with L1-norm or L2-norm priors.

A Multiscale Tracking Algorithm for the Coronary Extraction in MSCT Angiography

This paper deals with the extraction of the coronary network on dynamic volume sequences, acquired in multi-slice spiral computed tomography (MSCT). The proposed approach makes use of a tracking algorithm of the vascular structure, combining a 3D geometric moment operator with a multiscale Hessian filter to estimate the vessel central axis location, its local diameter and orientation. The method performs at the same time, a bifurcation detection to reconstitute the structure of the coronary network. The mean computation time to extract a coronary network is about 3 minutes using a P4-2.4G PC. Preliminary encouraging results are presented on one volume of a sequence

Vascular network segmentation in subtraction angiograms: a comparative study

The three-dimensional reconstruction of vascular trees from a very limited number of two-dimensional projections is an active research field. The quality of the results (resolution in terms of vessel size and geometrical location) is highly dependent on the overall distortions introduced in the data acquisition process but is also related to the reliability of feature detection. A new approach based on mathematical morphology is proposed in this paper for extracting the centrelines and edges of coronary vessels from digital subtracted angiograms. These results are compared with those from an alternative method based on vectorial tracking and a directed contour finder.

Coronary characterization in multi-slice computed tomography

We present a 3D extraction method of coronaries in MSCT, which aims at refining the delineating of the vascular inner wall and the calcified contours for quantification purposes. The proposed approach makes use of a two-step process: the first one performs a vessel central axis tracking by applying a semi-automatic 3D geometrical moment-based method. A refinement is then performed, based on a level set approach, to improve the detection accuracy of both contours and calcifications. The level sets were applied first in 2-D space, independently on each slice, then in 3-D to perform the extraction directly in the volume. A comparison between the 2-D and 3-D procedures is provided in term of quality of delineation.