Weighted Fusion Rule Research Articles

A novel approach for multimodal medical image fusion

Fusion of multimodal medical images increases robustness and enhances accuracy in biomedical research and clinical diagnosis. It attracts much attention over the past decade. In this paper, an efficient multimodal medical image fusion approach based on compressive sensing is presented to fuse computed tomography (CT) and magnetic resonance imaging (MRI) images. The significant sparse coefficients of CT and MRI images are acquired via multi-scale discrete wavelet transform. A proposed weighted fusion rule is utilized to fuse the high frequency coefficients of the source medical images; while the pulse coupled neural networks (PCNN) fusion rule is exploited to fuse the low frequency coefficients. Random Gaussian matrix is used to encode and measure. The fused image is reconstructed via Compressive Sampling Matched Pursuit algorithm (CoSaMP). To show the efficiency of the proposed approach, several comparative experiments are conducted. The results reveal that the proposed approach achieves better fused image quality than the existing state-of-the-art methods. Furthermore, the novel fusion approach has the superiority of high stability, good flexibility and low time consumption.

Optimal score level fusion combining multi-normalisation and separability measures

This paper demonstrates the utility of multi-normalisation and separability measures for the optimal fusion of fingerprint and speaker biometrics. The decision scores of the individual matchers are transformed using various normalisation techniques and the global scores are obtained by combining the multi-normalised scores using the weighted fusion rules. The class as well as the score separability measures, under various noise conditions are estimated and combined algebraically, to determine the best integration weight, for the complementary modalities employed. The weight factor is optimised against the recognition accuracy. Experiments done with chimeric user database result in minimising the intersection between the genuine and the impostor score distributions, which in turn reduces the classification errors. Hence, by incorporating multi-normalisation and integration weight optimisation scheme on a unified framework, we can achieve better recognition performance and make the system robust to fluctuating inputs, even under extreme noise conditions.

基于区域检测与非下采样轮廓波变换的红外与彩色可见光图像融合

An infrared and color visible image fusion method based on Snake model region detection and non-subsampled contourlet transform(NSCT) is presented. In this method, first of all, the luminance component is extracted by using IHS(intensity, hue, saturation) color space conversion for color visible images and the target region of infrared images is detected by adopting Snake model. Then NSCT decomposition is utilized for the luminance component and target replaced infrared image. Image fusion is done by using the largest pixels absolute value sum for the high frequency coefficient and the weighted fusion rules based on brightness mapping technology for the low frequency coefficient. NSCT inverse transform is adopted to obtain the brightness of the image fusion for the fusion coefficients. Finally, the color space inverse transformation is used to acquire fusion images. Experimental results show that the proposed fusion method can not only maintain a high resolution and natural colors of the visible image, but also accurately retain the target information detected in the infrared image. Compared with other methods, fusion images with a better visual effect and comprehensive indicator can be achieved.

An Image Fusion Algorithm Based on NSCT

The study proposed an improved NSCT fusion method based on the infrared and visible light images characteristics and fusion requirement. This paper improved the high-frequency coefficient and low-frequency coefficient fusion rules. The low-frequency sub-band images adopted the pixel feature energy weighted fusion rule. The high-frequency sub-band images adopted the neighborhood variance feature information fusion rule. The fusion experiment results show that this algorithm has good robustness. It could effectively extract edges and texture information. The fused images have abundance scene information and clear target. So this algorithm is an effective infrared and visible image fusion method.

Image Fusion Based on Nonsubsampled Contourlet Transform and Saliency-Motivated Pulse Coupled Neural Networks

In the nonsubsampled contourlet transform (NSCT) domain, a novel image fusion algorithm based on the visual attention model and pulse coupled neural networks (PCNNs) is proposed. For the fusion of high-pass subbands in NSCT domain, a saliency-motivated PCNN model is proposed. The main idea is that high-pass subband coefficients are combined with their visual saliency maps as input to motivate PCNN. Coefficients with large firing times are employed as the fused high-pass subband coefficients. Low-pass subband coefficients are merged to develop a weighted fusion rule based on firing times of PCNN. The fused image contains abundant detailed contents from source images and preserves effectively the saliency structure while enhancing the image contrast. The algorithm can preserve the completeness and the sharpness of object regions. The fused image is more natural and can satisfy the requirement of human visual system (HVS). Experiments demonstrate that the proposed algorithm yields better performance.

WE-E-213CD-02: Gaussian Weighted Multi-Atlas Based Segmentation for Head and Neck Radiotherapy Planning.

To develop a multi-atlas segmentation strategy for IMRT head and neck therapy planning. The method was tested on thirty-one head and neck simulation CTs, without demographic or pathology pre-clustering. We compare Fixed Number (FN) and Thresholding (TH) selection (based on normalized mutual information ranking) of the atlases to be included for current patient segmentation. Next step is a pairwise demons Deformable Registration (DR) onto current patient CT. DR was extended to automatically compensate for patient different field of view. Propagated labels are combined according to a Gaussian Weighted (GW) fusion rule, adapted to poor soft tissues contrast. Agreement with manual segmentation was quantified in terms of Dice Similarity Coefficient (DSC). Selection methods, number of atlases used, as well as GW, average and majority voting fusion were discriminated by means of Friedman Test (a=5%). Experimental tuning of the algorithm parameters was performed on five patients, deriving an optimal configuration for each structure. DSC reduction was not significant when ten or more atlases are selected, whereas DSC for single most similar atlas selection is 10% lower in median. DSC of FN selection rule were significantly higher for most structures. Tubular structures may benefit from computing average contour rather than looking at the singular voxel contribution, whereas the best performing strategy for all other structures was GW. When half database is selected, final median DSC were 0.86, 0.80, 0.51, 0.81, 0.69 and 0.79 for mandible, spine, optical nerves, eyes, parotids and brainstem respectively. We developed an efficient algorithm for multiatlas based segmentation of planning CT volumes, based on DR and GW. FN selection of database atlases is foreseen to increase computational efficiency. The absence of clinical pre-clustering and specific imaging protocol on database subjects makes the results closer to real clinical application. "Progetto Roberto Rocca" funded by the Fondazione Fratelli Agostino and Enrico Rocca, Italy.

A Multiple Classifier System for Functional Classification of G Protein-Coupled Receptors

G protein-coupled receptors (GPCRs) are the largest protein super family in the human body and play a significant role in the pharmaceutical industry as drug targets. Although the deep research in GPCRs is continuing to grow, the study on their structures and functions is limited, for it is difficult and complex for the researchers to obtain purified membrane protein structures of GPCRs. Currently, how to get the structures of GPCRs and how to analyze them are the most important issues in modern molecular biology and medicine. We adopted multi-classifier method to deal with the problem of functional classification of GPCRs. Based on class hierarchy, the different data sets for training the classifiers were formed, and the diversity and accuracy were considered together in selecting the classifier sets. The dynamic weighted fusion rule was used to combine the classifiers. Experimental results show the effectiveness of this multi-classifier system.

Fusion of multiparametric SAR images based on SW-nonsubsampled contourlet and PCNN

In this paper, a new fusion rule based on a pulse coupled neural network (PCNN) and the clarity of images is proposed for multi-band synthetic aperture radar (SAR) image fusion. By using a stationary wavelet-based nonsubsampled contourlet transform (SW-NSCT), we can calculate a flexible multiscale, multidirectional, anisotropy and shift-invariant representation of registered SAR images. A weighted fusion rule is performed on the low frequency subbands to calculate the fused lowpass band. For the fusion of high frequency directional subband images, a PCNN model is constructed, where the linking strength of each neuron is determined by the clarity of the decomposed subband images. The fusion approach exploits the advantages of both SW-NSCT in multiscale geometric representations and that of PCNN in the determination of fusion rules; as predicted, the obtained fusion image can preserve much more information regarding textures and edges of the images, compared to its counterparts. Some experiments are performed by comparing the new algorithm with other existing fusion rules and methods. The experimental results show that the proposed fusion approach is effective and can provide better performance in fusing multi-band SAR images than some current methods.

Information fusion Wiener filter for the multisensor multichannel ARMA signals with time-delayed measurements

For the multisensor multichannel autoregressive moving average (ARMA) signals with time-delayed measurements, a measurement transformation approach is presented, which transforms the equivalent state space model with measurement delays into the state space model without measurement delays, and then using the Kalman filtering method, under the linear minimum variance optimal weighted fusion rules, three distributed optimal fusion Wiener filters weighted by matrices, diagonal matrices and scalars are presented, respectively, which can handle the fused filtering, prediction and smoothing problems. They are locally optimal and globally suboptimal. The accuracy of the fuser is higher than that of each local signal estimator. In order to compute the optimal weights, the formulae of computing the cross-covariances among local signal estimation errors are given. A Monte Carlo simulation example for the three-sensor target tracking system with time-delayed measurements shows their effectiveness.

New approach to information fusion steady-state Kalman filtering

By the modern time series analysis method, based on the autoregressive moving average (ARMA) innovation model, a unified and general information fusion steady-state Kalman filtering approach is presented for the general multisensor systems with different local dynamic models and correlated noises. It can handle the filtering, smoothing, and prediction fusion problems for state or signal. The optimal fusion rule weighted by matrices is re-derived as a weighted least squares (WLS) fuser, and is reviewed. An optimal fusion rule weighted by diagonal matrices is presented, which is equivalent to the optimal fusion rule weighted by scalars for components, and it realizes a decoupled fusion. The new algorithms of the steady-state Kalman estimator gains are presented. In order to compute the optimal weights, the formulas of computing the cross-covariances among local estimation errors by Lyapunov equations are presented. The exponential convergence of the iterative solution of Lyapunov equation is proved. It is proved that the optimal fusion estimators under three weighted fusion rules are locally optimal, but are globally suboptimal. The proposed steady-state Kalman fusers can reduce the on-line computational burden, and are suitable for real-time applications. A simulation example for the 3-sensor steady-state Kalman tracking fusion estimators shows their effectiveness and correctness, and gives the accuracy comparison of the fusion rules.