Local Mutual Information Research Articles

Restoration of multispectral images by total variation with auxiliary image

In this paper, the restoration of a degraded image with an auxiliary image from another sensor is considered. In a typical multispectral satellite imaging system, multiple images from different sensors of the same area are available. When one of those images in a multiple image set is degraded, another image in the set can be used as a prior image for restoration. A hybrid algorithm based on the total variation approach using an auxiliary image is proposed in this paper. In this approach, the cost function for regularization has two terms: error from the degraded image being restored and the error from the auxiliary image. The amount of prior information from the auxiliary image to be used in the hybrid algorithm is determined based on the similarity between the auxiliary image and the degraded image. An algorithm, based on normalized local mutual information, is developed to estimate the amount of prior information to apply.The proposed algorithm is applied to both simulated and real multispectral images, and the performance of the proposed algorithm is compared with those of other image restoration algorithms. In both quantitative and qualitative comparisons, the proposed algorithm performed better than other algorithms.

Information analysis of iris biometrics for the needs of cryptology key extraction

The paper presents a rigorous analysis of iris biometric information for the synthesis of an optimized system for the extraction of a high quality cryptology key. Estimations of local entropy and mutual information were identified as segments of the iris most suitable for this purpose. In order to optimize parameters, corresponding wavelets were transformed, in order to obtain the highest possible entropy and mutual information lower in the transformation domain, which set frameworks for the synthesis of systems for the extraction of truly random sequences of iris biometrics, without compromising authentication properties.

Sonar Image Registration Based on Improved PSO and Powell Hybrid Algorithm

In order to further improve the accuracy of the sonar image registration, a novel hybrid algorithm was proposed. It proposed the normalized mutual information as similar estimation, drawn on multi-resolution data structure based on wavelet transform, a low precision solution was solved by improved PSO algorithm, which has strong global search capability, firstly and then a high precision solution was acquired by Powell method, which has strong local search capability. The hybrid algorithm is effective to overcome the fall of local maximum mutual information function; it also improves solution’s precision. Since the hybrid algorithm is the initial point of pre-treatment, an effective solution to the Powell method dependence on the initial point. Experiments reveal that the hybrid algorithm is efficiency and effectiveness.

Spatio-temporal (2D+T) non-rigid registration of real-time 3D echocardiography and cardiovascular MR image sequences

In this paper we describe a method to non-rigidly co-register a 2D slice sequence from real-time 3D echocardiography with a 2D cardiovascular MR image sequence. This is challenging because the imaging modalities have different spatial and temporal resolution. Non-rigid registration is required for accurate alignment due to imprecision of cardiac gating and natural motion variations between cardiac cycles. In our approach the deformation field between the imaging modalities is decoupled into temporal and spatial components. First, temporal alignment is performed to establish temporal correspondence between a real-time 3D echocardiography frame and a cardiovascular MR frame. Spatial alignment is then performed using an adaptive non-rigid registration algorithm based on local phase mutual information on each temporally aligned image pair. Experiments on seven volunteer datasets are reported. Evaluation of registration errors based on expert-identified landmarks shows that the spatio-temporal registration algorithm gives a mean registration error of 3.56 ± 0.49 and 3.54 ± 0.27 mm for the short and long axis sequences, respectively.

Local similarity measure for landslide detection and identification in comparison with the image differencing method

In this article, a new simple method of landslide detection and identification is proposed. It is based on the use of local mutual information and image thresholding. A binary change image is then produced. Connected component analysis is used to identify the connected regions. Landslides are identified as the largest connected regions in this image. Mathematical morphology is used to approximate the landslide region. This method is simple and suitable for the detection of large changed regions where the ratio of the unchanged to changed pixels in the image is approximately one to a few tens. Compared to the image differencing method, this method gives more reliable results.

Joint Diagnostic of the Surface Air Temperature in Southern South America and the Madden–Julian Oscillation

Abstract The objective of this research is to explore the relationship between maximum and minimum temperatures, daily precipitation, and the Madden–Julian oscillation (MJO). It was found that the different phases of the MJO show a consistent signal on winter temperature variability and precipitation in southeastern South America. Additionally, this paper explores the spatial–temporal variations of mutual information and joint entropy between temperature and the MJO. A defined spatial pattern was observed with an increased signal in northeastern Argentina and southern Brazil. In the local mutual information analysis, periods in which the mutual information doubled the average values were observed over the entire region. These results indicate that these connections can be used to forecast winter temperatures with a better skill score in situations where both variables covary.

A Bayesian Network Learning Algorithm Based on Independence Test and Ant Colony Optimization

To solve the drawbacks of the ant colony optimization for learning Bayesian networks (ACO-B), this paper proposes an improved algorithm based on the conditional independence test and ant colony optimization (I-ACO-B). First, the I-ACO-B uses order-0 independence tests to effectively restrict the space of candidate solutions, so that many unnecessary searches of ants can be avoided. And then, by combining the global score increase of a solution and local mutual information between nodes, a new heuristic function with better heuristic ability is given to induct the process of stochastic searches. The experimental results on the benchmark data sets show that the new algorithm is effective and efficient in large scale databases, and greatly enhances convergence speed compared to the original algorithm.

Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information

An automatic method for delineating the prostate (including the seminal vesicles) in three-dimensional magnetic resonance scans is presented. The method is based on nonrigid registration of a set of prelabeled atlas images. Each atlas image is nonrigidly registered with the target patient image. Subsequently, the deformed atlas label images are fused to yield a single segmentation of the patient image. The proposed method is evaluated on 50 clinical scans, which were manually segmented by three experts. The Dice similarity coefficient (DSC) is used to quantify the overlap between the automatic and manual segmentations. We investigate the impact of several factors on the performance of the segmentation method. For the registration, two similarity measures are compared: Mutual information and a localized version of mutual information. The latter turns out to be superior (median DeltaDSC approximately equal 0.02, p < 0.01 with a paired two-sided Wilcoxon test) and comes at no added computational cost, thanks to the use of a novel stochastic optimization scheme. For the atlas fusion step we consider a majority voting rule and the "simultaneous truth and performance level estimation" algorithm, both with and without a preceding atlas selection stage. The differences between the various fusion methods appear to be small and mostly not statistically significant (p > 0.05). To assess the influence of the atlas composition, two atlas sets are compared. The first set consists of 38 scans of healthy volunteers. The second set is constructed by a leave-one-out approach using the 50 clinical scans that are used for evaluation. The second atlas set gives substantially better performance (DeltaDSC=0.04, p < 0.01), stressing the importance of a careful atlas definition. With the best settings, a median DSC of around 0.85 is achieved, which is close to the median interobserver DSC of 0.87. The segmentation quality is especially good at the prostate-rectum interface, where the segmentation error remains below 1 mm in 50% of the cases and below 1.5 mm in 75% of the cases.

Mutual information and correlation measures in atomic systems

Mutual information is introduced as an electron correlation measure and examined for isoelectronic series and neutral atoms. We show that it possesses the required characteristics of a correlation measure and is superior to the behavior of the radial correlation coefficient in the neon series. A local mutual information, and related local quantities, are used to examine the local contributions to Fermi correlation, and to demonstrate and to interpret the intimate relationship between correlation and localization.

Distillation Protocols: Output Entanglement and Local Mutual Information

A complementary behavior between local mutual information and average output entanglement is derived for arbitrary bipartite ensembles. This leads to bounds on the yield of entanglement in distillation protocols that involve disinguishing. This bound is saturated in the hashing protocol for distillation, for Bell-diagonal states.

Cortical Shift Tracking Using a Laser Range Scanner and Deformable Registration Methods.

A novel brain shift tracking protocol is introduced in this paper which utilizes laser range scan (LRS) data and 2D deformable image registration. This protocol builds on previous efforts to incorporate intra-operative LRS data into a model-updated image guided surgery paradigm for brain shift compensation. The shift tracking method employs the use of a LRS system capable of capturing textures of the intra-operative scene during range data acquisition. Textures from serial range images are then registered using a 2D deformable registration approach that uses local support radial basis functions and mutual information. Given the deformation field provided by the registration, 3D points in serial LRS datasets can then be tracked. Results from this paper indicate that the error associated with tracking brain movement is 1.1mm on average given brain shifts of approximately 20.5mm. Equally important, a strategy is presented to rapidly acquire intra-operative measurements of shift which are compatible with model-based strategies for brain deformation compensation.

Global dynamics of a network of stochastic neurons maximizes local mutual information

We define a stochastic neuron as an element that increases its internal state with probability p until a threshold value is reached; after that its internal state is set back to the initial value. We study the local information of a stochastic neuron between the message arriving from the input neurons and the response of the neuron. We study the dependence of the local information on the firing probability [iopmath latex="$alpha$"] [/iopmath] of the synaptic inputs in a network of such stochastic neurons. The values of [iopmath latex="$alpha$"] [/iopmath] obtained in the simulations are the same as those obtained theoretically by maximization of local mutual information. We conclude that the global dynamics maximizes the local mutual information of single units, which means that the self-selected parameter value of the population dynamics is such that each neuron behaves as an optimal encoder.

Global dynamics of a network of stochastic neurons maximizes local mutual information

We define a stochastic neuron as an element that increases its internal state with probability p until a threshold value is reached; after that its internal state is set back to the initial value. We study the local information of a stochastic neuron between the message arriving from the input neurons and the response of the neuron. We study the dependence of the local information on the firing probability alpha of the synaptic inputs in a network of such stochastic neurons. The values of alpha obtained in the simulations are the same as those obtained theoretically by maximization of local mutual information. We conclude that the global dynamics maximizes the local mutual information of single units, which means that the self-selected parameter value of the population dynamics is such that each neuron behaves as an optimal encoder.

Optimum quantization for detector fusion: some proofs, examples, and pathology

We consider optimal decentralized (or equivalently, quantized) detection for the Neyman– Pearson, Bayes, Ali–Silvey distance, and mutual (Shannon) information criteria. In all cases, it is shown that the optimal sensor decision rules are quantizers that operate on the likelihood ratio of the observations. We further show that randomized fusion rules are suboptimal for the mutual information criterion. We also show that if the processes observed at the sensors are conditionally independent and identically distributed, and the criterion for optimization is either a member of a subclass of the Ali–Silvey distances or local mutual information, then the quantizers used at all of the sensors are identical. We give an example to show that for the Neyman–Pearson and Bayes criteria this is not generally true. We go into some detail with respect to this last, and derive necessary conditions for an assumptions of identical sensor quantizer maps to be reasonable.