An Efficient Histogram-Based Texture Classification Method with Weighted Symmetrized Kullback-Leibler Divergence

BackgroundUltrasound imaging is safer than other imaging modalities, because it is noninvasive and nonradiative. Speckle noise degrades the quality of ultrasound images and has negative effects on visual perception and diagnostic operations.MethodsIn this paper, a nonlocal total variation (NLTV) method for ultrasonic speckle reduction is proposed. A spatiogram similarity measurement is introduced for the similarity calculation between image patches. It is based on symmetric Kullback-Leibler (KL) divergence and signal-dependent speckle model for log-compressed ultrasound images. Each patch is regarded as a spatiogram, and the spatial distribution of each bin of the spatiogram is regarded as a weighted Gamma distribution. The similarity between the corresponding bins of the two spatiograms is computed by the symmetric KL divergence. The Split-Bregman fast algorithm is then used to solve the adapted NLTV object function. Kolmogorov-Smirnov (KS) test is performed on synthetic noisy images and real ultrasound images.ResultsWe validate our method on synthetic noisy images and clinical ultrasound images. Three measures are adopted for the quantitative evaluation of the despeckling performance: the signal-to-noise ratio (SNR), structural similarity index (SSIM), and natural image quality evaluator (NIQE). For synthetic noisy images, when the noise level increases, the proposed algorithm achieves slightly higher SNRS than that of the other two algorithms, and the SSIMS yielded by the proposed algorithm is obviously higher than that of the other two algorithms. For liver, IVUS and 3DUS images, the NIQE values are 8.25, 6.42 and 9.01, all of which are higher than that of the other two algorithms.ConclusionsThe results of the experiments over synthetic and real ultrasound images demonstrate that the proposed method outperforms current state-of-the-art despeckling methods with respect to speckle reduction and tissue texture preservation.

Speech enhancement using a wavelet thresholding method based on symmetric Kullback–Leibler divergence

In this correspondence, we propose a novel, efficient, and effective Refined Histogram (RH) for modeling the wavelet subband detail coefficients and present a new image signature based on the RH model for supervised texture classification. Our RH makes use of a step function with exponentially increasing intervals to model the histogram of detail coefficients, and the concatenation of the RH model parameters for all wavelet subbands forms the so-called RH signature. To justify the usefulness of the RH signature, we discuss and investigate some of its statistical properties. These properties would clarify the sufficiency of the signature to characterize the wavelet subband information. In addition, we shall also present an efficient RH signature extraction algorithm based on the coefficient-counting technique, which helps to speed up the overall classification system performance. We apply the RH signature to texture classification using the well-known databases. Experimental results show that our proposed RH signature in conjunction with the use of symmetrized Kullback-Leibler divergence gives a satisfactory classification performance compared with the current state-of-the-art methods.

Sparse representation with multi-manifold analysis for texture classification from few training images

Metric learning-based methods, which yield great performance and show considerable potential to improve the performance of hyperspectral image processing, aim to calculate the Mahalanobis distance metric matrix. In this article, we proposed a symmetric information-theoretic metric learning (SITML) method for hyperspectral target detection. The SITML algorithm is designed based on the classical information-theoretic metric learning (ITML) and, minimizes the differential Kullback–Leibler (KL) divergence. To enhance both of the detection performance and the generalization ability, we build metric spaces from the neighborhood of training samples to preserve the local discriminative information. Then, we conduct local pairwise constraints to maximize the Jeffery divergence (also named the symmetric KL divergence) of two multivariate Gaussian distributions to solve the problem of an asymmetric KL divergence. Finally, we use a closed-form solution to solve the optimization problem. Intensive experiments on three hyperspectral datasets indicate that SITML outperforms the classical ITML algorithm and other state-of-the-art target detection methods.

In this paper, we propose a texture classification method using local texture features BDIP (block difference of inverse probabilities) and BVLC (block variation of local correlation coefficients) in wavelet domain. BDIP and BVLC are known to be good texture features which are bounded and well normalized to reduce the effect of illumination and catch the own properties of textures effectively. In the method, a target image is first decomposed into wavelet subbands. BDIPs and BVLCs are then computed in wavelet subbands. The means and standard deviations of subband BDIPs and BVLCs and the subband standard deviations are fused into a texture feature vector. Finally, the Bayesian distance between the feature vector of a query image and that of each class is stably measured and it is classified into the class of minimum distance. Experimental results for three test databases (DBs) show the proposed method yields excellent performances.

Facial Expressions play major role in interpersonal communication and imparting intelligence to computer for identifying facial expressions is a crucial task. In this paper we present an efficient preprocessing algorithm combined with feature extraction using Local Binary Patterns (LBP) followed by classification using Kullback Leibler (KL) divergence. Firstly Viola Jones algorithm is used to detect pair of eyes using which effective part of face is obtained which is further processed to eliminate illumination effect. LBP operator is then applied on the preprocessed image to extract local features represented by histogram. Template histograms for seven basic expressions using training images are formed which are compared with the test histogram distribution using an efficient KL divergence for dissimilarity measure. This algorithm is implemented on JAFFE database resulting in a high classification accuracy of 95.24%.

This paper presents a new rotation-invariant image retrieval method, which extends a recently introduced classification technique based on steerable wavelet transforms. In the proposed procedure, the feature extraction step consists of estimating the covariations (lower-order cross-correlations) between the wavelet subband coefficients, which are modeled as subGaussian random vectors. The similarity measurement is carried out first by employing norms calculating the distance between the covariation matrices representing two distinct images and second by evaluating the Kullback-Leibler Distance (KLD) between their corresponding subGaussian distributions. We provide analytical expressions relating the subGaussian features corresponding to a rotated image from the features of the original image. Finally, we relate the employed optimal lower-order correlation (p/spl les/2) to the degree of nonGaussianity of the wavelet coefficients, and we demonstrate the effectiveness of our method using real texture images.

Iterative reconstruction (IR) algorithms based on the principle of optimization are known for producing better reconstructed images in computed tomography. In this paper, we present an IR algorithm based on minimizing a symmetrized Kullback-Leibler divergence (SKLD) that is called Jeffreys’ J-divergence. The SKLD with iterative steps is guaranteed to decrease in convergence monotonically using a continuous dynamical method for consistent inverse problems. Specifically, we construct an autonomous differential equation for which the proposed iterative formula gives a first-order numerical discretization and demonstrate the stability of a desired solution using Lyapunov’s theorem. We describe a hybrid Euler method combined with additive and multiplicative calculus for constructing an effective and robust discretization method, thereby enabling us to obtain an approximate solution to the differential equation. We performed experiments and found that the IR algorithm derived from the hybrid discretization achieved high performance.

The techniques of eigenfaces and neural netbased algorithms (LS-SVM and BP NNs) are combined to categorize gender from facial images in this paper. Based on exploration of the ralated techniques, the eigenfaces were firstly established from the training images, and the projection coefficients for training and testing images obtained in the space spanned by the eigenfaces; after that the LS-SVM and BP classifiers are built with training coefficients, which are used for classifying training and testing images, and classification accuracy percentage values are calculated. The experiments are implemented with our self-made facial images, and the results demonstrate that LS-SVM classification has better performance than BP . In experiments we also use cross validation to determine the number of selected primary components and kernel function parameter.

This paper introduces a new speech enhancement algorithm based on the adaptive threshold of intrinsic mode functions (IMFs) of noisy signal frames extracted by empirical mode decomposition. Adaptive threshold values are estimated by using the gamma statistical model of Teager energy operated IMFs of noisy speech and estimated noise based on symmetric Kullback–Leibler divergence. The enhanced speech signal is obtained by a semisoft thresholding function, which is utilized by threshold IMF coefficients of noisy speech. The method is tested on the NOIZEUS speech database and the proposed method is compared with wavelet-shrinkage and EMD-shrinkage methods in terms of segmental SNR improvement (SegSNR), weighted spectral slope (WSS), and perceptual evaluation of speech quality (PESQ). Experimental results show that the proposed method provides a higher SegSNR improvement in dB, lower WSS distance, and higher PESQ scores than wavelet-shrinkage and EMD-shrinkage methods. The proposed method shows better performance than traditional threshold-based speech enhancement approaches from high to low SNR levels.

Deep neural networks have greatly improved the performance of rail surface defect segmentation when the test samples have the same distribution as the training samples. However, in practical inspection scenarios, the rail surface exhibits variations in appearance due to different service times and natural conditions. Conventional deep learning models show limited generalization in scenes with distribution differences. To address this problem, we propose a novel one-shot unsupervised domain adaptation framework. Specifically, we introduce a shape-consistent style transfer module that performs pixel-level distribution alignment between the training and test images. Based on the one-shot test image, the training image is reconstructed to have the same appearance as the test image. Meanwhile, we employ a multitask learning strategy to prevent content distortion of the reconstructed images. To improve the robustness of the model to distribution differences, we design an edge-aware defect segmentation model and train the model using the reconstructed training images. The experimental results show that our method effectively improves the robustness of the model to distribution differences and achieves satisfying results in the task of rail surface defect segmentation.

2D cine MR imaging may be utilized to monitor rapidly moving tumors and organs-at-risk for real-time adaptive radiotherapy. This study systematically investigates the impact of geometric imaging parameters on the ability of 2D cine MR imaging to guide template-matching-driven autocontouring of lung tumors and abdominal organs.Abdominal 4D MR images were acquired of six healthy volunteers and thoracic 4D MR images were obtained of eight lung cancer patients. At each breathing phase of the images, the left kidney and gallbladder or lung tumor, respectively, were outlined as volumes of interest. These images and contours were used to create artificial 2D cine MR images, while simultaneously serving as 3D ground truth. We explored the impact of five different imaging parameters (pixel size, slice thickness, imaging plane orientation, number and relative alignment of images as well as strategies to create training images). For each possible combination of imaging parameters, we generated artificial 2D cine MR images as training and test images. A template-matching algorithm used the training images to determine the tumor or organ position in the test images. Subsequently, a 3D base contour was shifted to the determined position and compared to the ground truth via centroid distance and Dice similarity coefficient.The median centroid distance between adapted and ground truth contours was 1.56 mm for the kidney, 3.81 mm for the gallbladder and 1.03 mm for the lung tumor (median Dice similarity coefficient: 0.95, 0.72 and 0.93). We observed that a decrease in image resolution led to a modest decrease in localization accuracy, especially for the small gallbladder. However, for all volumes of interest localization accuracy varied substantially more between subjects than due to the different imaging parameters.Automated tumor and organ localization using 2D cine MR imaging and template-matching-based autocontouring is robust against variation of geometric imaging parameters. Future work and optimization efforts of 2D cine MR imaging for real-time adaptive radiotherapy is needed to characterize the influence of sequence- and anatomical site-specific imaging contrast.

A feature-based modulation recognition algorithm is proposed, to identify practical multilevel amplitude phase shift keying (MAPSK) signals using template matching, which suffers from various unknown effects, including carrier frequency, time delay and phase shift. The probability distribution functions (PDFs) of the amplitudes for each modulation constellation are estimated from the corresponding analytic signal of a received intermediate frequency signal. Then, a template matching algorithm based on Kullback-Leibler divergence is used to evaluate the similarity between the PDF of the amplitude for a received signal and the PDF templates, which has been stored in advance. The simulation results show that the proposed modulation recognition algorithm performs robustly and precisely even in an extremely low signal-to-noise ratio. The performance of the proposed algorithm is not very sensitive to the number of used symbols or timing error, which means that the performance will not be seriously degraded with a less number of symbols or with a larger timing error for symbol synchronisation.

Background The rapid and widespread dissemination of medical misinformation on social media platforms poses a significant threat to public health, leading to treatment delays, vaccine hesitancy, and the adoption of harmful practices. Addressing the challenges of overfitting and prediction instability is crucial when fine-tuning pre-trained language models for Chinese microblog health rumor detection, especially given the short, emotionally charged, and noisy nature of public health surveillance data. Purpose This paper aims to propose a simple yet effective training strategy to enhance model generalization and robustness in detecting Chinese microblog health rumors. By integrating R-Drop consistency regularization with robust loss functions, this study seeks to establish a stronger and more reliable performance baseline for identifying and mitigating the impact of harmful health-related rumors, thereby contributing to a healthier online information ecosystem. Methods We fine-tuned two powerful pre-trained Chinese language models, RoBERTa-wwm-ext and MacBERT, using a large corpus from the public Chinese Emergency Corpus (CED) dataset. Our approach introduced R-Drop consistency regularization, which constrains prediction consistency through dual forward passes with dropout and minimizes symmetric Kullback-Leibler (KL) divergence. To handle noisy labels and class imbalance, we compared standard Cross-Entropy loss against Focal Loss and Symmetric Cross-Entropy (SCE), employing a stable learning rate schedule and early stopping to prevent overfitting. Results The MacBERT model consistently outperformed RoBERTa-wwm-ext in health rumor detection. R-Drop consistency regularization yielded stable and significant improvements across all configurations, enhancing both accuracy and F1-score. The optimal configuration, pairing MacBERT with standard Cross-Entropy loss and R-Drop, achieved a peak test accuracy of 0.9198. Notably, a well-regularized standard Cross-Entropy loss proved more effective for this dataset and task than the specialized robust loss functions. Conclusions This research successfully establishes that integrating R-Drop consistency regularization offers a computationally efficient, easily implementable, and highly effective training paradigm for advancing Chinese microblog health rumor detection. The proposed methodology provides a strong, reproducible, and high-performing baseline, offering valuable guidance for public health authorities and social media platforms in combating medical misinformation and enhancing automated systems for safeguarding public health.