Narrow Results

As the most popular nonlinear denoise technique, the median filter has attracted significant attention in recent years. In this paper, a novel adaptive median filter is presented to remove random-valued impulse noise in images, named Adaptive Partition-Cluster-Based Median (APCM) Filter. Based on the partition cluster idea, the noise detector classifies pixels into different groups and identifies the noisy pixels in different regions adaptively without iterations. According to the results of noise detection, an improved adaptive decision-based filter is presented to restore the pixels which are corrupted by random-valued impulse noise. The proposed filter technique is open to any impulse noise. Extensive simulation results demonstrate that the proposed method substantially outperforms other state-of-the-arts impulse noise filter techniques both visually and in terms of objective quality measures. Furthermore, the proposed method is much friendly to the hardware parallel implementation of image processing because of its low computation complexity and simple realizable structure.

Salt-and-pepper noise suppression for vector-valued images usually employs vector median filtering, total variation L1 model, diffusion methods and variants. These approaches, however, often introduce excessive smoothing and can result in extensive visual feature blurring and are suitable only for images with low intensity noise. In this paper, a new method, as an important preprocessing step in cyber-physical systems, is presented to suppress salt-and-pepper noise that can overcomes this limitation. This method first detects the corrupted pixels and then restores them using channel-wise anisotropic diffusion. The means is twofold. On the one hand, the marginal approach is used to perform noise suppression separately in each channel because the contaminative pixel components are of independent distribution. On the other hand, a decision-based anisotropic diffusion method is applied to each channel to restores them. The anisotropic diffusion is an energy-dissipating process with time, and dependent on geometric analysis of shape of the energy surface. Simulation results indicate that the proposed method for impulsive noise removal achieves the state-of-the-arts results.

The performance of a classification model is invariably affected by the characteristics of the measurement data it is built upon. If the quality of the data is generally poor, then the classification model will demonstrate poor performance. The detection and removal of noisy instances will improve quality of the data, and consequently, the performance of the classification model. We investigate a noise handling technique that attempts to improve the quality of datasets for classification purposes by eliminating instances that are likely to be noise. Our approach uses twenty five different classification techniques to create an ensemble filter for eliminating likely noise. The basic assumption is that if a given majority of classifiers in the ensemble misclassify an instance, then it is likely to be a noisy instance. Using a relatively large number of base-level classifiers in the ensemble filter facilitates in achieving the desired level of noise removal conservativeness with several possible levels of filtering. It also provides a higher degree of confidence in the noise elimination procedure as the results are less likely to get influenced by (possibly) inappropriate learning bias of a few algorithms with twenty five base-level classifiers than with relatively smaller number of base-level classifiers. Empirical case studies of two high assurance software projects demonstrates the effectiveness of our noise elimination approach by the significant improvement achieved in classification accuracies at various levels of noise filtering.

There is extensive prior research in coronary artery disease (CAD) detection using sounds recorded from the chest. The acoustic approach to CAD detection is cost-effective, noninvasive and easy to implement; however, it is sensitive to external and internal noise commonly encountered in the clinical setting, which can reduce its reliability. If this noise can be accurately detected and eliminated, the accuracy of the acoustic approach to CAD detection can be significantly improved. In this paper, we develop and evaluate an algorithm to detect noise in acoustic recordings made in the clinical setting. This approach uses signals from a reference microphone placed near the stomach that detects both external and internal noise in the acoustic recording. Applying spectral subtraction and a histogram-based threshold to the reference signal, we are able to identify and eliminate segments that contain noise in the acoustic recording. This algorithm is effective in detecting noise from both external and internal sources.