This paper studies the combination of a centre-weighted median filter with block matching 3-dfiltering for digital images with mixed impulsive and Gaussian noise. The proposed combinedfilter has an extended applicat...
详细信息
This paper studies the combination of a centre-weighted median filter with block matching 3-dfiltering for digital images with mixed impulsive and Gaussian noise. The proposed combinedfilter has an extended application range with respect to both components. The work in the paper derives a simple formula for selecting the weight of the centre-weighted median filter. Adaptive weights are given for neighbourhoods 3 x 3 and wider as functions of the impulsive noise percentage and Gaussian noise strength. Simulation results confirm the effectiveness of the proposed combinedfilter.
In dark or poorly lit environments, it is often difficult for the naked eye to distinguish low-light-level images because of low brightness, low contrast and noise, and it is difficult to perform subsequent image proc...
详细信息
In dark or poorly lit environments, it is often difficult for the naked eye to distinguish low-light-level images because of low brightness, low contrast and noise, and it is difficult to perform subsequent image processing (such as video surveillance and target detection). To solve these problems, this paper proposes a low-light-level image enhancement algorithm based on deep learning. First, the low-light-level image is segmented into several super-pixels, and the noise level of each super-pixel is estimated by the ratio of the local standarddeviation to the local gradient. Then, the image is inverted and smoothed by a bm3d filter, and the structural filter adaptive method is used to obtain complete images without noise but with the correct texture. Finally, the noise-free image and texture-complete images are applied to the integrated network, which can not only enhance the contrast but also effectively prevent the over-enhancement of the contrast. The experimental results show that this method is superior to traditional methods in terms of both subjective and objective evaluation, and the peak signal-noise ratio and improved structural similarity are 31.64 dB and 91.2%, respectively.
Breast cancer is a widespread health threat for women globally, often difficult to detect early due to its asymptomatic nature. As the disease advances, treatment becomes intricate and costly, ultimately resulting in ...
详细信息
Breast cancer is a widespread health threat for women globally, often difficult to detect early due to its asymptomatic nature. As the disease advances, treatment becomes intricate and costly, ultimately resulting in elevated fatality rates. Currently, despite the widespread use of advanced machine learning (ML) anddeep learning (dL) techniques, a comprehensive diagnosis of breast cancer remains elusive. Most of the existing methods primarily utilize either attention-baseddeep models or models based on handcrafted features to capture and gather local details. However, both of these approaches lack the capability to offer essential local information for precise tumor detection. Additionally, the available breast cancer datasets suffer from class imbalance issue. Hence, this paper presents a novel weighted average ensemble network (WA-ENet) designed for early-stage breast cancer detection that leverages the ability of ensemble technique over single classifier-based models for more robust and accurate prediction. The proposed model employs a weighted average-based ensemble technique, combining predictions from three diverse classifiers. The optimal combination of weights is determined using the hill climbing (HC) algorithm. Moreover, the proposed model enhances overall system performance by integrating deep features and handcrafted features through the use of HOG, thereby providing precise local information. Additionally, the proposed work addresses class imbalance by incorporating borderline synthetic minority over-sampling technique (BSMOTE). It achieves 99.65% accuracy on BUSI and 97.48% on UdIAT datasets.
A novel experimental method based on the Coulomb coupling technique is used for visualizing the interaction of ultrasonic waves in PZT (Lead Zirconate Titanate - (Pb[ZrxTi1-x]O3 (0 < x < 1)) ceramic materials. T...
详细信息
A novel experimental method based on the Coulomb coupling technique is used for visualizing the interaction of ultrasonic waves in PZT (Lead Zirconate Titanate - (Pb[ZrxTi1-x]O3 (0 < x < 1)) ceramic materials. The method of excitation anddetection through a point contact produces representations of propagating wave vectors in the time domain as a series of images. In the acoustic image, several types of noises from different types of sources corrupt the signal as well as the image. As a result, the resolution and quality of the images are reduced. Block matching and3dfiltering (bm3d) algorithm is implemented for the reduction of noises from ultrasonic signals that are in the form of 2d images. Here, we also implemented a custom-designed hybridfilter and conventional total variation (TV-L1) filter on the noisy images to compare the final denoised outputs from the bm3d filter. Comparison metrics like PSNR (peak signal-to-noise ratio) and SSIM (structural similarity index measure) are used for quantitative analysis of those denoised ultrasonic images with respect to their ground truth or almost noise-free counterparts. Based upon those parameter values, the bm3d filterdemonstrated the best results for the denoising of the acoustic images acquired from the sample PZT material. This paper discusses and explains the results and proves the successful application of the bm3d algorithm on acoustic image data.
Similar blocks (patches) search plays an important role in image processing. However, there are many factors making this search problematic and leading to errors. Noise in images that arises due to bad acquisition con...
详细信息
ISBN:
(纸本)9780819499363
Similar blocks (patches) search plays an important role in image processing. However, there are many factors making this search problematic and leading to errors. Noise in images that arises due to bad acquisition conditions or other sources is one of the main factors. Performance of similar patch search might make worse dramatically if noise level is high and/or if noise is not additive, white and Gaussian. In this paper, we consider the influence of similarity metrics (distances) on search performance. We demonstrate that robustness of similarity metrics is a crucial issue for performance of similarity search. Two models of additive noise are used: AWGN and spatially correlated noise with a wide set of noise standarddeviations. To investigate metric performance, five test images are used for artificially inserted group of identical blocks. Metric effectiveness evaluation is carried out for nine different metric (including several unconventional ones) in three domains (one spatial and two spectral). It is shown that conventional Euclidian metric might be not the best choice which depends upon noise properties anddata processing domain. After establishing the best metrics, they are exploited within non-local image denoising, namely the bm3d filter. This filter is applied to intensity images of the database TId2008. It is demonstrated that the use of more robust metrics instead of classical ones (Euclidean) in bm3d filter allows improving similar block search and, as a result, provides better results of image denoising for the case of spatially correlated noise.
暂无评论