Search Results (194)

Automatic noise-robust speaker identification is essential in various applications, including forensic analysis, e-commerce, smartphones, and security systems. Audio files containing suspect speech often include background noise, as they are typically not recorded in soundproof environments. To this end, we address the challenges of noise robustness and accuracy in speaker identification systems. An ensemble approach is proposed combining two different neural network architectures including an RNN and DNN using softmax. This approach enhances the system’s ability to identify speakers even in noisy environments accurately. Using softmax, we combine voice activity detection (VAD) with a multilayer perceptron (MLP). The VAD component aims to remove noisy frames from the recording. The softmax function addresses these residual traces by assigning a higher probability to the speaker’s voice compared to the noise. We tested our proposed solution on the Kaggle speaker recognition dataset and compared it to two baseline systems. Experimental results show that our approach outperforms the baseline systems, achieving a 3.6% and 5.8% increase in test accuracy. Additionally, we compared the proposed MLP system with Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) classifiers. The results demonstrate that the MLP with VAD and softmax outperforms the LSTM by 23.2% and the BiLSTM by 6.6% in test accuracy. Full article

It is difficult to automatically recognize defects using digital image processing methods in X-ray radiographs of lap joints made from plates of unequal thickness. The continuous change in the wall thickness of the lap joint workpiece causes very different gray levels in an X-ray background image. Furthermore, due to the shape and fixturing of the workpiece, the distribution of the weld seam in the radiograph is not vertical which results in an angle between the weld seam and the vertical direction. This makes automatic defect detection and localization difficult. In this paper, a method of X-ray image correction based on invariant moments is presented to solve the problem. In addition, a novel background removal method based on image processing is introduced to reduce the difficulty of defect recognition caused by variations in grayscale. At the same time, an automatic defect detection method combining image noise suppression, image segmentation, and mathematical morphology is adopted. The results show that the proposed method can effectively recognize the gas pores in an automatic welded lap joint of unequal thickness, making it suitable for automatic detection. Full article

As cracks are a precursor landslide deformation feature, they can provide forecasting information that is useful for the early identification of landslides and determining motion instability characteristics. However, it is difficult to solve the size effect and noise-filtering problems associated with the currently available automatic crack detection methods under complex conditions using single remote sensing data sources. This article uses multidimensional target scene images obtained by UAV photogrammetry as the data source. Firstly, under the premise of fully considering the multidimensional image characteristics of different crack types, this article accomplishes the initial identification of landslide cracks by using six algorithm models with indicators including the roughness, slope, eigenvalue rate of the point cloud and pixel gradient, gray value, and RGB value of the images. Secondly, the initial extraction results are processed through a morphological repair task using three filtering algorithms (calculating the crack orientation, length, and frequency) to address background noise. Finally, this article proposes a multi-dimensional information fusion method, the Bayesian probability of minimum risk methods, to fuse the identification results derived from different models at the decision level. The results show that the six tested algorithm models can be used to effectively extract landslide cracks, providing Area Under the Curve (AUC) values between 0.6 and 0.85. After the repairing and filtering steps, the proposed method removes complex noise and minimizes the loss of real cracks, thus increasing the accuracy of each model by 7.5–55.3%. Multidimensional data fusion methods solve issues associated with the spatial scale effect during crack identification, and the F-score of the fusion model is 0.901. Full article

Monitoring row centerlines during early growth stages is essential for effective production management. However, detection becomes more challenging due to weed interference and crop row intersection in images. This study proposed an enhanced Region of Interest (ROI)-based approach for detecting early-stage maize rows. It integrated a modified green vegetation index with a dual-threshold algorithm for background segmentation. The median filtering algorithm was also selected to effectively remove most noise points. Next, an improved ROI-based feature point extraction method was used to eliminate residual noises and extract feature points. Finally, the least square method was employed to fit the row centerlines. The detection accuracy of the proposed method was evaluated using the unmanned aerial vehicle (UAV) image data set containing both regular and intersecting crop rows. The average detection accuracy of the proposed approach was between 0.456° and 0.789° (the angle between the fitted centerline and the expert line), depending on whether crop rows were regular/intersecting. Compared to the Hough Transform (HT) algorithm, the results demonstrated that the proposed method achieved higher accuracy and robustness in detecting regular and intersecting crop rows. The proposed method in this study is helpful for refined agricultural management such as fertilization and irrigation. Additionally, it can detect the missing-seedling regions and replenish seedings in time to increase crop yields. Full article

Background: Lung cancer, also known as lung carcinoma, has a high mortality rate; however, an early prediction helps to reduce the risk. In the current literature, various approaches have been developed for the prediction of lung carcinoma (at an early stage), but these still have various issues, such as low accuracy, high noise, low contrast, poor recognition rates, and a high false-positive rate, etc. Thus, in this research effort, we have proposed an advanced algorithm and combined two different types of deep neural networks to make it easier to spot lung melanoma in the early phases. Methods: We have used WDSI (weakly supervised dense instance-level lung segmentation) for laborious pixel-level annotations. In addition, we suggested an SS-CL (deep continuous learning-based deep neural network) that can be applied to the labeled and unlabeled data to improve efficiency. This work intends to evaluate potential lightweight, low-memory deep neural net (DNN) designs for image processing. Results: Our experimental results show that, by combining WDSI and LSO segmentation, we can achieve super-sensitive, specific, and accurate early detection of lung cancer. For experiments, we used the lung nodule (LUNA16) dataset, which consists of the patients’ 3D CT scan images. We confirmed that our proposed model is lightweight because it uses less memory. We have compared them with state-of-the-art models named PSNR and SSIM. The efficiency is 32.8% and 0.97, respectively. The proposed lightweight deep neural network (DNN) model archives a high accuracy of 98.2% and also removes noise more effectively. Conclusions: Our proposed approach has a lot of potential to help medical image analysis to help improve the accuracy of test results, and it may also prove helpful in saving patients’ lives. Full article

Background: Heart rate (HR) is a critical biomarker that provides insights into overall health, stress levels, and the autonomic nervous system. Pulse wave signals contain valuable information about the cardiovascular system and heart status. However, signal acquisition in wearables poses challenges, particularly when using electrical sensors, due to factors like the distance from the heart, body movement, and suboptimal electrode placement. Methods: Electrical bioimpedance (EBI) measurements using bipolar and tetrapolar electrode systems were employed for pulse wave signal acquisition from the wrist in both perpendicular and distal configurations. Signal preprocessing techniques, including baseline removal via Hankel matrix methods, normalization, cross-correlation, and peak detection, were applied to improve signal quality. This study describes the combination of sensor-level signal acquisition and processing for accurate wearable HR estimation. Results: The bipolar system was shown to produce larger $\Delta Z\left(t\right)$, while the tetrapolar system demonstrated higher sensitivity. Distal placement of the electrodes yielded greater $\Delta Z\left(t\right)$ (up to 0.231 $\Omega$) when targeting both wrist arteries. Bandpass filtering resulted in a better signal-to-noise ratio (SNR), achieving 3.6 dB for the best bipolar setup and 4.8 dB for the tetrapolar setup, compared to 2.6 and 3.3 dB SNR, respectively, with the Savitzky–Golay filter. The custom HR estimation algorithm presented in this paper demonstrated improved accuracy over a reference method, achieving an average error of 1.8 beats per minute for the best bipolar setup, with a mean absolute percentage error (MAPE) of 8%. Conclusions: The analysis supports the feasibility of using bipolar electrode setups on the wrist and highlights the importance of electrode positioning relative to the arteries. The proposed signal processing method, featuring a preprocessing pipeline and HR estimation algorithm, provides a proof-of-concept demonstration for HR estimation from EBI signals acquired at the wrist. Full article

Based on the performance and acoustic data files of reduced-size open-rotor engines in low-speed wind tunnels, the static sound pressure level was derived by converting the 1-foot lossless spectral density into sound-pressure-level data, the background noise was removed, and the results were corrected according to the environmental parameters of the low-speed wind tunnels. In accordance with the requirements of Annex 16 of the Convention on International Civil Aviation Organization and Part 36 of the Civil Aviation Regulations of China on noise measurement procedures, the takeoff trajectory was physically modeled; the static noise source was mapped onto the takeoff trajectory to simulate the propagation process of the noise during takeoff; and the 24 one-third-octave center frequencies that corresponded to the SPL data were corrected for geometrical dispersion, atmospheric absorption, and Doppler effects, so that the takeoff noise could be corrected to represent a real environment. In addition, the audible processing of noise data with a 110° source pointing angle was achieved, which can be useful for enabling practical observers to analyze the noise characteristics. Full article

Background: Distantly supervised relation extraction (DSRE) aims to identify semantic relations in large-scale texts automatically labeled via knowledge base alignment. It has garnered significant attention due to its high efficiency, but existing methods are plagued by noise at both the word and sentence level and fail to address these issues adequately. The former level of noise arises from the large proportion of irrelevant words within sentences, while noise at the latter level is caused by inaccurate relation labels for various sentences. Method: We propose a novel multi-level noise reduction neural network (MLNRNN) to tackle both issues by mitigating the impact of multi-level noise. We first build an iterative keyword semantic aggregator (IKSA) to remove noisy words, and capture distinctive features of sentences by aggregating the information of keywords. Next, we implement multi-objective multi-instance learning (MOMIL) to reduce the impact of incorrect labels in sentences by identifying the cluster of correctly labeled instances. Meanwhile, we leverage mislabeled sentences with cross-level contrastive learning (CCL) to further enhance the classification capability of the extractor. Results: Comprehensive experimental results on two DSRE benchmark datasets demonstrated that the MLNRNN outperformed state-of-the-art methods for distantly supervised relation extraction in almost all cases. Conclusions: The proposed MLNRNN effectively addresses both word- and sentence-level noise, providing a significant improvement in relation extraction performance under distant supervision. Full article

In electrocardiograms (ECGs), multiple forms of encryption and preservation formats create difficulties for data sharing and retrospective disease analysis. Additionally, photography and storage using mobile devices are convenient, but the images acquired contain different noise interferences. To address this problem, a suite of novel methodologies was proposed for converting paper-recorded ECGs into digital data. Firstly, this study ingeniously removed gridlines by utilizing the Hue Saturation Value (HSV) spatial properties of ECGs. Moreover, this study introduced an innovative adaptive local thresholding method with high robustness for foreground–background separation. Subsequently, an algorithm for the automatic recognition of calibration square waves was proposed to ensure consistency in amplitude, rather than solely in shape, for digital signals. The original signal reconstruction algorithm was validated with the MIT–BIH and PTB databases by comparing the difference between the reconstructed and the original signals. Moreover, the mean of the Pearson correlation coefficient was 0.97 and 0.98, respectively, while the mean absolute errors were 0.324 and 0.241, respectively. The method proposed in this study converts paper-recorded ECGs into a digital format, enabling direct analysis using software. Automated techniques for acquiring and restoring ECG reference voltages enhance the reconstruction accuracy. This innovative approach facilitates data storage, medical communication, and remote ECG analysis, and minimizes errors in remote diagnosis. Full article

Painted cultural relics hold significant historical value and are crucial in transmitting human culture. However, mold is a common issue for paper or silk-based relics, which not only affects their preservation and longevity but also conceals the texture, patterns, and color information, hindering cultural value and heritage. Currently, the virtual restoration of painting relics primarily involves filling in the RGB based on neighborhood information, which might cause color distortion and other problems. Another approach considers mold as noise and employs maximum noise separation for its removal; however, eliminating the mold components and implementing the inverse transformation often leads to more loss of information. To effectively acquire virtual restoration for mold removal from ancient paintings, the spectral characteristics of mold were analyzed. Based on the spectral features of mold and the cultural relic restoration philosophy of maintaining originality, a 3D CNN artifact restoration network was proposed. This network is capable of learning features in the near-infrared spectrum (NIR) and spatial dimensions to reconstruct the reflectance of visible spectrum, achieving the virtual restoration for mold removal of calligraphic and art relics. Using an ancient painting from the Qing Dynasty as a test subject, the proposed method was compared with the Inpainting, Criminisi, and inverse MNF transformation methods across three regions. Visual analysis, quantitative evaluation (the root mean squared error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MEA), and a classification application were used to assess the restoration accuracy. The visual results and quantitative analyses demonstrated that the proposed 3D CNN method effectively removes or mitigates mold while restoring the artwork to its authentic color in various backgrounds. Furthermore, the color classification results indicated that the images restored with 3D CNN had the highest classification accuracy, with overall accuracies of 89.51%, 92.24%, and 93.63%, and Kappa coefficients of 0.88, 0.91, and 0.93, respectively. This research provides technological support for the digitalization and restoration of cultural artifacts, thereby contributing to the preservation and transmission of cultural heritage. Full article

Accurate peach detection is essential for automated agronomic management, such as mechanical peach harvesting. However, ubiquitous occlusion makes identifying peaches from complex backgrounds extremely challenging. In addition, it is difficult to capture fine-grained peach features from a single RGB image, which can suffer from light and noise in scenarios with dense small target clusters and extreme light. To solve these problems, this study proposes a multimodal detector, called CRLNet, based on RGB and depth images. First, YOLOv9 was extended to design a backbone network that can extract RGB and depth features in parallel from an image. Second, to address the problem of information fusion bias, the Rough–Fine Hybrid Attention Fusion Module (RFAM) was designed to combine the advantageous information of different modes while suppressing the hollow noise at the edge of the peach. Finally, a Transformer-based Local–Global Joint Enhancement Module (LGEM) was developed to jointly enhance the local and global features of peaches using information from different modalities in order to enhance the percentage of information about the target peaches and remove the interference of redundant background information. CRLNet was trained on the Peach dataset and evaluated against other state-of-the-art methods; the model achieved an $mA{P}_{50}$ of 97.1%. In addition, CRLNet also achieved an $mA{P}_{50}$ of 92.4% in generalized experiments, validating its strong generalization capability. These results provide valuable insights for peach and other outdoor fruit multimodal detection. Full article

The consistent speckle noise in SAR images easily interferes with the semantic information of the target. Additionally, the limited quantity of supervisory information available in one-shot learning leads to poor performance. To address the aforementioned issues, we creatively propose an SAR target recognition model based on one-shot learning. This model incorporates a background noise removal technique to eliminate the interference caused by consistent speckle noise in the image. Then, a global and local complementary strategy is employed to utilize the data’s inherent a priori information as a supplement to the supervisory information. The experimental results show that our approach achieves a recognition performance of 70.867% under the three-way one-shot condition, which attains a minimum improvement of 7.467% compared to five state-of-the-art one-shot learning methods. The ablation studies demonstrate the efficacy of each design introduced in our model. Full article

(1) Background: The electroencephalogram (EEG) is frequently corrupted by ocular artifacts such as saccades and blinks. Methods for correcting these artifacts include independent component analysis (ICA) and recursive-least-squares (RLS) adaptive filtering (-AF). Here, we introduce a new method, AFFiNE, that applies Bayesian adaptive regression spline (BARS) fitting to the adaptive filter’s reference noise input to address the known limitations of both ICA and RLS-AF, and then compare the performance of all three methods. (2) Methods: Artifact-corrected P300 morphologies, topographies, and measurements were compared between the three methods, and to known truth conditions, where possible, using real and simulated blink-corrupted event-related potential (ERP) datasets. (3) Results: In both simulated and real datasets, AFFiNE was successful at removing the blink artifact while preserving the underlying P300 signal in all situations where RLS-AF failed. Compared to ICA, AFFiNE resulted in either a practically or an observably comparable error. (4) Conclusions: AFFiNE is an ocular artifact correction technique that is implementable in online analyses; it can adapt to being non-stationarity and is independent of channel density and recording duration. AFFiNE can be utilized for the removal of blink artifacts in situations where ICA may not be practically or theoretically useful. Full article

Acoustic emission (AE) technology has been widely utilized to monitor the SiC wafer lapping process. The root-mean-square (RMS) of the time–domain eigenvalues of the AE signal has a linear relationship with the material removal rate (MRR). However, the existence of background noise severely reduces signal monitoring accuracy. Noise interference often leads to increased RMS deviation and signal distortion. In the study presented in this manuscript, a frequency threshold noise reduction approach was developed by combining and improving wavelet packet noise reduction and spectral subtraction noise reduction techniques. Three groups of SiC lapping experiments were conducted on a fixed abrasive pad, and the lapping acoustic signals were processed using three different noise reduction approaches: frequency threshold, wavelet packet, and spectral subtraction. The results show that the noise reduction method using the frequency threshold is the most effective, with the best coefficient of determination (R²) for the linear fit of the RMS to the MRR. Full article

The orange (Citrus sinensis) is a fruit of the Citrus genus, which is part of the Rutaceae family. The orange has gained considerable importance due to its extensive range of applications, including the production of juices, jams, sweets, and extracts. The consumption of oranges confers several nutritional benefits, including flavonoids, vitamin C, potassium, beta-carotene, and dietary fiber. It is crucial to acknowledge that the primary quality criterion employed by consumers and producers is maturity, which is correlated with the visual quality associated with the color of the epicarp. This study proposes the implementation of a computer vision system that estimates the degree of ripeness of oranges Valencia using fuzzy logic (FL); the soluble solids content was determined by refractometry, while the firmness of the fruit was evaluated through the fruit firmness test. The proposed method was divided into five distinct steps. The initial stage involved the acquisition of RGB images. The second stage presents the segmentation of the fruit, which entails the removal of extraneous noise and backgrounds. The third and fourth steps involve determining the centroid of the fruit, and five regions of interest were obtained in the centroid of the fruit of the Citrus Color Index (CII), ranging from 3 × 3 to 11 × 11 pixels. Finally, in the fifth step, a model was created to estimate maturity, °Brix, and firmness using Matlab 2024 and the Fuzzy Logic Designer and Neuro-Fuzzy Designer applications. Consequently, a statistically significant correlation was established between maturity, degree Brix, and firmness, with a value greater than 0.9, using the Citrus Color Index (CII), which reflects the physical–chemical changes that occur in the orange. Full article