Gray Histogram Research Articles

Investigation on intermittent flow characteristics in horizontal pipe by visualization measurement method

Accurate measurement and prediction of the intermittent flow characteristics in horizontal pipes is important for constructing multiphase flow models and ensuring pipe flow safety. In this paper, a quantitative image post-processing technique for intermittent flow characteristics based on gray histogram image similarity is proposed, which can realize the measurement of slug frequency. In addition, the technique also has the ability to classify a large number of images, and can quickly find the elongated bubble head, liquid film area and liquid slug area of intermittent flow. On the basis of this technique, combined with image post-processing methods such as gas–liquid interface feature analysis, a set of intermittent flow image processing technique with perfect route is formed. Based on this post-processing technique, the similarity image oscillation trajectories of plug flow and slug flow are obtained. There are differences in the similarity image oscillation trajectories of the two intermittent sub-flow patterns, and the similarity image of the plug flow has an obvious platform period and trailing rising line, which can be used as a basis for the classification of the two intermittent sub-flow patterns. A correlation for predicting the slug frequency of intermittent sub-flow patterns is developed. The accuracy of this slug frequency prediction correlation can be improved by about 10 % compared to not dividing the sub-flow patterns. When the mixture Froude number Frm is less than 5.0, the radial position of the elongated bubble head decreases linearly as the Frm increases. When the Frm is greater than 5.0, the elongated bubble head oscillates near the middle of the pipe. Prediction correlations for the radial position of the elongated bubble head and the slug velocity are established separately, and the maximum error is ± 10 %. The modified mixed Froude number is proposed, and based on this, a new prediction model for the transition from plug flow to slug flow is established.

Exploring the Influence of Object, Subject, and Context on Aesthetic Evaluation through Computational Aesthetics and Neuroaesthetics

Background: In recent years, computational aesthetics and neuroaesthetics have provided novel insights into understanding beauty. Building upon the findings of traditional aesthetics, this study aims to combine these two research methods to explore an interdisciplinary approach to studying aesthetics. Method: Abstract artworks were used as experimental materials. Based on traditional aesthetics and in combination, features of composition, tone, and texture were selected. Computational aesthetic methods were then employed to correspond these features to physical quantities: blank space, gray histogram, Gray Level Co-occurrence Matrix (GLCM), Local Binary Pattern (LBP), and Gabor filters. An electroencephalogram (EEG) experiment was carried out, in which participants conducted aesthetic evaluations of the experimental materials in different contexts (genuine, fake), and their EEG data were recorded to analyze the impact of various feature classes in the aesthetic evaluation process. Finally, a Support Vector Machines (SVMs) was utilized to model the feature data, Event-Related Potentials (ERPs), context data, and subjective aesthetic evaluation data. Result: Behavioral data revealed higher aesthetic ratings in the genuine context. ERP data indicated that genuine contexts elicited more negative deflections in the prefrontal lobes between 200 and 1000 ms. Class II compositions demonstrated more positive deflections in the parietal lobes at 50–120 ms, while Class I tones evoked more positive amplitudes in the occipital lobes at 200–300 ms. Gabor features showed significant variations in the parieto-occipital area at an early stage. Class II LBP elicited a prefrontal negative wave with a larger amplitude. The results of the SVM models indicated that the model incorporating aesthetic subject and context data (ACC = 0.76866) outperforms the model using only parameters of the aesthetic object (ACC = 0.68657). Conclusion: A positive context tends to provide participants with a more positive aesthetic experience, but abstract artworks may not respond to this positivity. During aesthetic evaluation, the ERP data activated by different features show a trend from global to local. The SVM model based on multimodal data fusion effectively predicts aesthetics, further demonstrating the feasibility of the combined research approach of computational aesthetics and neuroaesthetics.

Siam-AUnet: An end-to-end infrared and visible image fusion network based on gray histogram

Infrared and visible image fusion aim to leverage the respective advantages of both modalities to extract richer information from a scene. In environments with ample lighting, it is imperative to preserve the characteristics of visible images and salvage details lost due to overexposure. Conversely, in dark environments, a preference is typically inclined towards the utilization of infrared imagery. However, current methodologies are unable to adaptively modulate their tendency towards either modality, thereby resulting in suboptimal fusion quality. A gray histogram visually represents the dynamic range of image distribution, revealing the contrast and degree of brightness variations. Drawing from this insight, in this paper, we propose a novel image fusion method called Siam-AUnet for the first time. This methodology transforms the distribution of luminance histograms extracted from visible images into weights during the fusion of the two modalities. We adopt a Siamese network architecture and a multi-scale attention mechanism to focus more effectively on key features while reducing the number of parameters. Extensive experiments on different datasets and comparisons with other methods have demonstrated the superiority of this fusion approach. By utilizing the characteristics of the histogram, Siam-AUnet can adaptively tend towards the modality with clearer texture details. Qualitative and quantitative experimental results on the MSRS test dataset demonstrate that Siam-AUnet achieves optimal performance in terms of EN, SSIM, and MS_SSIM, while exhibiting suboptimal performance in metrics such as SCD, VIF, and Qqbf. In well-lit conditions, it can preserve the detailed features of visible images and the salient features of infrared images; while under adverse lighting conditions, it emphasizes the infrared modality features more strongly. Our code will be publicly available at https://github.com/xkangKK/Siam-AUnet.

Advancements in low light image enhancement techniques and recent applications

Low-light image enhancement is an effective solution for improving image recognition by both humans and machines. Due to low illuminance, images captured in such conditions possess less color information compared to those taken in daylight, resulting in occluded images characterized by distortion, low contrast, low brightness, a narrow gray range, and noise. Low-light image enhancement techniques play a crucial role in enhancing the effectiveness of object detection. This paper reviews state-of-the-art low-light image enhancement techniques and their developments in recent years. Techniques such as gray transformation, histogram equalization, defogging, Retinex, image fusion, and wavelet transformation are examined, focusing on their working principles and assessing their ability to improve image quality. Further discussion addresses the contributions of deep learning and cognitive approaches, including attention mechanisms and adversarial methods, to image enhancement.

Experimental study on mechanical and microstructure properties of cemented tailings-waste rock backfill with continuous gradation

To reduce the risk of engineering disasters and improve the comprehensive utilization rate of solid waste from mines, cementitious tailings-wasted rock filling as a green and safe technology has been widely used in mines. Mechanical properties and microstructural characterization of cementitious tailings-wasted rock backfill (CTWRB) prepared with gradation coefficients (n) of 0.3–0.7 and waste rock contents (e.g., 10 %, 20 %, 30 %, 40 %, and 50 %) were investigated by using UCS (unconfined compressive strength) tests (e.g., peak strength, stress-strain curves, and damage modes), surface strain field analysis and SEM micro-graphs. The results indicate that the UCS value shows an overall “increasing and then decreasing trend” with increasing gradation factor n and waste rock dosage. The UCS value of CTWRB is maximum at 3.94 MPa when n = 0.5 and waste rock admixture is 30 %. The UCS has increased by 17.96 %. The compacting stage of CTWRB is more pronounced under loading. In the post-peak stage, CTWRB has superior resistance to deformation damage. The destruction form of backfill is dominated by the tension destruction parallel to the loading direction. The waste rock constrains the expansion path of cracks inside the specimen, which can effectively improve the UCS of backfill. The grayscale of the strain field in CTWRB shifts towards higher gray levels. The proportion of peaks in the strain field gray histogram changes slowly at first and then rapidly, with the peak stress serving as the boundary. Ettringite/CSH gel are the main hydration products in the backfill material. An overvalue of n leads to worse densification of the specimen and increased voids, which causes the UCS of CTWRB to decrease. The study's results could be a significant guide for ensuring safe mining production.

Identifying gastric cancer by optical coherence tomography based on an optimized depth-resolved attenuation estimation

Optical coherence tomography (OCT) is a reliable technique for cancer detection, with the potential to improve accuracy in identifying cancerous tissue through effective use of OCT image data. We proposed an optimized depth resolution estimation based optical attenuation coefficient (OAC) mapping method to reduce the error effect caused by discretization without considering whether the light is completely attenuated or not. The attenuation coefficient maps of gastric tissue were reconstructed using this method. Features were extracted from these maps using gray-level co-occurrence matrix and gray histogram, and a support vector machine was employed as a classifier for identifying gastric cancer tissues. The recognition accuracy achieved was 98.60%, which was higher than the 94.30% accuracy in the control group without OACs. This approach enhances the utilization of OCT image information and improves its practical application ability by increasing the recognition accuracy.

Pressure-Insensitive Epidermal Thickness of Fingertip Skin for Optical Image Encryption.

In this study, an internal fingerprint-guided epidermal thickness of fingertip skin is proposed for optical image encryption based on optical coherence tomography (OCT) combined with U-Net architecture of a convolutional neural network (CNN). The epidermal thickness of fingertip skin is calculated by the distance between the upper and lower boundaries of the epidermal layer in cross-sectional optical coherence tomography (OCT) images, which is segmented using CNN, and the internal fingerprint at the epidermis-dermis junction (DEJ) is extracted based on the maximum intensity projection (MIP) algorithm. The experimental results indicate that the internal fingerprint-guided epidermal thickness is insensitive to pressure due to normal correlation coefficients and the encryption process between epidermal thickness maps of fingertip skin under different pressures. In addition, the result of the numerical simulation demonstrates the feasibility and security of the encryption scheme by structural similarity index matrix (SSIM) analysis between the original image and the recovered image with the correct and error keys decryption, respectively. The robustness is analyzed based on the SSIM value in three aspects: different pressures, noise attacks, and data loss. Key randomness is valid by the gray histograms, and the average correlation coefficients of adjacent pixelated values in three directions and the average entropy were calculated. This study suggests that the epidermal thickness of fingertip skin could be seen as important biometric information for information encryption.

Enhancing the Visual Effectiveness of Overexposed and Underexposed Images in Power Marketing Field Operations Using Gray Scale Logarithmic Transformation and Histogram Equalization

Abstract In this paper, we propose an adaptive gamma transform that adjusts the local values of bright and dark parts to enhance the effect of low-illumination images, thereby improving the light component. We then apply diff texture enhancement to enhance the contrast of images processed by the Retinex algorithm, thereby optimizing the perception of overexposed and underexposed imagery. Analyze the effect of image brightness enhancement based on a nonlinear transformation combined with the LOL dataset. Use PSNR and SSIM image quality evaluation criteria to analyze the visual effect of improving low-illumination images based on Retinex theory. Create a dataset of power marketing field operation inspection images and examine the effects of overexposure and underexposure image processing on four types of images: high-voltage towers, transmission lines, high-voltage fixtures, and high-voltage wireframes, using the low-light image texture fusion algorithm based on Retinex theory. Overall, this paper’s algorithm and the three DeblurGAN and DMCNN models achieve the effect of deblurring overexposed and underexposed power marketing field operation inspection images. From the local details, the model in this paper has a better effect on the de-exposure of the image, which can provide effective help for the electric power staff to understand the situation of the electric power marketing operation site and has strong practicality.

Microcosmic characteristics of particulate matter emitted by GDI gasoline engine in plateau environment

The particulate matter samples of gasoline direction injection (GDI) gasoline engine obtained from road experiments are photographed to obtain the emission particulate matter images based on the transmission electron microscope under high altitude environment. The results show that the micro-morphology characteristics of the particulate matter emitted by GDI gasoline engine in plateau area are similar to those in low altitude area, and the main morphology is cloud-like, filamentous, flocculent, chain-like, cluster-like, like altitude contour line, etc. The images are processed by MATLAB and Python software, and the fractal dimension, average gray value and gray histogram are obtained. The fractal dimensions of the emission particulate data obtained are between 1.81 and 1.89, which has some deviation compared with the fractal dimension of the emission particulate data at low altitude of 1.58 and 1.80. With the increase of altitude, its fractal dimension increases more obviously. It can be seem from the characteristics of gray value and gray histogram of particle images that the average gray value of GDI gasoline engine particles is higher. The gray histogram distribution of 5–50 nm images is uniform, and the individual particles in the images are clear. The gray histogram of 100–500 nm images is scattered, so it is easy to extract and separate the image edge contour. 5–50 nm images are used to study the details and characteristics of individual particles, and 100–500 nm transmission electron microscope images are used to study the overall morphology of particles.

Mix and measure - Combining in situ X-ray powder diffraction and microtomography for accurate hydrating cement studies

It is reported an innovative methodology based on in situ MoKα1 laboratory X-ray powder diffraction (LXRPD) and microtomography (μCT) avoiding any sample conditioning. The pastes are injected in 2.0 mm capillaries and the extremes are just sealed. The measurements take place in the same region of the hydrating paste. Thick capillaries are key to avoiding self-desiccation, which dictates the need of high-energy X-ray radiation for the diffraction study. This approach has been tested with a PC 42.5 R paste having w/c = 0.50. μCT data were collected at 12 h and 1, 3, 7 and 79 days. LXRPD data were acquired at 1, 3, 7 and 77 days. In this proof-of-principle research, the same paste was also cured ex situ. Portlandite contents obtained by thermal analysis, ex situ powder diffraction, in situ mass balance calculation and in situ powder diffraction were 13.8, 13.1, 13.1 and 12.5 wt%, respectively. From the μCT study, the grey value histogram evolution with time showed a crossing point which allowed us to distinguish (appearing) hydrated products from (dissolving) unhydrated cement particles. Segmentations were carried out by global thresholding and the random forest approach (one type of supervised Machine Learning). The comparison of the segmented results for the unhydrated cement fraction and the Rietveld quantitative phase analysis outputs gave an agreement of 2 %. The potential of this methodology to deal with more complex binders is also presented.

Prognostic Value of Metabolic Parameters and Textural Features in Pretreatment 18F-FDG PET/CT of Primary Lesions for Pediatric Patients with Neuroblastoma

Our study evaluated the prognostic value of the metabolic parameters and textural features in pretreatment 18F-Fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) of primary lesions for pediatric patients with neuroblastoma. In total, 107 pediatric patients with neuroblastoma who underwent pretreatment 18F-FDG PET/CT were retrospectively included and analyzed. All patients were diagnosed by pathology, and baseline characteristics and clinical data were collected. The four metabolic parameters and 43 textural features of 18F-FDG PET/CT of the primary lesions were measured. The prognostic significance of metabolic parameters and other clinical variables was assessed using Cox proportional hazards regression models. Differences in progression-free survival (PFS) and overall survival (OS) in relation to parameters were examined using the Kaplan-Meier method. During a median follow-up period of 34.3 months, 45 patients (42.1%) experienced tumor recurrence or progression, and 21 patients (19.6%) died of cancer. In univariate Cox regression analysis, age, location of disease, International Neuroblastoma Risk Group Staging System (INRGSS) stage M, neuron-specific enolase (NSE), lactate dehydrogenase (LDH), four positron emission tomography (PET) metabolic parameters, and 33 textural features were significant predictors of PFS. In multivariate analysis, INRGSS stage M (hazard ratio [HR]=19.940, 95% confidence interval [CI]=2.733-145.491, P=0.003), skewness (＞0.173; PET first-order features; HR=2.938, 95% CI=1.389-6.215, P=0.005), coarseness (＞0.003; neighborhood gray-tone difference matrix; HR=0.253, 95% CI=0.132-0.484, P＜0.001), and variance (＞103.837; CT first-order gray histogram parameters; HR=2.810, 95% CI=1.160-6.807, P=0.022) were independent predictors of PFS. In univariate Cox regression analysis, gender, INRGSS stage M, MYCN amplification, NSE, LDH, two PET metabolic parameters, and five textural features were significant predictors of OS. In multivariate analysis, INRGSS stage M (HR=7.704, 95% CI=1.031-57.576, P=0.047), MYCN amplification (HR=3.011, 95% CI=1.164-7.786, P=0.023), and metabolic tumor volume (＞138.788; HR=3.930, 95% CI=1.317-11.727, P=0.014) were independent predictors of OS. The metabolic parameters and textural features in pretreatment 18F-FDG PET/CT of primary lesions are predictive of survival in pediatric patients with neuroblastoma.

Combination of effective color information and machine learning for rapid prediction of soil water content

Soil water content (SWC) is one of the critical indicators in various fields such as geotechnical engineering and agriculture. To avoid the time-consuming, destructive, and laborious drawbacks of conventional SWC measurements, the image-based SWC prediction is considered based on recent advances in quantitative soil color analysis. In this study, a promising method based on the Gaussian-fitting gray histogram is proposed for extracting characteristic parameters by analyzing soil images, aiming to alleviate the interference of complex surface conditions with color information extraction. In addition, an identity matrix consisting of 32 characteristic parameters from eight color spaces is constituted to describe the multi-dimensional information of the soil images. Meanwhile, a subset of 10 parameters is identified through three variable analytical methods. Then, four machine learning models for SWC prediction based on partial least squares regression (PLSR), random forest (RF), support vector machines regression (SVMR), and Gaussian process regression (GPR), are established using 32 and 10 characteristic parameters, and their performance is compared. The results show that the characteristic parameters obtained by Gaussian-fitting can effectively reduce the interference from soil surface conditions. The RGB, CIEXYZ, and CIELCH color spaces and lightness parameters, as the inputs, are more suitable for the SWC prediction models. Furthermore, it is found that 10 parameters could also serve as optimal and generalizable predictors without considerably reducing prediction accuracy, and the GPR model has the best prediction performance (R2 ≥ 0.95, RMSE ≤ 2.01%, RPD ≥ 4.95, and RPIQ ≥ 6.37). The proposed image-based SWC predictive models combined with effective color information and machine learning can achieve a transient and highly precise SWC prediction, providing valuable insights for mapping soil moisture fields.

Real-Time Video Smoke Detection Based on Deep Domain Adaptation for Injection Molding Machines

Leakage with smoke is often accompanied by fire and explosion hazards. Detecting smoke helps gain time for crisis management. This study aims to address this issue by establishing a video smoke detection system, based on a convolutional neural network (CNN), with the help of smoke synthesis, auto-annotation, and an attention mechanism by fusing gray histogram image information. Additionally, the study incorporates the domain adversarial training of neural networks (DANN) to investigate the effect of domain shifts when adapting the smoke detection model from one injection molding machine to another on-site. It achieves the function of domain confusion without requiring labeling, as well as the automatic extraction of domain features and automatic adversarial training, using target domain data. Compared to deep domain confusion (DDC), naïve DANN, and the domain separation network (DSN), the proposed method achieves the highest accuracy rates of 93.17% and 91.35% in both scenarios. Furthermore, the experiment employs t-distributed stochastic neighbor embedding (t-SNE) to facilitate fast training and smoke detection between machines by leveraging domain adaption features.

Quantification of brain developmental trajectories based on histogram parameters at slice of the anterior and posterior horns of the lateral ventricles on routine brain MRI in normal children aged 0 to 5 years

Objective: To investigate the value of histogram parameters in quantifying brain development trajectory at slice of anterior and posterior horns of lateral ventricles on conventional brain MRI in normal children aged 0-5 years. Methods: Routine brain MRI data [apparent diffusion coefficient (ADC) map, T1-weighted imaging (T1WI), and T2-weighted imaging (T2WI)] were retrospectively collected from 300 children aged 0-5 years who underwent MRI at Children 's Hospital of Nanjing Medical University from April 2014 to November 2021, 154 males and 146 females, aged [M (Q1, Q3) ] 35.57(17.98,50.66)months. According to the random sampling method, they were divided into training set (n=240) and validation set (n=60) in a ratio of 8∶2. The training set was divided into 6 groups according to age:≤0.5 years, 24 persons; >0.5-≤1 years,21 persons; >1-≤2 years,31 persons; >2-≤3 years,44 persons; >3-≤4 years,42 persons; >4-≤5 years,78 persons. MRIcron software was used to delineate the whole brain at the level of the anterior and posterior horns of the lateral ventricles of the three MRI data as the region of interest. Then gray histograms and their parameters [including mean, maximum, minimum, skewness, kurtosis, mode, variance, and percentiles at 5% intervals from 10% to 95%(10th-95th) ]were obtained. Intra-class correlation coefficients (ICC) were used to assess consistency of intra-observer and inter-observer measurement. Representative parameters were selected by Spearman correlation analysis and curve fitting. The linear regression coefficient β represented development rates at different ages. The selected curve regression models were applied to the validation set, and the reliability of the model was evaluated with accuracy. Results: Intra-observer and inter-observer histogram measurement parameters were generally in good consistency (ICC>0.800, all P<0.001). Histogram parameters ADC 10th-65th, T1WI 55th-80th and T2WI 10th-45th were highly correlated with age (∣r∣≥0.700, 0.600 and 0.600 respectively; all P<0.001). ADC 30th and T2WI 10th had the greatest goodness of fit (R²=0.871, 0.873; both P<0.001). Map of brain development trends showed that ADC 30th and T2WI 10th decreased with age. ADC 30th changed rapidly before the age of 2 years, most significantly within 6 months, and the rate of decrease slowed down after 2 years old. T2WI 10th decreased rapidly within 1 year, and moderately after 1 year old. The curve regression models of ADC 30th and T2WI 10th had higher accuracy in validation set [93% (56/60) and 95% (57/60), respectively]. Conclusion: Histogram parameters can quantify brain developmental trajectories at slice of anterior and posterior horns of lateral ventricles on conventional MRI in normal children aged 0-5 years, and obtain the brain development curves reflecting this slice of this age group.

Diagnosis of Laryngopharyngeal Reflux Disease Based on Gray and Texture Changes of Laryngoscopic Images

ObjectiveThis study aimed to compare the changing trends of gray and texture values of laryngoscopic images in patients with laryngopharyngeal reflux (LPR) and non-LPR. MethodsA total of 3428 laryngoscopic images were selected and divided into two groups, non-LPR and LPR groups based on the reflux symptom index. Gray histogram and gray-level co-occurrence matrix (GLCM) were used to quantify gray and texture features, and the model was trained based on these features. The total laryngoscopic images dataset was proportionally split into two parts including the training set and the test set according to the ratio of 7:3. Four different machine learning algorithms, including decision tree, naive Bayes, linear regression, and K-nearest neighbors, were applied to classify non-LPR or LPR laryngoscopic images. ResultsThe results showed that different classification algorithms are used to classify laryngoscopic image dataset and promising classification accuracy are obtained. Specifically, the accuracy of K-nearest neighbors was 83.38% for the gray histogram-only classification, that of linear regression was 88.63% for the GLCM-only classification, and that of the decision tree was 98.01% for the combined gray histogram and GLCM analysis. ConclusionGray histogram and GLCM analysis of the laryngoscopic images may be used as auxiliary tools to detect laryngopharyngeal mucosal damage in patients with LPR. Measurement of gray and texture feature values is an objective and convenient method, which may serve as a reference baseline for clinicians and have potential clinical usefulness.

Image encryption algorithm based on multi-bit superposition and optical chaos

Aiming at the problem that the leakage of single-layer key encryption may lead to the theft of image information, we propose an image encryption algorithm based on multi-bit superposition and optical chaos. The generated optical chaotic sequence is used to encrypt the encrypted image together with the user input key. In the scrambling stage, the 3D-cat map is used to encrypt the bit plane, and the multi-bit superposition method is used to encrypt the key space between the bit planes again by using the sub-block internal and external encryption methods. In the diffusion stage, the Logistic-tent map is used to diffuse the scrambling image to generate the ciphertext image, and the optical chaotic waveform is used as the carrier to mask the ciphertext image information in the transmission process. At the recipient, the ciphertext image information is obtained through the synchronized optical chaotic waveform, and the image is decrypted by using the synchronized optical chaotic sequence and the key transmitted through the secure channel. If only one of the two cannot decrypt the image, the security of image transmission is improved. The simulation results show that the correlation of adjacent pixels of the image encrypted by the algorithm is close to zero, the gray histogram is evenly distributed, the pixel change rate, the normalized average change intensity and the block average change intensity are close to the ideal value, and the sensitivity of the plaintext is further enhanced, which can effectively resist statistical attacks, differential attacks and exhaustive attacks.

Multifeature Fusion Classification Method for Adaptive Endoscopic Ultrasonography Tumor Image.

Endoscopic ultrasonography (EUS) has been found to be of great advantage in the diagnosis of digestive tract submucosal tumors. However, EUS-based diagnosis is limited by variability in subjective interpretation on the part of doctors. Tumor classification of ultrasound images with the computer-aided diagnosis system can significantly improve the diagnostic efficiency and accuracy of doctors. In this study, we proposed a multifeature fusion classification method for adaptive EUS tumor images. First, for different ultrasound tumor images, we selected the region of interest based on prior information to facilitate the estimation in the subsequent works. Second, we proposed a method based on image gray histogram feature extraction with principal component analysis dimensionality reduction, which learns the gray distribution of different tumor images effectively. Third, we fused the reduced grayscale features with the improved local binary pattern features and gray-level co-occurrence matrix features, and then used the multiclassification support vector machine. Finally, in the experiment, we selected the 431 ultrasound images of 109 patients in the hospital and compared the experimental effects of different features and different classifiers. The results revealed that the proposed method performed best, with the highest accuracy of 96.18% and an area under the curve of 99%. It is evident that the method proposed in this study can efficiently contribute to the classification of EUS tumor images.

Narrow Weld Joint Recognition Method Based on Laser Profile Sensor

Intelligent manufacturing technology has recently experienced rapid development, where robot welding systems are an essential component. A laser profile sensor is commonly utilized in intelligent robot welding systems. However, when the laser stripe is projected onto a narrow weld joint, the deformation of the laser stripe is not sufficiently apparent, and the traditional weld joint recognition methods based on the laser profile sensors cannot detect the narrow weld joint position. Meanwhile, the strong arc and spatter noise during welding and the expansion of weld joint width caused by welding thermal expansion are likely to interfere with weld joint recognition. In addition, many common weld seam recognition methods can only recognize certain weld joints and have limited flexibility and robustness for other types of weld joints. This study proposes a wide range of weld joint recognition algorithms based on the laser profile sensor to overcome these challenges. The gray value histogram analysis method, the adaptive threshold method, the internal propulsion center and boundary extraction (IPCBE) method, the coordinate analysis method, and the stripe end center detection method proposed in this study are used primarily in the algorithm. The algorithm solves the problem of identifying narrow weld joints and allows for the identification of larger conventional weld joints. Furthermore, the algorithm has good a anti-spatter and anti-arc interference ability and a fast speed, allowing it to meet the demand for real-time welding identification.

Enhanced Feature Fusion Segmentation for Tumor Detection Using Intelligent Techniques

In the field of diagnosis of medical images the challenge lies in tracking and identifying the defective cells and the extent of the defective region within the complex structure of a brain cavity. Locating the defective cells precisely during the diagnosis phase helps to fight the greatest exterminator of mankind. Early detection of these defective cells requires an accurate computer-aided diagnostic system (CAD) that supports early treatment and promotes survival rates of patients. An earlier version of CAD systems relies greatly on the expertise of radiologist and it consumed more time to identify the defective region. The manuscript takes the efficacy of coalescing features like intensity, shape, and texture of the magnetic resonance image (MRI). In the Enhanced Feature Fusion Segmentation based classification method (EEFS) the image is enhanced and segmented to extract the prominent features. To bring out the desired effect the EEFS method uses Enhanced Local Binary Pattern (EnLBP), Partisan Gray Level Co-occurrence Matrix Histogram of Oriented Gradients (PGLCMHOG), and iGrab cut method to segment image. These prominent features along with deep features are coalesced to provide a single-dimensional feature vector that is effectively used for prediction. The coalesced vector is used with the existing classifiers to compare the results of these classifiers with that of the generated vector. The generated vector provides promising results with commendably less computatio nal time for pre-processing and classification of MR medical images.

Brightness and Contrast Enhancement Method for Color Images Via Pairing Adaptive Gamma Correction and Histogram Equalization

For enhanced adaptability to poor light enhancement whilst achieving high image contrast, a new method for color image correction based on the advantages of non-linear function in grey transformation and histogram equalization techniques is proposed in this work. Firstly, the original red, green and blue (RGB) image is converted into the HSV color space, and the V channel is used for enhancement. An adaptive gamma generator is proposed to adaptively calculate gamma parameters in accordance with dark, medium, or bright image conditions. The computed gamma parameters are used to propose a cumulative distribution function that produces an optimized curve for illumination values. Next, a second modified equalization is performed to evenly correct the offset of the illumination curve values on the basis of the equal probability of the available values only. Finally, the processed V channel replaces the original V channel, and the new HSV model returns to the RGB color space. Experiments show that the proposed method can significantly improve the low contrast and poor illumination of the color image whilst preserving the color and details of the original image. Results from benchmark data sets and measurements indicate that the proposed method outperforms other state-of-the-art methods.