Grayscale Features Research Articles

Identification method for micro–nano defects in Si3N4 ceramic bearing rollers

In response to the surface micro–nano defects of small Si3N4 ceramic bearing rollers during use, as well as the poor generalization ability and low accuracy of the object detection model trained on the micro and nano defect dataset, an enhanced recognition algorithm based on deep convolutional generative adversarial networks is proposed. Due to the limited size of the dataset, the DCGAN model is reconstructed to effectively expand the micro–nano defect dataset. In addition, noise generalization is applied to stabilize DCGAN model training, creating a low-dimensional manifold distribution to ensure significant overlap between the data and the original dataset, and activating Jensen–Shannon (JS) divergence for stable training. To verify the effectiveness of the enhanced dataset, synthetic micro–nano defects are used to improve the YOLO-v4-tiny object detection model. By comparing t-distributed stochastic neighbor embedding (t-SNE) and feature vectors, it can be found that the images generated by the optimized DCGAN have higher grayscale feature diversity and better visual consistency. After generations of enhancements, the micro–nano defect detection speed has reached 226FPS, and the accuracy has reached 97.41%.

Joint Luminance-Saliency Prior and Attention for Underwater Image Quality Assessment

Underwater images, as a crucial medium for storing ocean information in underwater sensors, play a vital role in various underwater tasks. However, they are prone to distortion due to the imaging environment, which leads to a decline in visual quality, which is an urgent issue for various marine vision systems to address. Therefore, it is necessary to develop underwater image enhancement (UIE) and corresponding quality assessment methods. At present, most underwater image quality assessment (UIQA) methods primarily rely on extracting handcrafted features that characterize degradation attributes, which struggle to measure complex mixed distortions and often exhibit discrepancies with human visual perception in practical applications. Furthermore, current UIQA methods lack the consideration of the perception perspective of enhanced effects. To this end, this paper employs luminance and saliency priors as critical visual information for the first time to measure the enhancement effect of global and local quality achieved by the UIE algorithms, named JLSAU. The proposed JLSAU is built upon an overall pyramid-structured backbone, supplemented by the Luminance Feature Extraction Module (LFEM) and Saliency Weight Learning Module (SWLM), which aim at obtaining perception features with luminance and saliency priors at multiple scales. The supplement of luminance priors aims to perceive visually sensitive global distortion of luminance, including histogram statistical features and grayscale features with positional information. The supplement of saliency priors aims to perceive visual information that reflects local quality variation both in spatial and channel domains. Finally, to effectively model the relationship among different levels of visual information contained in the multi-scale features, the Attention Feature Fusion Module (AFFM) is proposed. Experimental results on the public UIQE and UWIQA datasets demonstrate that the proposed JLSAU outperforms existing state-of-the-art UIQA methods.

Study on lung CT image segmentation algorithm based on threshold-gradient combination and improved convex hull method

Lung images often have the characteristics of strong noise, uneven grayscale distribution, and complex pathological structures, which makes lung image segmentation a challenging task. To solve this problems, this paper proposes an initial lung mask extraction algorithm that combines threshold and gradient. The gradient used in the algorithm is obtained by the time series feature extraction method based on differential memory (TFDM), which is obtained by the grayscale threshold and image grayscale features. At the same time, we also proposed a lung contour repair algorithm based on the improved convex hull method to solve the contour loss caused by solid nodules and other lesions. Experimental results show that on the COVID-19 CT segmentation dataset, the advanced lung segmentation algorithm proposed in this article achieves better segmentation results and greatly improves the consistency and accuracy of lung segmentation. Our method can obtain more lung information, resulting in ideal segmentation effects with improved accuracy and robustness.

A thermal infrared target tracking based on multi-feature fusion and adaptive model update

Thermal infrared target tracking has attracted increasing attention from researchers due to its unique imaging advantages. In response to common issues encountered in correlation filtering algorithms during the tracking process, such as background clutter, distractors, and occlusion, a framework for improving infrared target tracking is proposed. This paper proposes to extend multi-channel stepped grayscale features and optimize the feature set, fully leveraging the complementarity between multiple features and enhancing their ability to represent tracking targets. The tracking results are evaluated using the peak energy of the position weighted average, enabling an adaptive model update that improves the algorithm's ability to resist occlusion. The proposed algorithm is evaluated on the LSOTB-TIR and PTB-TIR infrared tracking datasets in terms of precision, success rate, and processing speed. In addition, the algorithm is also experimented on a self-collected dataset. The experimental results indicate that the proposed optimization framework can be integrated into correlation filtering trackers with a certain level of applicability. The improved algorithm demonstrates effective handling of various complex infrared scenarios and interferences, achieving high-precision and real-time tracking of infrared targets.

Texture feature similarity-based roughness intelligent evaluation: a case study applied to milled surfaces

Surface roughness is of great significance in maintaining mechanical performance and improving the reliability of the equipment. However, fast surface roughness evaluations that are sufficiently stable and efficient for engineering in situ use have not yet been realized. To address this issue, an image-driven roughness intelligent method is proposed in this research. By evaluating the texture similarity intelligently between the testing image and the reference image, the surface roughness of the testing image can be acquired. Firstly, with a proposed adaptive texture extraction method, the texture feature of an image can be extracted even under a complex background. Secondly, by establishing the graph structure of the texture grayscale features, the similarity between different images is evaluated. Finally, by establishing a sparrow-optimized support vector machine regression method, the mapping relationship between the similarity and the surface roughness can be acquired. The experimental results indicate that the proposed method for intelligent evaluation of roughness has superior prediction performance (the average relative prediction error of Ra and Rz are 8.8156% and 8.0571%, respectively). Therefore, this work provides a useful tool for non-contact detection of workpiece surface roughness.

Automatic Detection of Cast Billet Dendrite Based on Improved Hough Transform

Primary dendrite information is one of the most important metrics to measure the quality of continuous cast slabs. The contrast of low magnification images is very low under the influence of illumination and sampling devices, so the traditional dendrite detection method has the problem of missed detections. We propose an automatic dendrite detection method based on an improved Hough transform, which effectively improves the accuracy and efficiency of primary dendrite detection. By using the local grayscale features of the image, a genetic algorithm-based local contrast enhancement algorithm is proposed. Compared with the traditional contrast enhancement algorithm, it can retain all the information of the dendrites. Combined with the image binarization method based on Hessian matrix, we can obtain more detailed information about the dendrites. According to the continuity and solidification characteristics of dendrites, the Hough transform is improved to extract dendrite information, which effectively reduces the computational cost of the Hough transform. The experimental results show that the method of this paper has versatility, and the error is four pixels compared with the manual method, which can provide a reliable basis for the subsequent judgement of the quality of cast billets.

A Space Infrared Dim Target Recognition Algorithm Based on Improved DS Theory and Multi-Dimensional Feature Decision Level Fusion Ensemble Classifier

Space infrared dim target recognition is an important applications of space situational awareness (SSA). Due to the weak observability and lack of geometric texture of the target, it may be unreliable to rely only on grayscale features for recognition. In this paper, an intelligent information decision-level fusion method for target recognition which takes full advantage of the ensemble classifier and Dempster–Shafer (DS) theory is proposed. To deal with the problem that DS produces counterintuitive results when evidence conflicts, a contraction–expansion function is introduced to modify the body of evidence to mitigate conflicts between pieces of evidence. In this method, preprocessing and feature extraction are first performed on the multi-frame dual-band infrared images to obtain the features of the target, which include long-wave radiant intensity, medium–long-wave radiant intensity, temperature, emissivity–area product, micromotion period, and velocity. Then, the radiation intensities are fed to the random convolutional kernel transform (ROCKET) architecture for recognition. For the micromotion period feature, a support vector machine (SVM) classifier is used, and the remaining categories of the features are input into the long short-term memory network (LSTM) for recognition, respectively. The posterior probabilities corresponding to each category, which are the result outputs of each classifier, are constructed using the basic probability assignment (BPA) function of the DS. Finally, the discrimination of the space target category is implemented according to improved DS fusion rules and decision rules. Continuous multi-frame infrared images of six flight scenes are used to evaluate the effectiveness of the proposed method. The experimental results indicate that the recognition accuracy of the proposed method in this paper can reach 93% under the strong noise level (signal-to-noise ratio is 5). Its performance outperforms single-feature recognition and other benchmark algorithms based on DS theory, which demonstrates that the proposed method can effectively enhance the recognition accuracy of space infrared dim targets.

Building classification extraction from remote sensing images combining hyperpixel and maximum interclass variance

ABSTRACT In recent years, semantic segmentation algorithms based on deep learning have been widely used in building extraction, which requires large sample data and does not consider the geometric features of the building, and the effect of the extraction is greatly affected by the data scene, while the traditional methods are difficult to extract the remote sensing buildings accurately because they only consider their greyscale features when extracting them. To solve this problem, we propose a method for building classification extraction from remote sensing images that combine over-pixel and maximum interclass variance. The method combines superpixel and maximum interclass variance (OTSU). First, a number of superpixel subregions with different shapes and sizes are generated based on the watershed transform. Then, the superpixels of buildings are merged using the spectral features of buildings, so the first extraction of buildings is achieved by this method.Then, the noise is suppressed with median filtering. Finally, the post-extraction of buildings is performed according to the OTSU algorithm. In this paper, seven images of buildings located in different landscapes were selected. The experimental results show that the algorithm is more advantageous than the classical algorithm and the deep learning algorithm..

Precise positioning method of deformed workpiece by fusing edge and grayscale features

Precise positioning method of deformed workpiece by fusing edge and grayscale features

Detection of skin defects on mangoes based on hyperspectral imaging combined with band ratio and improved Otsu method

Skin defects are one of the major concerns in post-harvest grading and processing of mangoes. Skin defects can cause mangoes to be easily damaged during transportation and storage, and also raise the risk of infection for other mangoes in the batch. To solve the problems of inefficiency and time-consuming of traditional detection methods of skin defects on mangoes, the hyperspectral imaging combined with band ratio and improved Otsu method for detecting on mangoes was proposed in this study. Firstly, Principal Component Analysis was used to the three regions of Vis-NIR (450–1000 nm), Vis (450–780 nm), and NIR (780–1000 nm). It was found that the PC2 image of the Vis-NIR region and the PC1 image of the Vis region were more effective in distinguishing defect areas. Next, based on the weight coefficient curves derived from the selected PC images, four feature wavelengths (642 nm, 702 nm, 744 nm and 942 nm) were determined. Additionally, the PC images and band ratio images were obtained from these feature wavelength images. The band ratio Q744/942 image was determined to be the most suitable for detecting skin defects on mangoes. Finally, the segmentation results of global thresholding and the improved Otsu method were compared, and it was found that the improved Otsu method had better segmentation results. Mis-segmentation due to the stem-end region and the defective region had the same gray scale features. The band ratio Q744/702 image based on the linear stretch transformation could be used to effectively distinguish the stem-end region and the defect region. The final overall accuracy was 96.67 % with no false positives. The results indicate that the proposed detection method in this study has the potential for online detection of skin defects on mangoes.

Multi-sensor fusion rolling bearing intelligent fault diagnosis based on VMD and ultra-lightweight GoogLeNet in industrial environments

As artificial intelligence and sensor technology develop rapidly, intelligent fault diagnosis methods based on deep learning are widely used in industrial production. However, in practical industrial applications, the complex noise environment affects the performance of the diagnostic model, and the huge model parameters cannot meet the requirements of low cost and high performance in industrial production. To address the above problems, this paper proposes a lightweight intelligent fault diagnosis model using multi-sensor data fusion that not only meets the lightweight requirements of "small, light, and fast", but also realizes high accuracy diagnosis in noisy environments. Firstly, the vibration signals from different sensors of rolling bearings are processed using the variational mode decomposition (VMD) to design a unique method of constructing grayscale feature maps based on each intrinsic modal function (IMF) component. Then, the ultra-lightweight GoogLeNet model (UL-GoogLeNet) is constructed to adjust the traditional GoogLeNet structure, while the Ultra-lightweight subspace attention module (ULSAM) is introduced to reduce the model parameters and enhance the feature extraction capability. UL-GoogLeNet is trained and tested by dividing the grayscale feature maps into training and testing sets to realize the intelligent recognition of different fault types in rolling bearings. Experiments are conducted on two datasets and compared with multiple methods, and the final experimental results prove the effectiveness and superiority of the proposed method in this paper.

Automated Image Analysis of Transmission Electron Micrographs: Nanoscale Evaluation of Radiation-Induced DNA Damage in the Context of Chromatin.

Heavy ion irradiation (IR) with high-linear energy transfer (LET) is characterized by a unique depth dose distribution and increased biological effectiveness. Following high-LET IR, localized energy deposition along the particle trajectories induces clustered DNA lesions, leading to low electron density domains (LEDDs). To investigate the spatiotemporal dynamics of DNA repair and chromatin remodeling, we established the automated image analysis of transmission electron micrographs. Human fibroblasts were irradiated with high-LET carbon ions or low-LET photons. At 0.1 h, 0.5 h, 5 h, and 24 h post-IR, nanoparticle-labeled repair factors (53BP1, pKu70, pKu80, DNA-PKcs) were visualized using transmission electron microscopy in interphase nuclei to monitor the formation and repair of DNA damage in the chromatin ultrastructure. Using AI-based software tools, advanced image analysis techniques were established to assess the DNA damage pattern following low-LET versus high-LET IR. Low-LET IR induced single DNA lesions throughout the nucleus, and most DNA double-strand breaks (DSBs) were efficiently rejoined with no visible chromatin decondensation. High-LET IR induced clustered DNA damage concentrated along the particle trajectories, resulting in circumscribed LEDDs. Automated image analysis was used to determine the exact number of differently sized nanoparticles, their distance from one another, and their precise location within the micrographs (based on size, shape, and density). Chromatin densities were determined from grayscale features, and nanoparticles were automatically assigned to euchromatin or heterochromatin. High-LET IR-induced LEDDs were delineated using automated segmentation, and the spatial distribution of nanoparticles in relation to segmented LEDDs was determined. The results of our image analysis suggest that high-LET IR induces chromatin relaxation along particle trajectories, enabling the critical repair of successive DNA damage. Following exposure to different radiation qualities, automated image analysis of nanoparticle-labeled DNA repair proteins in the chromatin ultrastructure enables precise characterization of specific DNA damage patterns.

Dual-Core Adaptive NLM Image Denoising Algorithm Based on Variable-Size Window and Neighborhood Multifeatures

To solve the problem that the similarity calculation between neighbors was easily disturbed by noise in the traditional nonlocal mean (NLM) denoising algorithm, a dual-core NLM denoising algorithm based on neighborhood multifeatures and variable-size search window was proposed. The algorithm first proposed to use the eigenvalues of the structure tensor to classify the region where the target pixel points were located and used different sizes of the search window to search for similar neighborhoods for target pixel points in different categories of the region, thus effectively avoiding the problem of oversmoothing or inadequate denoising of the image caused by the use of the global size. Then, the gradient features between image blocks were defined and combined with grayscale features and spatial features to measure the similarity of neighborhood blocks, which solved the problem of noise interfering with the search of similar blocks. Then, an adaptive algorithm with Gaussian–Sinusoidal dual kernel function and quantitative estimation of the optimal values of the filtering parameters was designed to calculate the neighborhood similarity weights to improve the accuracy of image denoising. Finally, the similarity weights were used to weight and average the search neighborhood of the target pixel points to achieve the denoising of the target pixel points. To test the effectiveness of the algorithm, denoising tests were performed using multiple standard grayscale images with different levels of Gaussian white noise added and compared with several advanced denoising algorithms. The experimental results showed that the algorithm was effective. The algorithm improved the image peak signal-to-noise ratio by more than 56.54% on average when Gaussian white noise was removed, and the structural similarity reached more than 0.701 on average. Compared with the traditional NLM algorithm and other improved algorithms, the algorithm proposed in this paper had strong denoising ability, better protection of edges and texture details, and the quality of the image was greatly improved, which had a good application prospect.

Deep features fusion for KCF-based moving object tracking

Real-time object tracking and occlusion handling are critical research areas in computer vision and machine learning. Developing an efficient and accurate object-tracking method that can operate in real-time while handling occlusion is essential for various applications, including surveillance, autonomous driving, and robotics. However, relying solely on a single hand-crafted feature results in less robust tracking. As a hand-crafted feature extraction technique, HOG effectively detects edges and contours, which is essential in localizing objects in images. However, it does not capture fine details in object appearance and is sensitive to changes in lighting conditions. On the other hand, the grayscale feature has computational efficiency and robustness to changes in lighting conditions. The deep feature can extract features that express the image in more detail and discriminate between different objects. By fusing different features, the tracking method can overcome the limitations of individual features and capture a complete representation of the object. The deep features can be generated with transfer learning networks. However, selecting the right network is difficult, even in real-time applications. This study integrated the deep feature architecture and hand-crafted features HOG and grayscale in the KCF method to solve this problem. The object images were obtained through at least three convolution blocks of transfer learning architecture, such as Xception, DenseNet, VGG16, and MobileNet. Once the deep feature was extracted, the HOG and grayscale features were computed and combined into a single stack. In the KCF method, the stacked features acquired the actual object location by conveying a maximum response. The result shows that this proposed method, especially in the combination of Xception, grayscale, and HOG features, can be implemented in real-time applications with a small center location error.

Diagnostic Accuracy of Ultrasound to Differentiate Neoplastic and Non-Neoplastic causes of Cervical Lymphadenopathy taking Histopathology as the Gold Standard

Objective: To evaluate the efficacy of high-resolution ultrasound and colour Doppler in differentiating neoplastic and nonneoplastic causes of cervical lymphadenopathy compared to histopathological diagnosis.
 Study Design: Cross-Sectional study.
 Place and Duration of Study: Pakistan Institute of Medical Sciences, Islamabad Pakistan, from Jan to Jun 2019.
 Methodology: The study included 110 patients with palpable cervical lymph nodes undergoing neck ultrasound and Fine needle aspiration cytology/Biopsy. Certain important sonological features were considered to categorize them into nonneoplastic and neoplastic groups. Colour Doppler imaging was employed along with grey-scale imaging. The histopathology results were compared with sonographic findings to determine the diagnostic accuracy of ultrasound in differentiating neoplastic from non-neoplastic causes of enlarged cervical lymph nodes.
 Results: Our study revealed that High-resolution sonography has 94.4% sensitivity and 88.8% specificity, differentiating between neoplastic and non-neoplastic causes of cervical lymphadenopathy. At the same time, the overall accuracy of ultrasound is 90.9%. The most consistent grey-scale feature in the non-neoplastic nodal group was preserved central fatty hilum, while its loss was significantly associated with neoplastic etiologies.Conclusion: Due to high sensitivity and negative predictive value, high-resolution sonography can be deployed as a first-line investigating tool for enlarged lymph nodes, and invasive procedures like Fine needle aspiration cytology (FNAC) can be abandoned in non-neoplastic lymphadenopathies.

Hashimoto Thyroiditis - A Comprehensive Review

Hashimoto thyroiditis (HT) is an inflammatory disorder that often results in hypothyroidism. It has several global implications affecting different regions worldwide. Risk factors for acquiring HT include diet, inheritance, sex, epigenetics, and comorbidities. HT is a complex autoimmune illness characterized by an attack on the thyroid gland by the immune system. At the cellular level, genetic predisposition, environmental triggers, and the loss of immunological tolerance to thyroid antigens all play significant roles in the disease's genesis and progression. There are several mechanisms by which HT may develop, but the typical progression is autoimmune in origin. Many patients do not initially present with symptoms, but later develop symptoms of hypothyroidism. These symptoms include constipation, fatigue, dry skin, weight gain, cold intolerance, decreased energy, memory loss, muscle cramps, hair loss, and irregular menses. Patients with HT usually present with a firm, nontender neck goiter on a physical exam. To distinguish HT from other thyroid pathologies, patient serum should be collected to check for thyroid-specific auto-antibodies against thyroglobulin, thyroid peroxidase, thyroid stimulating hormone. Imaging studies such as ultrasonography with computer-aided techniques using gray-scale features are also diagnostic tools in differentiating between a healthy thyroid and HT. While the most common intervention of HT is synthetic hormone administration with levothyroxine sodium (L-T4), other alternatives or additional treatments include glucocorticoid use, diet alterations, selenium supplementation, vitamin D supplementation, and in more extreme cases, thyroidectomy. While research continues discovering new interventions, each treatment plan is highly variable based on underlying causes and presentations. This comprehensive review hopes to provide an up-to-date compact analysis of literature pertinent to the epidemiology, etiology, risk factors, genetics, pathophysiology, classifications, clinical presentation, diagnosis, and treatments of HT.

Infrared maritime target detection based on edge dilation segmentation and multiscale local saliency of image details

Infrared maritime target detection is a key technology in the field of maritime search and rescue, which usually requires high detection accuracy. It is challenging to detect dark and weak targets and targets of different sizes. Some methods utilizing grayscale features unable to detect dark targets owing to the inconsideration of the target whose grayscale is lower than its local background. To solve this problem, the medium and high-frequency information in the image is extracted and used as the basis for feature extraction. Besides, although methods based on local contrast can solve the problem of missing detection caused by weak targets with obscure features, the local contrast calculation may be inaccurate and the targets may be missed when the size of the sliding window and target are unmatched. To solve this problem, an edge dilation segmentation method is proposed to obtain complete suspected targets. Then each suspected target is taken as the central block of the local area to ensure that both weak targets and targets of different sizes can be detected. In addition, some wave clutter is prone to cause false alarms due to its characteristics similar to the target. To solve this problem, the multiscale local backgrounds are constructed with certain proportions of the size of the suspected target, and the local saliency of the suspected target is calculated to separate the target from the clutters. Compared with the ten leading methods, the proposed method shows outstanding results, with relatively higher detection accuracy.

Color Saturation: Upper and Lower Percentage Histogram Manipulation

There are various color correction techniques that can be applied to digital photographs to account for environmental lighting variations. This manuscript contains a proposed method for such color correction. The method involves saturating an image by a specified percentage of its pixels via upper and lower percentage histogram manipulation using the image’s RGB histograms. Variations of this new technique, the white balance (WB) correction method, and a multivariable fit are used to test its performance against common color correction techniques. The findings demonstrate that the upper and lower percentage histogram manipulation method is not only more applicable to photos because it doesn’t require calibration regions to be sampled but it is also more consistent in its correction of photos when there are substantial gray scale features (e.g. a black and white grid or text). Our motivation for testing these techniques is to find the most robust color correction technique that is broadly applicable (not requiring a color checker chart) and is consistent across different lighting. KEYWORDS: Color Correction; Histogram Manipulation; Saturation; White Balance; Scientific Image Analysis; Color Comparisons; Euclidean Distance; Standard Deviation; Color Difference

Valid measurement region segmentation method for the interferogram based on local fringe distribution features

Oblique laser interferometry is an effective method to measure the form deviation of gear tooth flank. In the measurement, segmenting the valid measurement region (VMR) of the tooth flank from the captured interference fringe patterns (IFPs) is a crucial step that affects the measurement accuracy. To address the problem that current segmentation algorithms are susceptible to multiple forms of noise, making it difficult to guarantee their segmentation accuracy, this paper proposes a segmentation method that introduces the simulation tooth image (STI) as a template of the active shape model (ASM) to improve the segmentation accuracy. Firstly, an STI with a stable and noiseless fringe grayscale distribution was used to build the dataset and train, in order to obtain the initial contour of the tooth flank VMR. Next, the local grayscale features of the STI fringe were used to build a grayscale model of the initial contour, and the transformation parameters were adaptively calculated based on their a priori shape information. The trained segmentation model is searched in the IFPs to segment the tooth flank VMR. Finally, the proposed method was verified by comparing with segmentation methods based on grayscale and phase-shifting information. Moreover, this paper proves that the proposed method can be applied to the VMR recognition of IFPs of complex precision surfaces.

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.