Histogram Equalization Research Articles

LTPLN: Automatic pavement distress detection.

Automatic pavement disease detection aims to address the inefficiency in practical detection. However, traditional methods heavily rely on low-level image analysis, handcrafted features, and classical classifiers, leading to limited effectiveness and poor generalization in complex scenarios. Although significant progress has been made with deep learning methods, challenges persist in handling high-resolution images and diverse disease types. Therefore, this paper proposes a novel approach based on the lightweight Transformer Patch Labeling Network (LTPLN) to enhance the efficiency of automatic pavement disease detection and overcome the limitations of existing methods. Firstly, the input images undergo histogram equalization preprocessing to enhance image quality. Subsequently, the images are evenly partitioned into small patch blocks, serving as inputs to the enhanced Transformer model. This enhancement strategy involves integrating feature map labels at each layer of the model to reduce computational complexity and enhance model lightweightness. Furthermore, a depthwise separable convolution module is introduced into the Transformer architecture to introduce convolutional bias and reduce the model's dependence on large amounts of data. Finally, an iterative training process utilizing the label distillation strategy based on expectation maximization is employed to update the labels of patch blocks and roughly locate the positions of pavement diseases under weak supervision. Experimental results demonstrate that compared to the baseline model, the proposed enhanced model achieves a reduction of 2.5G Flops computational complexity and a 16% speed improvement on a private pavement disease dataset, with only a 1.2 percentage point decrease in AUC accuracy. Moreover, compared to other mainstream image classification models, this model exhibits more balanced performance on a public dataset, with improved accuracy and speed that better align with the practical requirements of pavement inspection. These findings highlight the significant performance advantages of the LTPLN model in automatic pavement disease detection tasks, making it more efficiently applicable in real-world scenarios.

Analysis of Hybrid Feature Optimization Techniques Based on the Classification Accuracy of Brain Tumor Regions Using Machine Learning and Further Evaluation Based on the Institute Test Data.

The goal of this study was to get optimal brain tumor features from magnetic resonance imaging (MRI) images and classify them based on the three groups of the tumor region: Peritumoral edema, enhancing-core, and necrotic tumor core, using machine learning classification models. This study's dataset was obtained from the multimodal brain tumor segmentation challenge. A total of 599 brain MRI studies were employed, all in neuroimaging informatics technology initiative format. The dataset was divided into training, validation, and testing subsets online test dataset (OTD). The dataset includes four types of MRI series, which were combined together and processed for intensity normalization using contrast limited adaptive histogram equalization methodology. To extract radiomics features, a python-based library called pyRadiomics was employed. Particle-swarm optimization (PSO) with varying inertia weights was used for feature optimization. Inertia weight with a linearly decreasing strategy (W1), inertia weight with a nonlinear coefficient decreasing strategy (W2), and inertia weight with a logarithmic strategy (W3) were different strategies used to vary the inertia weight for feature optimization in PSO. These selected features were further optimized using the principal component analysis (PCA) method to further reducing the dimensionality and removing the noise and improve the performance and efficiency of subsequent algorithms. Support vector machine (SVM), light gradient boosting (LGB), and extreme gradient boosting (XGB) machine learning classification algorithms were utilized for the classification of images into different tumor regions using optimized features. The proposed method was also tested on institute test data (ITD) for a total of 30 patient images. For OTD test dataset, the classification accuracy of SVM was 0.989, for the LGB model (LGBM) was 0.992, and for the XGB model (XGBM) was 0.994, using the varying inertia weight-PSO optimization method and the classification accuracy of SVM was 0.996 for the LGBM was 0.998, and for the XGBM was 0.994, using PSO and PCA-a hybrid optimization technique. For ITD test dataset, the classification accuracy of SVM was 0.994 for the LGBM was 0.993, and for the XGBM was 0.997, using the hybrid optimization technique. The results suggest that the proposed method can be used to classify a brain tumor as used in this study to classify the tumor region into three groups: Peritumoral edema, enhancing-core, and necrotic tumor core. This was done by extracting the different features of the tumor, such as its shape, grey level, gray-level co-occurrence matrix, etc., and then choosing the best features using hybrid optimal feature selection techniques. This was done without much human expertise and in much less time than it would take a person.

A convolution neural network for rapid and accurate staging of breast cancer based on mammography

IntroductionBreast cancer (BC) has been one of the main reasons for women's deaths in the recent decade. This study hypothesizes that the deep features resulting from mammography staging can be used to determine tumor staging and lymph nodes of the sentinel lymph node (SLN) before surgery in BC patients. MethodsA retrospective study of female BC patients being treated. Pathological variables were collected from medical records, including age, tumor location, staging based on the American Joint Committee on Cancer (AJCC), pathological type, human epidermal growth factor receptor 2 (HER2) status, Progesterone Receptor (PR) status, and Estrogen Receptor (ER) status. The contrast enhancement technique with Contrast-Limited Adaptive Histogram Equalization (CLAHE) was applied to the studied data using MATLAB software. The images were first changed from color to gray in the preprocessing process, and then the images were changed from gray to color again. The regions of interest (ROI) of the primary tumor were isolated from other areas of breast tissue by two expert radiologists. Therefore, a proposed convolution neural network (CNN) model was applied. ResultsIn this study, 390 patients' information was used to analyze the data. In total, out of 390 patients, 300 had metastatic SLN involvement, and 390 had a tumor size greater than 1 mm. Performance evaluation of the proposed CNN staging was AUC 0.919 (95 % CI: 0.852,0.971) for the training group and AUC 0.877 (95 % CI: 0.805,0.949) for the validation group. ConclusionsThis study proposes a deep learning model based on CNN based on mammographic images, which has a suitable function for determining tumor staging and SLN metastasis.

Early Breast Cancer Detection Based on Locally Available Mammography Data Using Convolutional Neural Network

In this work, convolutional neural network model was developed to read mammography image scans to predict malignancy. Firstly, mammography image data was sourced locally from University of Abuja Teaching hospital, Gwagwalada, Nigeria and then combined with publicly available mammography image dataset from The Mammographic Image Analysis Society (MIAS) database. The data obtained were then preprocessed using Contrast Limited Adaptive Histogram Equalization (CLAHE), Image Denoising, Padding and Formatting. Transfer learning was implemented by re-architecting pre-trained VGG-16, VGG-19, MobileNet-V2 and DenseNet-121 models to have an output layer with two neurons and softmax activation function, each signifying the degree to which calcifications in the mammography image is benign or malignant. The model was then trained on the preprocessed data and evaluated, the following metrics were achieved: VGG-16 and VGG-19 based models achieved an accuracy of 86% each, precision of 87% and 88% respectively and recall of 92% and 93% respectively. MobileNet-V2 has accuracy of 90%, precision and recall of 93% while the DenseNet-121 model achieved an accuracy of 95%, precision of 93% and 100% score in recall. MobileNet-V2 performed best in the computational complexity analysis with 336.34 MFLOPs, followed by DenseNet-121 with 5.69GFLOPs. VGG-16 and VGG-19 have computational complexity of 15.3 GFLOPs and 19.6 GFLOPs respectively.

Future Iris Imaging with Advanced Fuzzified Histogram Equalization

Future Iris Imaging with Advanced Fuzzified Histogram Equalization

Hybrid healthcare unit recommendation system using computational techniques with lung cancer segmentation.

Our research addresses the critical need for accurate segmentation in medical healthcare applications, particularly in lung nodule detection using Computed Tomography (CT). Our investigation focuses on determining the particle composition of lung nodules, a vital aspect of diagnosis and treatment planning. Our model was trained and evaluated using several deep learning classifiers on the LUNA-16 dataset, achieving superior performance in terms of the Probabilistic Rand Index (PRI), Variation of Information (VOI), Region of Interest (ROI), Dice Coecient, and Global Consistency Error (GCE). The evaluation demonstrated a high accuracy of 91.76% for parameter estimation, confirming the effectiveness of the proposed approach. Our investigation focuses on determining the particle composition of lung nodules, a vital aspect of diagnosis and treatment planning. We proposed a novel segmentation model to identify lung disease from CT scans to achieve this. We proposed a learning architecture that combines U-Net with a Two-parameter logistic distribution for accurate image segmentation; this hybrid model is called U-Net++, leveraging Contrast Limited Adaptive Histogram Equalization (CLAHE) on a 5,000 set of CT scan images.

Research on marine flexible biological target detection based on improved YOLOv8 algorithm.

To address the challenge of suboptimal object detection outcomes stemming from the deformability of marine flexible biological entities, this study introduces an algorithm tailored for detecting marine flexible biological targets. Initially, we compiled a dataset comprising marine flexible biological subjects and developed a Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm, supplemented with a boundary detection enhancement module, to refine underwater image quality and accentuate the distinction between the images' foregrounds and backgrounds. This enhancement mitigates the issue of foreground-background similarity encountered in detecting marine flexible biological entities. Moreover, the proposed adaptation incorporates a Deformable Convolutional Network (DCN) network module in lieu of the C2f module within the YOLOv8n algorithm framework, thereby augmenting the model's proficiency in capturing geometric transformations and concentrating on pivotal areas. The Neck network module is enhanced with the RepBi-PAN architecture, bolstering its capability to amalgamate and emphasize essential characteristics of flexible biological targets. To advance the model's feature information processing efficiency, we integrated the SimAM attention mechanism. Finally, to diminish the adverse effects of inferior-quality labels within the dataset, we advocate the use of WIoU (Wise-IoU) as a bounding box loss function, which serves to refine the anchor boxes' quality assessment. Simulation experiments show that, in comparison to the conventional YOLOv8n algorithm, our method markedly elevates the precision of marine flexible biological target detection.

Efficient-VGG16: A Novel Ensemble Method for the Classification of COVID-19 X-ray Images in Contrast to Machine and Transfer Learning

Corona Virus Disease 2019 (COVID-19) is a contagious respiratory disease characterized by its high transmissibility and exponential spread, presenting persistent difficulties. This investigation sought to incorporate machine learning (ML) and transfer learning (TL) and introduced Efficient-VGG16, a novel ensemble approach that integrated the EfficientNet-B0 and VGG16 architectures to classify chest X-ray images as either COVID-19 positive or non-COVID. The COVID-Xray-5k dataset used in the research was split into different training and testing sets (with ratios of 80:20, 75:25, and 70:30), preprocessed, and then used to evaluate the approach’s effectiveness. Throughout the investigation, all procedures operated effectively at the same selected image size, 224*224. Preprocessing included Gaussian blur to remove noise and relics, while Contrast Limited Adaptive Histogram Equalization (CLAHE) adjusted contrast. Among the employed ML classifiers, XgBoost attained the highest accuracy, with F1 scores of 95.78% and 71.56%, respectively. In addition, the research investigated the effectiveness of TL using pre-trained convolutional neural networks (CNNs) such as VGG16, MobileNetV3, ResNet101, Densenet201, and EfficientNet-B0. EfficientNet-B0 achieved the highest levels of accuracy and F1 score, 99.31% and 93.72%, respectively. Furthermore, the proposed Efficient-VGG16 achieved accuracy and an F1 score of 99.46% and 98.41%, respectively, and outperformed TL with EfficientNet-B0 and XgBoost. The investigation demonstrated the effectiveness of the Efficient-VGG16 for accurately classifying COVID-19.

Evaluation of Normalization Algorithms for Breast Mammogram Mass Segmentation

Medical images acquired at different institutions have different data distributions due to varying scanners, imaging protocols, or patient cohorts. Thus, normalizing samples before using them to train the Deep Learning (DL) models is an essential task. Scholars have used various normalization methods to normalize mammograms. However, which normalization method works best on mammograms and if it can help training generalize the DL model has not been analyzed in the literature. This paper presents a comparative analysis of commonly used normalization methods, such as scaling, Contrast Limited Adaptive Histogram Equalization (CLAHE), and Z-score normalization on mammograms for breast mass segmentation tasks. We trained the Attention Unet model on INbreast and the subset of the Cohort of Screen-Aged Women dataset (CSAW-S). We performed cross-dataset analysis on trained models to investigate how normalization methods helped train robust models to handle diverse datasets. Our results suggest that the normalizing method of input data affects the segmentation model’s performance. We achieved the best scores with the Z-score normalization closely followed by CLAHE. However, further investigation suggests that the normalization method’s performance may depend on the variability of mammograms in the dataset. Results of cross-dataset analysis suggest the importance of choosing the normalization method for consistent DL model performance. To our knowledge, this study represents the first systematic analysis of the performance of prevalent normalization techniques on a diverse dataset of mammogram images. The insights gained from our experiments can guide the selection of normalization methods for improved mass segmentation accuracy.

Effectual Augmentation of Glaucoma Prediction in Retinal Fundus Images using Hybrid Level Fusion of Image Pre-Processing Techniques

Glaucoma is a condition where the eyes of human beings are infected due to retinal damage which could result in loss of vision. It generally occurs due to prolonged pressure on the eye and affects the optic nerve if not treated at the earliest stage. However, it is hard for even experts to detect it at the earlier stage. Hence numerous image processing techniques were applied to identify Glaucoma in retinal eyes. The profound purpose of the work is to propose a pre-processing console to remove outliers in the Glaucoma retinal Fundus images using Denoising techniques of pre-processing to enhance the prediction using image pre-processing and computer vision techniques. The model was created with three stages including applying the denoising model using the Median Filtering for Edge Preservation, Contrast Limited Adaptive Histogram Equalization (CLAHE) and optimizing by eliminating irrelevant features using the Black Widow Optimization model and finally evaluating the performance of denoising techniques using accuracy-based predictions. The results showed that after performing a combination of denoising and optimizing techniques, the image quality was enhanced with 97% outperforming the existing models.

Enhanced Breast Cancer Detection Using Modified Particle Swarm Optimization-Based Back Propagation Neural Network

Breast cancer detection faces challenges due to late diagnosis and inaccurate results, leading to improper treatment. Particle Swarm Optimization (PSO), a common optimization technique, often gets trapped in local optima, resulting in high false negatives and computational time. To address this, a study devised a modified PSO-based Back Propagation Neural Network (BPNN) using White Shark Optimization (WSO) for more accurate breast cancer detection. The research collected 1097 mammogram images from two medical centers and categorized them into benign, and malignant groups. Image preprocessing involved techniques like Otsu's method and contrast limited adaptive histogram equalization, with Fuzzy C Means used for segmentation. Region of Interest (ROI) extraction utilized Gabor filter and Local Binary Pattern, followed by weighted average fusion of textural features. WSPSO was then applied for optimal feature selection, and BPNN classified the identified features. MATLAB R2016a implemented the system. Evaluation metrics included accuracy, precision, sensitivity, specificity, False Positive Rate (FPR), and Computation Time (CT). Compared to PSO-BPNN, WSPSO-BPNN demonstrated superior performance. The accuracy, precision, sensitivity, specificity, FPR and CT of WSPSO-BPNN for malignant dataset were 96.88%, 99.08%, 96.43%, 97.92%, 2.08%, and 32.38 seconds, respectively, while the corresponding values for PSO-BPNN were 93.13%, 96.33%, 93.75%, 91.67%, 8.33% and 44.03 seconds, respectively. Also for the accuracy, precision, sensitivity, specificity, FPR and CT of WSPSO-BPNN for benign dataset were 96.15%, 98.14%, 96.34%, 95.71%, 4.29%, and 40.04 seconds, respectively, while the corresponding values for PSO-BPNN were 93.59%, 96.27%, 94.51%, 91.43%, 8.57% and 61.94 seconds respectively showcasing its potential for improving breast cancer diagnosis. Keywords: Back Propagation Neural Network, Breast Cancer, Classification, Mammogram Images, Particle Swarm Optimization, White Shark Optimization. Oyerinde, I.M., Olabiyisi, S.O., Falohun, A.A. & Awodoye, O.O. (2024); Enhanced Breast Cancer Detection Using Modified Particle Swarm Optimization-Based Back Propagation Neural Network. Journal of Advances in Mathematical & Computational Science. Vol. 12, No. 1. Pp 53-62. Available online at www.isteams.net/mathematics-computationaljournal. dx.doi.org/10.22624/AIMS/MATHS/V12N1P5

Disease Prognosis of Fetal Heart’s Four-Chamber and Blood Vessels in Ultrasound Images Using CNN Incorporated VGG 16 and Enhanced DRNN

Fetal Heart Disease (FHD) based Structural Heart Disorders (SHD) occur when certain features of the heart develop abnormally. These flaws may cause blood flow to circulate in the erroneous spot, slow down, or be utterly blocked. Heart Defects (HD) caused via FHD or disorders that primarily impact embryonic heart conditions are alternatively referred to as Congenital Heart Defects (CHD). Multiple prior investigation algorithms such as Multi-Resolution Convolutional Neural Network (MRCNN), Deep Convolutional Neural Network (DCNN), Faster-RCNN (FRCNN) and DANomaly Wgan-GP and Convolutional Neural Network (DGACNN) rendered in the detection of FHD. Yet, the models have endured several challenges due to fuzzy constraints and irrelevant adherence. The intended aim is to detect the dilemma of the fetal heart in UltraSound (US) images using two distinct tier methods. The initial tier detects the fetal heart chamber's walls and valves using the Convolutional Neural Network (CNN)-incorporated Visual Geometry Group 16 (VGG 16) technique for processing fetal ultrasound images, allowing it to detect and dissolve anomalies in heart walls. This initial investigation concerns improving the image's quality in each subsequent sequence, from lowest to most improved using the conventional Augmented Wiener Filtering (AWF) approach. Succeeding, an instance-level Region of Interest (ROI) segmentation for exploiting the feature mining approach will be carried out via spatial features masking and ground-truth labeling framework for septal defect diagnosis. The second tier determines the flaws in fetal heart blood flow size, structure and vessels utilizing Deep Recurrent Neural Network (DRNN) integrated with region-based texture characteristics Local-Binary-Pattern (LBP), Histogram-of-Oriented-Gradient (HOG) and the Bags Of Features (BOF) segmentation framework via image acquiring. In eventual, the histogram equalization enhancement algorithm with Median Modified Wiener Filter (MMWF) is enumerated to enhance the visual quality, tests for signal-to-noise ratio, rate of variations, and noise proportion for sorting the blood vessels of the input fetal image. The analyzed CNN’s VGG 16 and DRNN model’s efficiency via Matrix Laboratory (MATLAB) has detected the cardiac features both in normal and abnormal ranges with an overall accuracy of 99.89% and 98.7%.

A Machine Learning Approach for Automated Detection and Classification of Cracks in Ancient Monuments using Image Processing Techniques

Stone monuments stand as enduring testaments to human history and cultural heritage, yet they are susceptible to deterioration over time. In this paper, we propose a comprehensive approach for the automated detection and classification of cracks in ancient monuments, integrating machine learning and advanced image processing techniques. Our method addresses the pressing need for efficient and objective assessment of structural integrity in these invaluable artifacts. The proposed algorithm begins with preprocessing steps, including image enhancement using adaptive histogram equalization to improve crack visibility. Subsequently, feature extraction techniques such as Grey Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP) are applied to capture essential characteristics of crack patterns. Central to our approach are the Back Propagation Neural Network (BPNN) and Improved Support Vector Machine (ISVM) classifiers, which are trained on the extracted features to detect and classify cracks with high accuracy. The BPNN learns complex relationships between input features and crack types, while the ISVM leverages a margin-based approach for robust classification. Through extensive experimentation on a diverse dataset of ancient monuments, we demonstrate the effectiveness of our approach in accurately identifying and categorizing cracks. The proposed method offers a scalable and objective solution for monitoring the structural health of ancient monuments, contributing to proactive conservation efforts and the preservation of cultural heritage.

Deep Spectral Convolution Neural Network Based Leukemia Cancer Detection Using Invariant Entity Scalar Feature Selection

Leukemia, a cancer that attacks human white blood cells, is one of the deadliest illnesses. Detecting affected cells in microscopic images becomes tedious because feature variants are not predicted correctly by a hematologist. Therefore image handling techniques failed to select the importance of the features scaling counts, entities, and precise size and shape of cells presented in the microscopic image. To resolve this problem, Deep Spectral Convolution Neural Network (DSCNN) based on Leukemia cancer detection using Invariant Entity Scalar Feature Selection (IESFS) is proposed to identify the risk factor of cancer for early diagnosis. Initially, preprocessing is carried out using cascade Gabor filters. Based on Structural Cascade Segmentation (SCS), the white blood cell regions are categorized into affected and non-affected margins and verify the edges using canny edge mapping. This estimates the scaling cell size, counts, entities and angular cell projection of weights from each segmented feature region. Then find the entity relation of cell projection equivalence using Color Intensive Histogram Equalization (CIHE). After segmenting the angular vector, projection scaling is applied to correlate the entity's object scaling comparator. Then scaling features were selected using Invariant Entity Scalar Feature Selection (IESFS) by averaging the mean depth values of feature weight and trained with a deep convolution neural network for predicting max equivalence entity weights for finding the affected cells and counts in microscopic images. This improves the prediction of cancer cell accuracy as well high performance in sensitivity 92.7 %, specificity 92.3 %, and f-measure 93.6 % with redundant time complexity.

Enhancing breast cancer detection from histopathology images: A novel ensemble approach with deep learning-based feature extraction

Effective detection and diagnostic procedures are necessary to enhance patient results for the common and life-threatening illness of breast cancer. Current approaches have limits in scalability and efficiency, highlighting the need for more study. This work introduces a hybrid Breast Cancer (BC) detecting approach that merges Deep Learning (DL) with pre-trained modeling of Histopathology Images (HPI) and an ensemble-based Machine Learning (ML) approach. DL integration allows learning and identifying hidden trends in intricate BC pictures, while ML techniques provide interpretability and generalization skills. Contrast Limited Adaptive Histogram Equalization (CLAHE) was used on HPI as a pre-processing technique to improve picture quality. The ResNet50V2 model was used for deep feature extraction. The Ensemble Learning (EL) model combines predictions from four basic ML approaches using soft voting. The research attained a superior accuracy, precision, recall, and F1 score compared to the most advanced models. This study provides substantial advancements in breast cancer diagnosis, thorough performance evaluation, and reliable assessment. Furthermore, it helps medical personnel make well-informed choices, enhance patient care, and improve results for BC sufferers.

Neutrosophic Fuzzy Logic based SVM approach for Enhanced Skin Cancer Prediction

In this study, a thorough methodology is used to present a unique way for improving skin cancer prediction accuracy. The research uses sophisticated preprocessing methods, such as the Frost filter for noise reduction and histogram equalization for contrast enhancement, to boost contrast on dermoscopic pictures from various sources, using an ISIC 2020 dataset. These actions greatly raise the dermoscopic pictures’ overall quality and usefulness for diagnosis. Utilizing labeled data for training, we offer a Fuzzy-based C-means clustering technique based on Neutrosophic Logic during the segmentation phase. In order to overcome ambiguities in skin lesion segmentation, the neutrosophic set—a groundbreaking idea in philosophy—is used. The suggested model enhances the accuracy of segmentation by modifying the neutrosophic set functions. For precise prediction, the approach combines Support Vector Machine (SVM) classification with Histogram of Oriented Gradient (HOG) feature extraction. While SVM, a supervised learning algorithm, diagnoses skin lesions based on the collected features, HOG features capture gradient information. To improve object recognition and classification, the HOG-SVM architecture is made to methodically collect and quantify essential information using dermoscopic pictures. The use of Neutrosophic Fuzzy Logic, which combines the benefits of fuzzy clustering with neutrosophic sets to produce more precise and nuanced predictions, sets the suggested method apart. The integration of different approaches into a holistic solution for skin cancer prediction is what makes the proposed study innovative. Findings and performance analysis show of the HOG-SVM method exhibits an outstanding accuracy of 98.69%, outperforming LR, KNN, and GNB methods. Python software is used to accomplish the suggested approach. This discovery opens up a possible path for better skin cancer diagnosis and advances the rapidly developing fields of dermatology and medical image processing.

Target detection and classification via EfficientDet and CNN over unmanned aerial vehicles.

Advanced traffic monitoring systems face significant challenges in vehicle detection and classification. Conventional methods often require substantial computational resources and struggle to adapt to diverse data collection methods. This research introduces an innovative technique for classifying and recognizing vehicles in aerial image sequences. The proposed model encompasses several phases, starting with image enhancement through noise reduction and Contrast Limited Adaptive Histogram Equalization (CLAHE). Following this, contour-based segmentation and Fuzzy C-means segmentation (FCM) are applied to identify foreground objects. Vehicle detection and identification are performed using EfficientDet. For feature extraction, Accelerated KAZE (AKAZE), Oriented FAST and Rotated BRIEF (ORB), and Scale Invariant Feature Transform (SIFT) are utilized. Object classification is achieved through a Convolutional Neural Network (CNN) and ResNet Residual Network. The proposed method demonstrates improved performance over previous approaches. Experiments on datasets including Vehicle Aerial Imagery from a Drone (VAID) and Unmanned Aerial Vehicle Intruder Dataset (UAVID) reveal that the model achieves an accuracy of 96.6% on UAVID and 97% on VAID. The results indicate that the proposed model significantly enhances vehicle detection and classification in aerial images, surpassing existing methods and offering notable improvements for traffic monitoring systems.

Atelectasis detection in chest X-ray images using convolutional neural networks and transfer learning with anisotropic diffusion filter

Atelectasis is the loss of volume caused by decreasing gas in a specific area of the lung. It occurs when the lung sacs (alveoli) do not fully inflate, resulting in a lack of oxygen to the blood, tissues, organs, and fill with alveolar fluid. It can be caused by pressure outside of your lung, an obstruction, poor airflow, or scarring. It is critical to diagnose this lung condition as soon as possible. Chest X-rays are the most commonly utilized diagnostic tool for this condition. Examining chest X-rays, however, is difficult even for a professional radiologist. There is a need to improve diagnosis accuracy. As a result, this study proposes a novel detection and classification approach for rapid diagnosis of atelectasis utilizing patient chest X-ray data. To diagnose atelectasis from chest X-ray images, we used state-of-the-art models like VGG19, Inception, and a deep learning method (CNN). This study presents an effective method for categorizing chest X-ray images as normal or atelectasis-infected. This study offers a convolutional neural network (CNN) method to aid medical experts in identifying atelectasis disease. The anisotropic diffusion filtering (ADF) approach was used to improve image edge preservation, reduce noise, and contrast limited adaptive histogram equalization (CLAHE) for improving the contrast of low-intensity images. After evaluating the CNN model, it achieved 99.88 % training accuracy, 99 % validation accuracy, and 99 % test accuracy. In this study, CNN achieved a result that outperformed state-of-the-art models (VGG19 and Inception). As a result of the findings, deep features provided consistent and reliable features for detecting atelectasis. Therefore, the suggested method expedites atelectasis diagnosis and radiologists' screening of atelectasis patients.

Cetacean Optimization Based Medical Image Contrast-Enhancement Technique for Improving Disease Diagnosis in Cardiac MRI

Conventional preprocessing methods in medical imaging can effectively reduce the combination of Gaussian and Impulsive noise, while still maintaining the crucial features such as edges within the images. However, these techniques are found to lag in the optimizing the certain image parameters which play a crucial rule in enhancing the input images and thus may lead to failing in preserving the edges that may adversely affect the early diagnosis of diseases. An attempt has been made to enhance the contrast of cardiac MR (Medical Resonance) images using Cetacean Optimization Algorithm (COA) for improving disease diagnosis. Input cardiac images have been acquired from the free online available databases viz., SCMR consensus and AMRG Atlas. The methodology includes integration of the cost function with contrast measure based on certain metrics to create a newer transformation function. It results in enhanced search pattern using a transformation function in spatial domain and improves the pixel intensity to increase the resolution of an image. The developed algorithm’s performance was evaluated by computing various parameters including peak signal-to-noise ratio (PSNR), structural similarity index measurement (SSIM), mean square error (MSE), and normalized absolute error (NAE). Analysis of the results reveals that the proposed method achieves the highest PSNR (72 dB) and SSIM (0.99) values, along with the lowest NAE (0.16%) and MSE (0.22%) compared to both the particle swarm optimized texture-based histogram equalization (PSOTHE) method and the modified sunflower optimization (MSFO) method. The results indicate that the suggested strategy might improve the intricate details of the input cardiac MRI images. This enhancement can contribute to the efficient identification of cardiac disorder-specific biomarkers.

Nighttime Car Accident Prevention with AI Vision

Abstract: Nighttime car prevention with AI vision performs a vital function in diverse fields, which include surveillance, protection, and autonomous navigation. However, the demanding situations posed through low-mild situations make accurate and reliable object detection a complex undertaking. The proposed device leverages ultra-modern photograph enhancement algorithms to improve the visibility of objects in low-light environments. Utilizing an aggregate of adaptive histogram equalization, noise discount, and comparison enhancement, the machine enhances the uncooked input from nighttime imaginative and prescient sensors, presenting a clearer and greater particular image for subsequent analysis. the item detection module employs a deep knowledge of the primary-based method, making use of a pre-educated convolutional neural network (CNN) optimized for low-light eventualities. To deal with actual-time deployment requirements, the gadget is optimized for computational performance, making it suitable for integration into resource-restrained systems consisting of surveillance cameras and unmanned aerial cars (UAVs). The proposed answer is evaluated via good-sized experiments, demonstrating goodsized improvements in item detection accuracy as compared to standard nighttime imaginative and prescient systems.