Image Characteristics Research Articles

DualTransAttNet: A Hybrid Model with a Dual Attention Mechanism for Corn Seed Classification

Varietal purity is a critical quality indicator for seeds, yet various production processes can lead to the mixing of seeds from different varieties. Consequently, seed variety classification is an essential step in seed production. Existing classification algorithms often suffer from limitations such as reliance on single information sources, constrained feature extraction capabilities, time consumption, low accuracy, and the potential to cause irreversible damage to seeds. To address these challenges, this paper proposes a fast and non-destructive classification method for corn seeds, named DualTransAttNet, based on multi-source image information and hybrid feature extraction. High-resolution hyperspectral images of various corn varieties were collected, and a sliding sampling approach was employed to capture feature information across all spectral bands, resulting in the construction of a hyperspectral dataset for corn seed classification. Hyperspectral and RGB image data were then integrated to complement one another’s information and mitigate the insufficient feature diversity caused by single-source data. The proposed method leverages the strengths of convolutional neural networks (CNNs) and transformers to extract both local and global features, effectively capturing spectral and image characteristics. The experimental results demonstrate that the DualTransAttNet model can achieve a compact size of only 1.758 MB and an inference time of 0.019 ms. Compared to typical machine learning and deep learning models, the proposed model exhibits superior performance with an overall accuracy, F1-score, and Kappa coefficient of 90.01%, 88.9%, and 88.4%, respectively. The model’s rapid inference capability and low parameter count make it an excellent technical solution for agricultural automation and intelligent systems, thereby enhancing the efficiency and profitability of agricultural production.

Total variational noise reduction method for EBAPS image based on weighted nuclear norm minimization

The electron-bombarded active pixel sensor (EBAPS) is a highly sensitive vacuum-solid hybrid low-light imaging device capable of functioning in ultra-low illumination environments as low as 10-4 lx. However, this high sensitivity also causes problems, such as a low signal-to-noise ratio and complex noise. To enhance the quality of low-light night vision images captured by EBAPS and achieve effective imaging in ultra-low illumination, this study proposes a noise reduction algorithm based on the noise characteristics of EBAPS images. By utilizing the weighted nuclear norm minimization (WNNM) as the fundamental framework, several enhanced methods to address the multi-source noise of the EBAPS under ultra-low illumination have been proposed. These methods include outlier removal and variance-stabilizing transformation. To address the lack of edge preservation, a four-directional total variational regularization term has been incorporated into the WNNM model to maintain the image edge. Experimental results demonstrated that the improved method effectively eliminates various types of EBAPS noise while considerably returning the edges, ultimately enhancing the quality of low-light images. This study greatly facilitates subsequent applications of the low-light night vision technology.

Zero-TCE: Zero Reference Tri-Curve Enhancement for Low-Light Images

Addressing the common issues of low brightness, poor contrast, and blurred details in images captured under conditions such as night, backlight, and adverse weather, we propose a zero-reference dual-path network based on multi-scale depth curve estimation for low-light image enhancement. Utilizing a no-reference loss function, the enhancement of low-light images is converted into depth curve estimation, with three curves fitted to enhance the dark details of the image: a brightness adjustment curve (LE-curve), a contrast enhancement curve (CE-curve), and a multi-scale feature fusion curve (MF-curve). Initially, we introduce the TCE-L and TCE-C modules to improve image brightness and enhance image contrast, respectively. Subsequently, we design a multi-scale feature fusion (MFF) module that integrates the original and enhanced images at multiple scales in the HSV color space based on the brightness distribution characteristics of low-light images, yielding an optimally enhanced image that avoids overexposure and color distortion. We compare our proposed method against ten other advanced algorithms based on multiple datasets, including LOL, DICM, MEF, NPE, and ExDark, that encompass complex illumination variations. Experimental results demonstrate that the proposed algorithm adapts better to the characteristics of images captured in low-light environments, producing enhanced images with sharp contrast, rich details, and preserved color authenticity, while effectively mitigating the issue of overexposure.

Cross-modal feature interaction network for heterogeneous change detection

ABSTRACT Heterogeneous change detection is a task of considerable practical importance and significant challenge in remote sensing. Heterogeneous change detection involves identifying change areas using remote sensing images obtained from different sensors or imaging conditions. Recently, research has focused on feature space translation methods based on deep learning technology for heterogeneous images. However, these types of methods often lead to the loss of original image information, and the translated features cannot be efficiently compared, further limiting the accuracy of change detection. For these issues, we propose a cross-modal feature interaction network (CMFINet). Specifically, CMFINet introduces a cross-modal interaction module (CMIM), which facilitates the interaction between heterogeneous features through attention exchange. This approach promotes consistent representation of heterogeneous features while preserving image characteristics. Additionally, we design a differential feature extraction module (DFEM) to enhance the extraction of true change features from spatial and channel dimensions, facilitating efficient comparison after feature interaction. Extensive experiments conducted on the California, Toulouse, and Wuhan datasets demonstrate that CMFINet outperforms eight existing methods in identifying change areas in different scenes from multimodal images. Compared to the existing methods applied to the three datasets, CMFINet achieved the highest F1 scores of 83.93%, 75.65%, and 95.42%, and the highest mIoU values of 85.38%, 78.34%, and 94.87%, respectively. The results demonstrate the effectiveness and applicability of CMFINet in heterogeneous change detection.

ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic images.

ChatGPT has the ability to generate human-like text, analyze and understand medical images using natural Language processing (NLP) algorithms. It can generate real-time diagnosis and recognize patterns and learn from previous cases to improve accuracy by combining patient history, symptoms, and image characteristics. It has been used recently for learning about maxillofacial diseases, writing and translating radiology reports, and identifying anatomical landmarks, among other things.

Fault Diagnosis of Lithium Battery Modules via Symmetrized Dot Pattern and Convolutional Neural Networks.

This paper proposes a hybrid algorithm combining the symmetrized dot pattern (SDP) method and a convolutional neural network (CNN) for fault detection in lithium battery modules. The study focuses on four fault types: overcharge, over-discharge, aging, and leakage caused by manual perforation. An 80.5 kHz high-frequency square wave signal is input into the battery module and recorded using a high-speed data acquisition card. The signal is processed by the SDP method to generate characteristic images for fault diagnosis. Finally, a deep learning algorithm is used to evaluate the state of the lithium battery. A total of 3000 samples were collected, with 400 samples used for training and 200 for testing for each fault type, achieving an overall identification accuracy of 99.9%, demonstrating the effectiveness of the proposed method.

Filling the Gap: Enhancing Borehole Imaging with Tensor Neural Network

Borehole imaging is crucial in geological research as it offers insights into subsurface formations and supports reservoir assessment, mineral exploration, and hydrocarbon extraction. However, the effectiveness of borehole imaging is limited by the incompleteness of data due to the design constraints of borehole imaging tools. Missing areas in borehole images pose challenges to geologists. While existing methods, such as pattern filling and CNN-based techniques, show some efficacy, they often require a large amount of complete images for training. In recent years, unsupervised deep learning and tensor-based methods have gained attention for their ability to reconstruct missing or degraded geological images by leveraging the structural characteristics of images. In particular, tensor representations based on Tucker decomposition have shown strong capabilities in data completion. Inspired by this, we propose a novel self-supervised Tensor Neural Network (TNN) utilizing Tucker decomposition as our backbone. Since borehole images are wraped to 2D data, converting them into tensor representations is a critical step in leveraging the proposed tensor representation. To achieve this, we introduce the Adaptive Boundary-Detection Cropping with Augmentation algorithm, which adapts 2D images into 3D tensors. After interpolating the tensors using the proposed tensor network, we employ Adaptive Slice Concatenation with Replacement to restore the complete images from the enhanced tensors, ensuring that the tensor representation of 3D data is accurately depicted in the 2D images. The proposed TNN can be further enhanced by incorporating a structural regularizer. Actual data experiments demonstrate that our method effectively fills gaps in borehole images with higher clarity and detail. The completed images retain crucial geological features and textures, surpassing some of the existing self-supervised learning methods.

ENSEMBLE METHOD BASED ON AVERAGING SHAPES OF OBJECTS USING THE PYRAMID METHOD

Context. Image segmentation plays a key role in computer vision. The quality of segmentation is affected by many factors: noise, artifacts, complex shapes of objects. Classical methods cannot always guarantee good success, depending on the quality of the image and the existing noise, they cannot always achieve the desired result. The proposed method uses an ensemble of neural networks, which makes it possible to increase the accuracy and stability of segmentation. Objective. The goal of the work is to develop a new method of combining predictions of neural network ensembles, which can improve segmentation accuracy by combining images of different image sizes. Method. A method is proposed that averages the shapes of objects depicted on prediction masks. A pyramid of images is used to improve segmentation quality, each level of the pyramid corresponds to an increased size of the original image. This approach allows obtaining image characteristics at different levels. For a test image, a prediction is obtained from each neural network in the ensemble, after which a pyramid is built for the image. All pyramid levels are combined into the final image using SAAMC. All obtained final images for each neural network are also combined at the end using SAAMC. The use of an ensemble of neural networks combined with the pyramid method allows for reducing the impact of noise and artifacts on the segmentation results. Results. The use of this method was compared with the usual use of individual neural networks and the ensemble averaging method. The obtained results show that the proposed method outperforms its competitors. Application of the proposed method improved the accuracy and quality of segmentation. Conclusions. The conducted research confirmed the sense of using an ensemble of neural networks and creating a new method of combining predictions. The use of an ensemble of neural networks makes it possible to compensate for the errors and shortcomings of individual neural networks. Using the proposed method can significantly reduce the impact of noise and artifacts on segmentation. Further study and modification of this method will make it possible to further improve the quality of segmentation.

Low-Light Image Enhancement Using CycleGAN-Based Near-Infrared Image Generation and Fusion

Image visibility is often degraded under challenging conditions such as low light, backlighting, and inadequate contrast. To mitigate these issues, techniques like histogram equalization, high dynamic range (HDR) tone mapping and near-infrared (NIR)–visible image fusion are widely employed. However, these methods have inherent drawbacks: histogram equalization frequently causes oversaturation and detail loss, while visible–NIR fusion requires complex and error-prone images. The proposed algorithm of a complementary cycle-consistent generative adversarial network (CycleGAN)-based training with visible and NIR images, leverages CycleGAN to generate fake NIR images by blending the characteristics of visible and NIR images. This approach presents tone compression and preserves fine details, effectively addressing the limitations of traditional methods. Experimental results demonstrate that the proposed method outperforms conventional algorithms, delivering superior quality and detail retention. This advancement holds substantial promise for applications where dependable image visibility is critical, such as autonomous driving and CCTV (Closed-Circuit Television) surveillance systems.

Lossless Image Compression Using Context-Dependent Linear Prediction Based on Mean Absolute Error Minimization.

This paper presents a method for lossless compression of images with fast decoding time and the option to select encoder parameters for individual image characteristics to increase compression efficiency. The data modeling stage was based on linear and nonlinear prediction, which was complemented by a simple block for removing the context-dependent constant component. The prediction was based on the Iterative Reweighted Least Squares (IRLS) method which allowed the minimization of mean absolute error. Two-stage compression was used to encode prediction errors: an adaptive Golomb and a binary arithmetic coding. High compression efficiency was achieved by using an author's context-switching algorithm, which allows several prediction models tailored to the individual characteristics of each image area. In addition, an analysis of the impact of individual encoder parameters on efficiency and encoding time was conducted, and the efficiency of the proposed solution was shown against competing solutions, showing a 9.1% improvement in the bit average of files for the entire test base compared to JPEG-LS.

DSCONV-GAN: a UAV-BASED model for Verticillium Wilt disease detection in Chinese cabbage in complex growing environments

Verticillium wilt greatly hampers Chinese cabbage growth, causing significant yield limitations. Rapid and accurate detection of Verticillium wilt in the Chinese cabbage (Brassica rapa L. ssp. pekinensis) can provide significant agronomic benefits. Here, we propose a detection model, DSConv-GAN, which is based on images acquired by an unmanned aerial vehicle (UAV). Based on YOLOv8, with the addition of the dynamic snake convolution (DSConv) module and the improved loss function maximum possible distance intersection-over-union (MPDIoU), we acquired enhanced complex structures and global characteristics in Chinese cabbage images under different growth conditions. To reduce the difficulty of acquiring diseased Chinese cabbage data, a cycle-consistent generative adversarial network (CycleGAN) was used to simulate and generate images of the Verticillium wilt characteristics for multiple fields. The detection of lightly infected plants achieved precision, recall, mean average precision (mAP), and F1-score of 81.3, 86.6, 87.7, and 83.9%, respectively. DSConv-GAN outperforms other models in terms of precision, detection speed, robustness, and generalization. The model is combined with software to improve the practicability of the proposed method. Our results demonstrate DSConv-GAN to be an effective intelligent farming tool that provides early, rapid, and accurate detection of Chinese cabbage Verticillium wilt in complex growing environments.

Optimization of Cocoa Pods Maturity Classification Using Stacking and Voting with Ensemble Learning Methods in RGB and LAB Spaces.

Determining the maturity of cocoa pods early is not just about guaranteeing harvest quality and optimizing yield. It is also about efficient resource management. Rapid identification of the stage of maturity helps avoid losses linked to a premature or late harvest, improving productivity. Early determination of cocoa pod maturity ensures both the quality and quantity of the harvest, as immature or overripe pods cannot produce premium cocoa beans. Our innovative research harnesses artificial intelligence and computer vision technologies to revolutionize the cocoa industry, offering precise and advanced tools for accurately assessing cocoa pod maturity. Providing an objective and rapid assessment enables farmers to make informed decisions about the optimal time to harvest, helping to maximize the yield of their plantations. Furthermore, by automating this process, these technologies reduce the margins for human error and improve the management of agricultural resources. With this in mind, our study proposes to exploit a computer vision method based on the GLCM (gray level co-occurrence matrix) algorithm to extract the characteristics of images in the RGB (red, green, blue) and LAB (luminance, axis between red and green, axis between yellow and blue) color spaces. This approach allows for in-depth image analysis, which is essential for capturing the nuances of cocoa pod maturity. Next, we apply classification algorithms to identify the best performers. These algorithms are then combined via stacking and voting techniques, allowing our model to be optimized by taking advantage of the strengths of each method, thus guaranteeing more robust and precise results. The results demonstrated that the combination of algorithms produced superior performance, especially in the LAB color space, where voting scored 98.49% and stacking 98.71%. In comparison, in the RGB color space, voting scored 96.59% and stacking 97.06%. These results surpass those generally reported in the literature, showing the increased effectiveness of combined approaches in improving the accuracy of classification models. This highlights the importance of exploring ensemble techniques to maximize performance in complex contexts such as cocoa pod maturity classification.

Novel variant transformer-based method for aluminum profile surface defect detection

Abstract The detection of surface defects on metal plays a pivotal role in the evaluation of product quality for aluminum profiles. So far, the most prevalent approach for detecting metal surface defects is still through the utilization of traditional conventional neural networks (CNNs). However, transformer-based methods have made notable improvements in computer vision in recent years, exhibiting superiority over traditional CNNs in the majority of tasks. In regard to aluminum surface defect image characteristics, such as intricate textures, few defect samples, and large-scale differences in various defects, traditional CNNs have difficulty further improving performance. This paper proposes a novel method based on a variant transformer for surface defect detection of aluminum profiles, which combines a traditional CNN and a transformer architecture with a deformable attention module (DAM). The DAM better focuses on part of critical sampling points around the reference point, which alleviates the unacceptable complexity in high-resolution feature maps and enhances the recognition effect of small target defects. The image stitching method proposed uses defect-free samples to generate new samples, which partially mitigates the issue of class imbalance. Moreover, we carried out supplementary experiments to confirm the effectiveness of transfer learning in training small-scale datasets. Compared with the baseline, the mean average precision (mAP) was improved by 3.32%. Extensive experimental results demonstrate the efficacy of our method in accurately detecting surface defects of aluminum profiles and significantly improving the detection of small target defects.

A Novel Three-Stage Dehazing Model Using Improved Auto-Color Transfer Method, Adaptive Dehazing, and Adaptive Contrast Enhancement

The problems of underexposure, under-detail-enhancement and residual haze are detected in the previous dehazing techniques. These issues occur due to different reasons and are highly difficult to be resolved using a single algorithm. Therefore, a three-stage dehazing model (TSDM) is proposed in this paper using pre-processing, dehazing and post-processing modules. The improved auto-color transfer (IACT) approach is presented as part of pre-processing to efficiently enhance the hazy image to overcome underexposure. Also, adaptive dehazing (AD) is developed in this work which considers the global characteristics of the hazy image as a parameter, to adaptively enhance the details. Moreover, adaptive contrast enhancement (ACE) is proposed as a post-processing operation that adaptively fuses the dehazed image and its contrast-enhanced image to effectively improve the contrast. However, the IACT operation is performed on the hazy image only when dark regions are detected. Similarly, the ACE is performed only when a dehazed image exhibits residual haze. Based on these prior conditions, the proposed work can be implemented in four distinct ways i.e. using only the AD technique; using IACT and AD approaches, using AD and ACE methods, and using all IACT, AD and ACE algorithms. The proposed TSDM is experimentally analyzed using many databases which shows improved results compared to previous techniques.

Clinical and radiologic criteria to predict endoscopic third ventriculostomy success in non-communicating pediatric hydrocephalus

ObjectiveEndoscopic third ventriculocisternostomy (ETV) became the relevant treatment option for non-communicating pediatric hydrocephalus. ETV success was predicted in relation to age, diagnosis, and previous shunt implantation. Radiological factors are usually taken for indication decision-making. The aim of this study is to investigate radiological signs of non-communicating hydrocephalus for ETV success in a single-center retrospective analysis.Patients and methodsETV interventions were collected from a 10-year period (2010–2019) from our institution. Clinical patient characteristics such as prematurity, age, diagnosis, and previous shunt treatment and follow-up in terms of possible shunt implantation or revision surgeries were investigated. Radiological data was retrieved from the in-house PACS system to analyze preoperative signs for non­communicating hydrocephalus such as ventricular size, pressure gradients at the third ventricle, and any signs of obstruction from internal towards external cerebral spinal fluid communication. Fisher’s test was used to demonstrate the significance of each individual predictor. A multivariable model was built using the backward elimination method with multiple logistic regression.ResultsFrom 136 ETV interventions, 95 met the inclusion criteria (age < 18 years; > 6-month follow-up; MR image data availability, treatment goal for shunt independence). In chi-square statistical evaluation of single parameters age > 6 months (OR 32.5; 95% CI 4.8–364), ventricular width (FOHR < 0.56; OR 6.1; 95% CI 2.2–16.3) and non-post-hemorrhagic hydrocephalus as underlying diagnosis (OR 13.1; 95% CI 1.9–163) showed significant increased odds ratio for shunt independence during follow-up. Logistic regression analysis for multiple parameters showed age > 6 months (OR 29.3; 95% CI 4.1–606) together with outward bulged lamina terminalis (OR 4.6; 95% CI 1.2–19.6), smaller FOHR (continuous parameter; OR 2.83 × 10−5; 95% CI 4.7 × 10−9–0.045), and non-4th-ventricular-outlet obstruction (4thVOO; OR 0.31; 95% CI 0.09–1.02) as significant factors for ETV success.ConclusionETV has become a relevant treatment for non-communicating hydrocephalus, with typical MR image characteristics. Analyzing radiological markers as predictors for success smaller ventricular width and outward displaced lamina terminalis was relevant in combination with age > 6 months. Since the analysis is based on single-center experience, a larger cohort of patients with a multi-center approach should further investigate the combined clinical and radiological criteria.

COMPRESSION METHODS FOR SATELLITE IMAGES USING WAVELET TRANSFORM AND PERFORMANCE EVALUATION

Research on image compression spans various fields, focusing on achieving efficient compression while preserving a specific image quality. Satellite images captured by observation satellites, possess unique characteristics distinct from other images. Analyzing these specific traits is crucial, leading to the proposal of tailored compression methods and transforms suitable for satellite image characteristics. This study comprehensively assesses the performance of six well-known compression methods in the literature, utilizing wavelet transform and metrics such as bits per pixel (BPP), compression ratio (CR), Peak Signal-to-Noise Ratio (PSNR), calculation time (CT), and Mean Squared Error (MSE). The compressed satellite images, generated through six methods and the Coif3 wavelet, are systematically compared and evaluated using performance metrics. The average values obtained for all six methods are 96.37%, 47.10 dB, and 7.92 seconds for CR, PSNR and CT receptively, while WDR exhibits CR 96.36%, PSNR 48.84 dB, and CT 6.58 seconds. The findings indicate that the Wavelet Difference Reduction (WDR) compression method utilizing the Coif3 wavelet outperforms others when considering all parameters together. For effective compression of observation satellite images, we suggest that operators and manufacturers choose for wavelet transform and WDR compression methods to achieve optimal results.

Clinical Course and Prognostic Factors in Non-Neovascular Age-Related Macular Degeneration with Subretinal Fluid.

To investigate the clinical course and prognostic factors of age-related macular degeneration (AMD) without macular neovascularization (MNV) in patients presenting with pigment epithelial detachment (PED) and the associated subretinal fluid (SRF). Morphological characteristics of spectral-domain optical coherence tomography images were analyzed to determine anatomic outcomes. Factors associated with the progression to late AMD, defined as complete retinal pigment epithelium and outer retinal atrophy (cRORA) or MNV, were investigated. Fifty eyes of 41 patients were included in this study. The most common SRF location was the angle of the PED (56%), and there was a significant decrease in SRF thickness and PED height and width over the follow-up period. Eleven (22%) eyes developed cRORA, and seven (14%) eyes developed MNV during a mean period of 52.1 months. Multivariate analysis revealed that hyperreflective foci and MNV in the fellow eye were associated with the development of cRORA, and higher PED height was a significant factor associated with the development of MNV. In patients with AMD, SRF can be accompanied by PED in the absence of MNV. Notably, patients with this characteristic entity can progress to late AMD, including cRORA and MNV, in a significant proportion of cases.

Evaluation of COVID-19 Findings on Thoracic CT: Is There any Correlation with Age and Comorbidity?

Aim: To share insights gained from low-dose thoracic computed tomography (CT) findings of patients diagnosed with COVID-19. Additionally, we aimed to evaluate the correlation between the observed CT findings, CT severity index, patient age, and the presence of comorbid conditions. Material and Method: One hundred patients having a COVID-19 diagnosis were included in the study's sample. We meticulously reviewed the thoracic CT image characteristics, the lung severity index, and various clinical data related to the patients. The relationships between these factors were then analyzed to draw meaningful conclusions. Results: The study included 100 patients, consisting of 67 men and 33 women. Among these patients, 30 had at least one underlying comorbid condition, with hypertension being the most prevalent. CT scans were positive in 65 patients. Within this group, 60 patients (93.3%) exhibited ground-glass opacities (GGO), 27 patients (41.5%) showed signs of consolidation, 22 patients (33.8%) had both GGO and consolidation, and 8 patients (12.3%) displayed the crazy paving pattern. The total lung severity score (TLSS) ranged from 0 to 19, with mean score of 3.11±3.71. Each lung lobe was systematically evaluated for the extent of involvement. We found a statistically significant relationship indicating that increasing age correlated with higher grades of lung involvement. Furthermore, significant association was noted between presence of comorbidities and the lung involvement grades. Our analysis revealed a moderate positive correlation between CT lung involvement grade and patient age, alongside a weaker positive correlation between the lung involvement grade and comorbid conditions. Conclusion: CT imaging has proven to be important tool in managing patients suspected of or confirmed to have COVID-19. Notably, the CT lung severity grade was significantly elevated in patients over 65 years and those with comorbidities. These findings underscore the critical role that CT plays in evaluating and managing the severity of COVID-19 pneumonia.

Multi-Sensor Image Classification Using the Random Forest Algorithm in Google Earth Engine with KOMPSAT-3/5 and CAS500-1 Images

This study conducted multi-sensor image classification by utilizing Google Earth Engine (GEE) and applying satellite imagery from Korean Multi-purpose Satellite 3 (KOMPSAT-3), KOMPSAT-5 SAR, Compact Advanced Satellite 500-1 (CAS500-1), Sentinel-1, and Sentinel-2 within GEE. KOMPSAT-3/5 and CAS500-1 images are not provided by GEE. The land-use and land-cover (LULC) classification was performed using the random forest (RF) algorithm provided by GEE. The study experimented with 10 cases of various combinations of input data, integrating Sentinel-1/-2 imagery and high-resolution imagery from external sources not provided by GEE and those normalized difference vegetation index (NDVI) data. The study area is Boryeong city, located on the west coast of Korea. The classified objects were set to six categories, reflecting the region’s characteristics. The accuracy of the classification results was evaluated using overall accuracy (OA), the kappa coefficient, and the F1 score of the classified objects. The experimental results show a continued improvement in accuracy as the number of applied satellite images increased. The classification result using CAS500-1, Sentinel-1/-2, KOMPSAT-3/5, NDVI from CAS500-1, and NDVI from KOMPSAT-3 achieved the highest accuracy. This study confirmed that the use of multi-sensor data could improve classification accuracy, and the high-resolution characteristics of images from external sources are expected to enable more detailed analysis within GEE.

Using Deep Learning Techniques to Enhance Blood Cell Detection in Patients with Leukemia

Medical diagnosis plays a critical role in the early detection and treatment of diseases by examining symptoms and supporting findings through advanced laboratory testing. Early and accurate diagnosis is essential for detecting medical problems and then prescribing the most effective treatment strategies, especially in life-threatening diseases such as leukemia. Leukemia, a blood malignancy, is one of the most prevalent cancer types affecting both adults and children. It is caused by the rapid and uncontrolled growth of abnormal white blood cells in the bone marrow. This accumulation interferes with the production of normal blood cells, leading to a weakened immune deficiency, anemia, and bleeding disorders. Conventional leukemia diagnostic methods are time-consuming, manually intensive, and inefficient. This research study proposes an automatic diagnostics prediction of leukemia by analyzing blood images according to the shape of the blast cells using digital image processing and machine learning. The purpose of blood cell detection is to precisely identify and classify diverse blood cells, detecting anomalies associated with blood cancers like leukemia. This supports early diagnosis and monitoring, which leads to more effective treatments and improved results for cancer patients. To accomplish this task, we use digital image processing techniques and then apply the convolutional neural network (CNN) deep learning algorithm to blood sample images. This research employs a multi-stage methodology, including data preparation, data preprocessing, feature extraction, and then classification. While our model is built on a typical CNN architecture, we make significant advances by using preprocessing techniques and hyperparameter tuning. We have modified its layers combination to include convolutional, pooling, and fully connected layers that are optimized for image characteristics. These layers are fine-tuned for better feature extraction and classification accuracy. This study showed that blood cell detection for diagnosing acute leukemia based on images had 99% accuracy and outperformed other advanced models, including DenseNet121, ResNet-50, Incep-tionv3, MobileNet, and EfficientNet. The comprehensive analysis of the results reveals the highest accuracy of leukemia detection as compared to existing studies in the relevant literature.