Image Converter Research Articles

Machine learning based fileless malware traffic classification using image visualization

In today’s interconnected world, network traffic is replete with adversarial attacks. As technology evolves, these attacks are also becoming increasingly sophisticated, making them even harder to detect. Fortunately, artificial intelligence (AI) and, specifically machine learning (ML), have shown great success in fast and accurate detection, classification, and even analysis of such threats. Accordingly, there is a growing body of literature addressing how subfields of AI/ML (e.g., natural language processing (NLP)) are getting leveraged to accurately detect evasive malicious patterns in network traffic. In this paper, we delve into the current advancements in ML-based network traffic classification using image visualization. Through a rigorous experimental methodology, we first explore the process of network traffic to image conversion. Subsequently, we investigate how machine learning techniques can effectively leverage image visualization to accurately classify evasive malicious traces within network traffic. Through the utilization of production-level tools and utilities in realistic experiments, our proposed solution achieves an impressive accuracy rate of 99.48% in detecting fileless malware, which is widely regarded as one of the most elusive classes of malicious software.

Automatic Segmentation of Histological Images of Mouse Brains

Using a high-throughput neuroanatomical screen of histological brain sections developed in collaboration with the International Mouse Phenotyping Consortium, we previously reported a list of 198 genes whose inactivation leads to neuroanatomical phenotypes. To achieve this milestone, tens of thousands of hours of manual image segmentation were necessary. The present work involved developing a full pipeline to automate the application of deep learning methods for the automated segmentation of 24 anatomical regions used in the aforementioned screen. The dataset includes 2000 annotated parasagittal slides (24,000 × 14,000 pixels). Our approach consists of three main parts: the conversion of images (.ROI to .PNG), the training of the deep learning approach on the compressed images (512 × 256 and 2048 × 1024 pixels of the deep learning approach) to extract the regions of interest using either the U-Net or Attention U-Net architectures, and finally the transformation of the identified regions (.PNG to .ROI), enabling visualization and editing within the Fiji/ImageJ 1.54 software environment. With an image resolution of 2048 × 1024, the Attention U-Net provided the best results with an overall Dice Similarity Coefficient (DSC) of 0.90 ± 0.01 for all 24 regions. Using one command line, the end-user is now able to pre-analyze images automatically, then runs the existing analytical pipeline made of ImageJ macros to validate the automatically generated regions of interest resulting. Even for regions with low DSC, expert neuroanatomists rarely correct the results. We estimate a time savings of 6 to 10 times.

A novel code generator for graphical user interfaces

Graphical user interfaces (GUIs) are widely used in human–computer interaction, providing a convenient interface for operation. Automating the conversion of GUI design images into source code can significantly reduce the coding workload for front-end developers. Detecting elements in GUI images is a key challenge in achieving automatic GUI code generation and is crucial for tasks such as GUI automation and testing. However, current state-of-the-art methods do not fully consider the unique characteristics of GUI images and elements, and they lack the required high localization accuracy, resulting in low detection accuracy for GUI element boxes. In this paper, we propose GUICG, an automatic GUI code generator that combines deep neural networks with image processing techniques to efficiently detect GUI elements from GUI images and generate front-end code. We empirically investigate various deep learning approaches and image processing methods for GUI component detection. Based on a comprehensive understanding of their performance and characteristics, we design GUICG by fusing image processing with a deep learning-based target detection model, achieving state-of-the-art performance. GUICG outperforms existing methods in accuracy and F1 score for component detection tasks, while producing human-readable code with a logical structure. Furthermore, we conduct an ablation study to quantitatively assess the impact of each key element in GUICG.

Abstract 17760: Conversion of Dicom ECG Images to Tabular Format for Building Large Language Model in Diagnoses and Disease Progression of Cardiovascular Conditions

Introduction: DICOM Electrocardiography (ECG) images from individuals are routinely stored at the institutional PACS server, including normal and abnormal findings. Hypothesis: The study’s objective is to create a database of ECGs as per Standard Communication Protocol (SCP) and to build an accurate Large Language Model (LLM) across different cardiovascular conditions Methods: DICOM ECGs are retrieved, anonymized and labelled to convert the signals to (x, y) coordinates with the help of PyDicom libraries. The tabular format is then stored with lead definition and dimensions of duration and amplitude, metadata, clinical conditions, and textual diagnoses. Results: In the pilot study, 1308 ECGs from individuals with different age (<45 & >45 years), gender (male & female), binary clinical categories (normal & abnormal) and heart rate (<90 & >90 per min) are selected for analysis and modeling. The DICOM image signal reproducibility following conversion (Figure 1 & 2) shows Cross Correlation Percentage of 0.85 (0.76 - 0.94) (Figure 3). An eXtreme Gradient Boosting (XGBoost) model (6) was trained to predict above variables. The results (Figure 4) show AUC highest for predicting binary clinical categories (normal vs abnormal) at 0.81 (0.7 - 0.9) and lowest for predicting age (<45 & >45 years) at 0.6 (0.46 - 0.7). The accuracies in the leads also show similar trend. The limitations include reproducibility of results in Lead VIII, IX and XI, which are sub average and hence being retrained with optimizers. These are initial results with relatively smaller database where multiclass disease or condition classifications are not performed. Conclusions: To conclude, the methodology possesses opportunities to improve the model with Deep Learning and Entity Disambiguation Techniques (NLP) to build Large Language ECG Models for cardiovascular diagnoses and disease progression trajectories.

Quantitatively sensitive and resolution-enhancing strategies in optical signal conversion of SPR images using extensive angle-scanning and image-reconstruction

Surface plasmon resonance imaging (SPRi) is a technology developed from SPR that has emerged in response to the growing need for high-throughput and for discovering diverse applications across multiple domains. Despite its potential, SPRi has encountered limitations in sensitivity when handling low-molecular-mass materials, which emphasizes the need for the quantitative processing of SPRi signals. In this study, an SPRi signal conversion process was developed to enhance the contrast of SPR images and convert them into quantitatively analyzed signals. At first, an optimum incident angle of light was determined as an angle that maximized the difference between sums of the brightness % of functionalized regions and the brightness % of background region in the SPR image, which enabled to obtain a distinct SPR image. In addition, the enhancement of contrast and reduction of noise in the SPR image was achieved using Contrast Limited Adaptive Histogram Equalization (CLAHE) method. Then various pixel domains of the SPR images were simultaneously quantified and visualized the multi-pixel processing technique. For validating the process, an SiO2/Au thin film was modified with four different functionalities and applied to the detection of gas molecules. The SPR images processed using the proposed process exhibited sensitive and quantitative information about the interactions of the functionalities with the target gas in the distinct multiple regions, thus, were applicable to the quantitative monitoring of various phenomena occurring on the plasmonic interface via the advantages of SPRi.

A novel deep-learning-based pressure distribution prediction approach of airfoils

Pressure distribution is a crucial flow characteristic and a key consideration in supercritical airfoil design. Traditionally, obtaining the pressure distribution involves time-consuming and computationally expensive wind tunnel experiments and computational fluid dynamics calculations. This study proposes a deep-learning-based approach to directly map input geometric information to the pressure distribution output, thereby avoiding costly wind tunnel experiments and iterative computational fluid dynamics simulations based on Navier–Stokes equations to address these challenges. Conventional surrogate models typically focus on predicting simple force factors, such as lift and drag coefficients, or require the conversion of airfoil data into images for model training. The novel approach utilizes a Variational Autoencoder for pressure distribution characteristic extraction and reconstruction from feature variables. Unlike conventional models, this approach avoids image conversion and employs a radial basis function neural network for effective mapping. The model exhibits good fitting and generalization capabilities on both training and test datasets, offering a promising solution for rapid pressure distribution prediction in airfoil design. This novel deep-learning-based approach advances airfoil design methodologies, offering significant advantages in computational efficiency and performance prediction. By directly mapping geometric information to pressure distribution, it provides an innovative and promising tool for airfoil design optimization.

Image encoding selection based on Pearson correlation coefficient for time series anomaly detection

Recently, anomaly detection in time-series data has received great attention from researchers due to its importance in problem-solving and predicting future system events. The majority of researchers combine convolutional neural networks (CNN) with image-encoding methods, including Gramian Angular Field (GAF) and Markov Transition Field (MTF). The selection of the right image-encoding method typically involves an iterative evaluation process that requires extensive computational time. This study proposes descriptive statistical analysis and Pearson correlation to find the correlation between statistical features in the encoded data from each image encoding and CNN accuracy. This information is essential for determining the image encoding method without image conversion processes and CNN trials, thus accelerating the computational time. The method tested on the initial dataset showed that the standard-deviation difference has the highest correlation with CNN accuracy (with a Pearson correlation coefficient of r = 0.944), followed by the mean difference (r = 0.705) and the count difference (r = 0.455), also resulting in a 95.35 % reduction in the computation time. The validity of this result was confirmed through the evaluation of several new datasets with different anomaly patterns, making this proposed approach suitable for selecting an appropriate image-encoding method.

Implementation of Continous Delivery using Jenkins And Kubernetes with Docker Local Images

The need for software has increased and the development process has also become more complex as technology has developed which resulted application will take a long time to deployed, which can be completed in weeks or even months. One reason is the large number of teams involved in application development, especially the Development Team and Operations Team. These teams can cause the application delivery process to the user's side to be hampered if a conflict occurs, so the term DevOps appears. Support for DevOps continues to be improved, so there is CI/CD (Continuous Integration and Continuous Delivery/Deployment). Banyak penelitian mengenai CI/CD yang sudah dilakukan dan menggunakan tools Jenkins, Kubernetes, dan Docker. Namun penelitian yang sudah ada menggunakan repository DockerHub untuk menyimpan Docker Image This research focuses on the local implementation of the docker image which is then run with Kubernetes Orchestration so it can reduce the platform used by CI/CD. This implementation requires conversion from docker image to Kubernetes Image Cache. The results show that the Continous Delivery implementation using Kubernetes with the Local Docker image is successful and can run well. The results show that the average time required to create a docker image is 649 seconds (10 minutes 49 seconds) and image conversion process which takes an average time of 275 seconds (4 minutes 35 seconds). Research can be developed further by researching techniques to shorten build time, minimize resource utilitation and minimize time conversion from docker images to Kubernetes Image Cache.

DIAGNOSE EYES DISEASES USING VARIOUS FEATURES EXTRACTION APPROACHES AND MACHINE LEARNING ALGORITHMS

Ophthalmic diseases like glaucoma, diabetic retinopathy, and cataracts are the main cause of visual impairment worldwide. With the use of the fundus images, it could be difficult for a clinician to detect eye diseases early enough. By other hand, the diagnoses of eye disease are prone to errors, challenging and labor-intensive. Thus, for the purpose of identifying various eye problems with the use of the fundus images, a system of automated ocular disease detection with computer-assisted tools is needed. Due to machine learning (ML) algorithms' advanced skills for image classification, this kind of system is feasible. An essential area of artificial intelligence)AI (is machine learning. Ophthalmologists will soon be able to deliver accurate diagnoses and support individualized healthcare thanks to the general capacity of machine learning to automatically identify, find, and grade pathological aspects in ocular disorders. This work presents a ML-based method for targeted ocular detection. The Ocular Disease Intelligent Recognition (ODIR) dataset, which includes 5,000 images of 8 different fundus types, was classified using machine learning methods. Various ocular diseases are represented by these classes. In this study, the dataset was divided into 70% training data and 30% test data, and preprocessing operations were performed on all images starting from color image conversion to grayscale, histogram equalization, BLUR, and resizing operation. The feature extraction represents the next phase in this study ,two algorithms are applied to perform the extraction of features which includes: SIFT(Scale-invariant feature transform) and GLCM(Gray Level Co-occurrence Matrix), ODIR dataset is then subjected to the classification techniques Naïve Bayes, Decision Tree, Random Forest, and K-nearest Neighbor. This study achieved the highest accuracy for binary classification (abnormal and normal) which is 75% (NB algorithm), 62% (RF algorithm), 53% (KNN algorithm), 51% (DT algorithm) and achieved the highest accuracy for multiclass classification (types of eye diseases) which is 88% (RF algorithm), 61% (KNN algorithm) 42% (NB algorithm), and 39% (DT algorithm).

Assessment of Narrow Band Imaging Algorithm for Video Capsule Endoscopy Based on Decorrelated Color Space for Esophageal Cancer.

Video capsule endoscopy (VCE) is increasingly used to decrease discomfort among patients owing to its small size. However, VCE has a major drawback of not having narrow band imaging (NBI) functionality. The current VCE has the traditional white light imaging (WLI) only, which has poor performance in the computer-aided detection (CAD) of different types of cancer compared to NBI. Specific cancers, such as esophageal cancer (EC), do not exhibit any early biomarkers, making their early detection difficult. In most cases, the symptoms are unnoticeable, and EC is diagnosed only in later stages, making its 5-year survival rate below 20% on average. NBI filters provide particular wavelengths that increase the contrast and enhance certain features of the mucosa, thereby enabling early identification of EC. However, VCE does not have a slot for NBI functionality because its size cannot be increased. Hence, NBI image conversion from WLI can presently only be achieved in post-processing. In this study, a complete arithmetic assessment of the decorrelated color space was conducted to generate NBI images from WLI images for VCE of the esophagus. Three parameters, structural similarity index metric (SSIM), entropy, and peak-signal-to-noise ratio (PSNR), were used to assess the simulated NBI images. Results show the good performance of the NBI image reproduction method with SSIM, entropy difference, and PSNR values of 93.215%, 4.360, and 28.064 dB, respectively.

Gray-to-color image conversion in the classification of breast lesions on ultrasound using pre-trained deep neural networks.

Breast ultrasound (BUS) image classification in benign and malignant classes is often based on pre-trained convolutional neural networks (CNNs) to cope with small-sized training data. Nevertheless, BUS images are single-channel gray-level images, whereas pre-trained CNNs learned from color images with red, green, and blue (RGB) components. Thus, a gray-to-color conversion method is applied to fit the BUS image to the CNN's input layer size. This paper evaluates 13 gray-to-color conversion methods proposed in the literature that follow three strategies: replicating the gray-level image to all RGB channels, decomposing the image to enhance inherent information like the lesion's texture and morphology, and learning a matching layer. Besides, we introduce an image decomposition method based on the lesion's structural information to describe its inner and outer complexity. These gray-to-color conversion methods are evaluated under the same experimental framework using a pre-trained CNN architecture named ResNet-18 and a BUS dataset with more than 3000 images. In addition, the Matthews correlation coefficient (MCC), sensitivity (SEN), and specificity (SPE) measure the classification performance. The experimental results show that decomposition methods outperform replication and learning-based methods when using information from the lesion's binary mask (obtained from a segmentation method), reaching an MCC value greater than0.70 and specificity up to0.92, although the sensitivity is about0.80. On the other hand, regarding the proposed method, the trade-off between sensitivity and specificity is better balanced, obtaining about0.88 for both indices and an MCC of0.73. This study contributes to the objective assessment of different gray-to-color conversion approaches in classifying breast lesions, revealing that mask-based decomposition methods improve classification performance. Besides, the proposed method based on structural information improves the sensitivity, obtaining more reliable classification results on malignant cases and potentially benefiting clinical practice.

WSIC: a Python package and command-line interface for fast whole slide image conversion.

Whole slide images (WSIs) are multi-gigapixel images of tissue sections, which are used in digital and computational pathology workflows. WSI datasets are commonly heterogeneous collections of proprietary or niche specialized formats which are challenging to handle. This note describes an open-source Python application for efficiently converting between WSI formats, including common, open, and emerging cloud-friendly formats. WSIC is a software tool that can quickly convert WSI files across various formats. It has a high performance and maintains the resolution metadata of the original images. WSIC is ideal for pre-processing large-scale WSI datasets with different file types. Source code is available on GitHub at https://github.com/John-P/wsic/ under a permissive licence. WSIC is also available as a package on PyPI at https://pypi.org/project/WSIC/.

The role of parametric feature maps to correct different volume of interest sizes: an in vivo liver MRI study

BackgroundDifferent volume of interest (VOI) sizes influence radiomic features. This study examined if translating images into feature maps before feature sampling could compensate for these effects in liver magnetic resonance imaging (MRI).MethodsT1- and T2-weighted sequences from three different scanners (two 3-T scanners, one 1.5-T scanner) of 66 patients with normal abdominal MRI were included retrospectively. Three differently sized VOIs (10, 20, and 30 mm in diameter) were drawn in the liver parenchyma (right lobe), excluding adjacent structures. Ninety-three features were extracted conventionally using PyRadiomics. All images were also converted to 93 parametric feature maps using a pretested software. Agreement between the three VOI sizes was assessed with overall concordance correlation coefficients (OCCCs), while OCCCs > 0.85 were rated reproducible. OCCCs were calculated twice: for the VOI sizes of 10, 20, and 30 mm and for those of 20 and 30 mm.ResultsWhen extracted from original images, only 4 out of the 93 features were reproducible across all VOI sizes in T1- and T2-weighted images. When the smallest VOI was excluded, 5 features (T1-weighted) and 7 features (T2-weighted) were reproducible. Extraction from parametric maps increased the number of reproducible features to 9 (T1- and T2-weighted) across all VOIs. Excluding the 10-mm VOI, reproducibility improved to 16 (T1-weighted) and 55 features (T2-weighted). The stability of all other features also increased in feature maps.ConclusionsTranslating images into parametric maps before feature extraction improves reproducibility across different VOI sizes in normal liver MRI.Relevance statementThe size of the segmented VOI influences the feature quantity of radiomics, while software-based conversion of images into parametric feature maps before feature sampling improves reproducibility across different VOI sizes in MRI of normal liver tissue.Key points• Parametric feature maps can compensate for different VOI sizes.• The effect seems dependent on the VOI sizes and the MRI sequence.• Feature maps can visualize features throughout the entire image stack.Graphical

Using RegGAN to generate synthetic CT images from CBCT images acquired with different linear accelerators

BackgroundThe goal was to investigate the feasibility of the registration generative adversarial network (RegGAN) model in image conversion for performing adaptive radiation therapy on the head and neck and its stability under different cone beam computed tomography (CBCT) models.MethodsA total of 100 CBCT and CT images of patients diagnosed with head and neck tumors were utilized for the training phase, whereas the testing phase involved 40 distinct patients obtained from four different linear accelerators. The RegGAN model was trained and tested to evaluate its performance. The generated synthetic CT (sCT) image quality was compared to that of planning CT (pCT) images by employing metrics such as the mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). Moreover, the radiation therapy plan was uniformly applied to both the sCT and pCT images to analyze the planning target volume (PTV) dose statistics and calculate the dose difference rate, reinforcing the model’s accuracy.ResultsThe generated sCT images had good image quality, and no significant differences were observed among the different CBCT modes. The conversion effect achieved for Synergy was the best, and the MAE decreased from 231.3 ± 55.48 to 45.63 ± 10.78; the PSNR increased from 19.40 ± 1.46 to 26.75 ± 1.32; the SSIM increased from 0.82 ± 0.02 to 0.85 ± 0.04. The quality improvement effect achieved for sCT image synthesis based on RegGAN was obvious, and no significant sCT synthesis differences were observed among different accelerators.ConclusionThe sCT images generated by the RegGAN model had high image quality, and the RegGAN model exhibited a strong generalization ability across different accelerators, enabling its outputs to be used as reference images for performing adaptive radiation therapy on the head and neck.

Improving radiomics reproducibility using deep learning-based image conversion of CT reconstruction algorithms in hepatocellular carcinoma patients.

CT reconstruction algorithms affect radiomics reproducibility. In this study, we evaluate the effect of deep learning-based image conversion on CT reconstruction algorithms. This study included 78 hepatocellular carcinoma (HCC) patients who underwent four-phase liver CTs comprising non-contrast, late arterial (LAP), portal venous (PVP), and delayed phase (DP), reconstructed using both filtered back projection (FBP) and advanced modeled iterative reconstruction (ADMIRE). PVP images were used to train a convolutional neural network (CNN) model to convert images from FBP to ADMIRE and vice versa. LAP, PVP, and DP images were used for validation and testing. Radiomic features were extracted for each patient with a semi-automatic segmentation tool. We used concordance correlation coefficients (CCCs) to evaluate the radiomics reproducibility for original FBP (oFBP) vs. original ADMIRE (oADMIRE), oFBP vs. converted FBP (cFBP), and oADMIRE vs. converted ADMIRE (cADMIRE). In the test group including 30 patients, the CCC and proportion of reproducible features (CCC ≥ 0.85) for oFBP vs. oADMIRE were 0.65 and 32.9% (524/1595) for LAP, 0.65 and 35.9% (573/1595) for PVP, and 0.69 and 43.8% (699/1595) for DP. For oFBP vs. cFBP, the values increased to 0.92 and 83.9% (1339/1595) for LAP, 0.89 and 71.0% (1133/1595) for PVP, and 0.90 and 79.7% (1271/1595) for DP. Similarly, for oADMIRE vs. cADMIRE, the values increased to 0.87 and 68.1% (1086/1595) for LAP, 0.91 and 82.1% (1309/1595) for PVP, and 0.89 and 76.2% (1216/1595) for DP. CNN-based image conversion between CT reconstruction algorithms improved the radiomics reproducibility of HCCs. This study demonstrates that using a CNN-based image conversion technique significantly improves the reproducibility of radiomic features in HCCs, highlighting its potential for enhancing radiomics research in HCC patients. Radiomics reproducibility of HCC was improved via CNN-based image conversion between two different CT reconstruction algorithms. This is the first clinical study to demonstrate improvements across a range of radiomic features in HCC patients. This study promotes the reproducibility and generalizability of different CT reconstruction algorithms in radiomics research.

PUPC-GANs: A Novel Image Conversion Model using Modified CycleGANs in Healthcare

Introduction: Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) both have their areas of specialty in the medical imaging world. MRI is considered to be a safer modality as it exploits the magnetic properties of the hydrogen nucleus. Whereas a CT scan uses multiple X-rays, which is known to contribute to carcinogenesis and is associated with affecting the patient's health. Methods: In scenarios, such as radiation therapy, where both MRI and CT are required for medical treatment, a unique approach to getting both scans would be to obtain MRI and generate a CT scan from it. Current deep learning methods for MRI to CT synthesis purely use either paired data or unpaired data. Models trained with paired data suffer due to a lack of availability of wellaligned data. Results: Training with unpaired data might generate visually realistic images, although it still does not guarantee good accuracy. To overcome this, we proposed a new model called PUPCGANs (Paired Unpaired CycleGANs), based on CycleGANs (Cycle-Consistent Adversarial Networks). Conclusion: This model is capable of learning transformations utilizing both paired and unpaired data. To support this, a paired loss is introduced. Comparing MAE, MSE, NRMSE, PSNR, and SSIM metrics, PUPC-GANs outperform CycleGANs.

Deep Learning Modeling of Cardiac Arrhythmia Classification on Information Feature Fusion Image with Attention Mechanism.

The electrocardiogram (ECG) is a crucial tool for assessing cardiac health in humans. Aiming to enhance the accuracy of ECG signal classification, a novel approach is proposed based on relative position matrix and deep learning network information features for the classification task in this paper. The approach improves the feature extraction capability and classification accuracy via techniques of image conversion and attention mechanism. In terms of the recognition strategy, this paper presents an image conversion using relative position matrix information. This information is utilized to describe the relative spatial relationships between different waveforms, and the image identification is successfully applied to the Gam-Resnet18 deep learning network model with a transfer learning concept for classification. Ultimately, this model achieved a total accuracy of 99.30%, an average positive prediction rate of 98.76%, a sensitivity of 98.90%, and a specificity of 99.84% with the relative position matrix approach. To evaluate the effectiveness of the proposed method, different image conversion techniques are compared on the test set. The experimental results demonstrate that the relative position matrix information can better reflect the differences between various types of arrhythmias, thereby improving the accuracy and stability of classification.

Mixture design and multivariate image analysis to monitor the colour of strawberry yoghurt purée

Food colour is a commercial added value, since it represents the first appealing factor for consumers. In this context, this study was aimed at evaluating the effect of strawberry yoghurt purée (SYP) formulation on the corresponding colour and on its variation over time, which is mainly due to degradation and browning phenomena. To this aim, a combined approach was used that included mixture design and multivariate analysis of RGB images. Strawberry purée, sugar, lemon juice and two types of thickener were mixed in different proportions by I-optimal mixture design to obtain 44 SYP formulations. The samples were subjected to light and temperature stress conditions for five weeks; during this time the RGB images of the samples were acquired using a flatbed scanner, along with the images of the corresponding control samples. The dimensionality of the acquired images was reduced by two different approaches: i) the conversion of images into signals, namely colourgrams, which can be seen as the colour fingerprint of the imaged samples, and ii) the calculation of the median values of various colour-related parameters. The colourgrams dataset was then subjected to exploratory data analysis using Principal Component Analysis, while the median values of colour-related parameters were analysed using Response Surface Methodology and Partial Least Squares-Discriminant Analysis. The aim of data analysis was both to find the best colour parameters to describe colour variability over time, and to investigate the cause-effect relationship between mixture proportions and colour response. The results highlighted that, among the considered colour parameters, relative green (i.e., the ratio of green to lightness) and red could be used to monitor colour changes. Colour variation due to stress conditions was more pronounced for samples with a high percentage of strawberry purée, and the type of thickener also affected the colour degradation kinetics.

Fourier Ptychographic Microscopic Reconstruction Method Based on Residual Hybrid Attention Network.

Fourier ptychographic microscopy (FPM) is a novel technique for computing microimaging that allows imaging of samples such as pathology sections. However, due to the influence of systematic errors and noise, the quality of reconstructed images using FPM is often poor, and the reconstruction efficiency is low. In this paper, a hybrid attention network that combines spatial attention mechanisms with channel attention mechanisms into FPM reconstruction is introduced. Spatial attention can extract fine spatial features and reduce redundant features while, combined with residual channel attention, it adaptively readjusts the hierarchical features to achieve the conversion of low-resolution complex amplitude images to high-resolution ones. The high-resolution images generated by this method can be applied to medical cell recognition, segmentation, classification, and other related studies, providing a better foundation for relevant research.

Adaptable 2D to 3D Stereo Vision Image Conversion Based on a Deep Convolutional Neural Network and Fast Inpaint Algorithm.

Algorithms for converting 2D to 3D are gaining importance following the hiatus brought about by the discontinuation of 3D TV production; this is due to the high availability and popularity of virtual reality systems that use stereo vision. In this paper, several depth image-based rendering (DIBR) approaches using state-of-the-art single-frame depth generation neural networks and inpaint algorithms are proposed and validated, including a novel very fast inpaint (FAST). FAST significantly exceeds the speed of currently used inpaint algorithms by reducing computational complexity, without degrading the quality of the resulting image. The role of the inpaint algorithm is to fill in missing pixels in the stereo pair estimated by DIBR. Missing estimated pixels appear at the boundaries of areas that differ significantly in their estimated distance from the observer. In addition, we propose parameterizing DIBR using a singular, easy-to-interpret adaptable parameter that can be adjusted online according to the preferences of the user who views the visualization. This single parameter governs both the camera parameters and the maximum binocular disparity. The proposed solutions are also compared with a fully automatic 2D to 3D mapping solution. The algorithm proposed in this work, which features intuitive disparity steering, the foundational deep neural network MiDaS, and the FAST inpaint algorithm, received considerable acclaim from evaluators. The mean absolute error of the proposed solution does not contain statistically significant differences from state-of-the-art approaches like Deep3D and other DIBR-based approaches using different inpaint functions. Since both the source codes and the generated videos are available for download, all experiments can be reproduced, and one can apply our algorithm to any selected video or single image to convert it.