Mathematical Morphology Research Articles

A Heat Method for Generalized Signed Distance

We introduce a method for approximating the signed distance function (SDF) of geometry corrupted by holes, noise, or self-intersections. The method implicitly defines a completed version of the shape, rather than explicitly repairing the given input. Our starting point is a modified version of the heat method for geodesic distance, which diffuses normal vectors rather than a scalar distribution. This formulation provides robustness akin to generalized winding numbers (GWN) , but provides distance function rather than just an inside/outside classification. Our formulation also offers several features not common to classic distance algorithms, such as the ability to simultaneously fit multiple level sets, a notion of distance for geometry that does not topologically bound any region, and the ability to mix and match signed and unsigned distance. The method can be applied in any dimension and to any spatial discretization, including triangle meshes, tet meshes, point clouds, polygonal meshes, voxelized surfaces, and regular grids. We evaluate the method on several challenging examples, implementing normal offsets and other morphological operations directly on imperfect curve and surface data. In many cases we also obtain an inside/outside classification dramatically more robust than the one obtained provided by GWN.

An image processing approach for fatigue crack identification in cellulose acetate replicas

The cellulose acetate replication technique is an important method for studying material fatigue. However, extracting accurate information from pictures of cellulose replicas poses challenges because of distortions and numerous artifacts. This paper presents an image processing procedure for effective fatigue crack identification in plastic replicas. The approach employs thresholding, adaptive Gaussian thresholding, and Otsu binarization to convert gray-scale images into binary ones, enhancing crack visibility. Morphological operations refine object shapes, and Connected Components Analysis facilitates crack identification. Despite limited data, the handcrafted feature extraction algorithm proves robust, addressing challenges. The algorithm shows efficacy in detecting cracks as small as 30 μm, even in the presence of cellulose replication artifacts. The results highlight ability to capture significant cracks’ orientation, length, and growth stages, essential for understanding fatigue mechanisms. Analysis of results, especially evaluation metrics encompassing false positives and false negatives, provides a comprehensive understanding of the algorithm’s strengths and limitations. The proposed tool is available on GitHub.

Solving Advanced Task-Specific Problems in Measurement Sciences with Generative AI.

The Generative Pre-Trained Transformer known as ChatGPT-4 has undergone extensive pretraining on a diverse data set, enabling it to generate coherent and contextually relevant text based on the input it receives. This capability allows it to perform tasks from answering questions and has attracted significant interest in material sciences, synthetic chemistry, and drug discovery. In this work, we posed four advanced task-specific problems to ChatGPT, which were recently published in leading journals for topics in analytical chemistry, spectroscopy, bioimage super-resolution, and electrochemistry. ChatGPT-4 successfully implemented the four ideas after assigning the "persona" to the AI and posing targeted questions. We show two cases where "unguided" ChatGPT could complete the assignments with minimal human direction. The construction of a microwave spectrum from a free induction curve and super-resolution of bioimages was accomplished using this approach. Two other specific tasks, correcting a complex baseline with morphological operations of set theory and estimating the diffusion current, required additional input, e.g., equations and specific directions from the user. In each case, the MATLAB code was eventually generated by ChatGPT-4 even when the original authors did not provide any code themselves. We show that a validation test must be implemented to detect and correct mistakes made by ChatGPT-4, followed by feedback correction. These approaches will pave the way for open and transparent science and eliminate the black boxes in measurement science when it comes to advanced data processing.

Jet classification using high-level features from anatomy of top jets

Recent advancements in deep learning models have significantly enhanced jet classification performance by analyzing low-level features (LLFs). However, this approach often leads to less interpretable models, emphasizing the need to understand the decision-making process and to identify the high-level features (HLFs) crucial for explaining jet classification. To address this, we consider the top jet tagging problems and introduce an analysis model (AM) that analyzes selected HLFs designed to capture important features of top jets. Our AM mainly consists of the following three modules: a relation network analyzing two-point energy correlations, mathematical morphology and Minkowski functionals for generalizing jet constituent multiplicities, and a recursive neural network analyzing subjet constituent multiplicity to enhance sensitivity to subjet color charges. We demonstrate that our AM achieves performance comparable to the Particle Transformer (ParT) while requiring fewer computational resources in a comparison of top jet tagging using jets simulated at the hadronic calorimeter angular resolution scale. Furthermore, as a more constrained architecture than ParT, the AM exhibits smaller training uncertainties because of the bias-variance tradeoff. We also compare the information content of AM and ParT by decorrelating the features already learned by AM. Lastly, we briefly comment on the results of AM with finer angular resolution inputs.

Ship Detection in SAR Images Based on Steady CFAR Detector and Knowledge-Oriented GBDT Classifier

Ship detection is a significant issue in remote sensing based on Synthetic Aperture Radar (SAR). This paper combines the advantages of a steady constant false alarm rate (CFAR) detector and a knowledge-oriented Gradient Boosting Decision Tree (GBDT) classifier to achieve the location and the classification of ship candidates. The steady CFAR detector smooths the image by a moving-average filter and models the probability distribution of the smoothed clutter as a Gaussian distribution. The mean and the standard deviation of the Gaussian distribution are estimated according to the left half of the histogram to remove the effect of land, ships, and other targets. From the Gaussian distribution and a preset constant false alarm rate, a threshold is obtained to segment land, ships, and other targets from the clutter. Then, a series of morphological operations are introduced to eliminate land and extract ships and other targets, and an active contour algorithm is utilized to refine ships and other targets. Finally, ships are recognized from other targets by a knowledge-oriented GBDT classifier. Based on the brain-like ship-recognition process, we change the way of the decision-tree generation and achieve a higher classification performance than the original GBDT. The results on the AIRSARShip-1.0 dataset demonstrate that this scheme has a competitive performance against deep learning, especially in the detection of offshore ships.

Cardboard packaging minimization: Autonomous box selection by RGB-depth vision system and complementary deep learning classification

Amidst the dramatic expansion of online shopping, wasted cardboard packaging has become a significant challenge in modern-day society. In this paper, we propose an innovative approach to address the issue of box packaging waste by efficiently selecting an optimal cardboard box for a set of items. Employing depth vision and deep learning classification techniques, the proposed system analyzes depth images to compute an optimal cuboid for unpackaged items while accounting for fragility characteristics. The system, facilitated by two Intel RealSense RGB-D cameras, first captures the overhead and sideview images to determine the dimensions of an unknown object. Then, the developed vision system utilizes averaging and morphological opening filters to denoise the acquired images, calculates the difference between the background image and object image, and employs thresholding by Otsu’s algorithm to find the minimum cuboid of the irregular object. After, a two-step deep learning model is used to determine the general category and characteristics of an object, considering factors, such as fragility, that may necessitate wrapping or separate packaging. Finally, a modified largest area first fit algorithm uses the outputted dimensions for irregular-shaped objects and packaged objects to determine the optimal fitting box from the standard Amazon box catalog. The computer simulation shows that the proposed method can be implemented in a cardboard packaging warehouse for optimal box selection, effectively minimizing cardboard waste.

Oil painting teaching design based on the mobile platform in higher art education

To improve the current oil painting teaching mode in Chinese universities, this study combines deep learning technology and artificial intelligence technology to explore oil painting teaching. Firstly, the research status of individualized education and related research on image classification based on brush features are analyzed. Secondly, based on a convolutional neural network, mathematical morphology, and support vector machine, the oil painting classification model is constructed, in which the extracted features include color and brush features. Moreover, based on artificial intelligence technology and individualized education theory, a personalized intelligent oil painting teaching framework is built. Finally, the performance of the intelligent oil painting classification model is evaluated, and the content of the personalized intelligent oil painting teaching framework is explained. The results show that the average classification accuracy of oil painting is 90.25% when only brush features are extracted. When only color features are extracted, the average classification accuracy is over 89%. When the two features are extracted, the average accuracy of the oil painting classification model reaches 94.03%. Iterative Dichotomiser3, decision tree C4.5, and support vector machines have an average classification accuracy of 82.24%, 83.57%, and 94.03%. The training speed of epochs data with size 50 is faster than that of epochs original data with size 100, but the accuracy is slightly decreased. The personalized oil painting teaching system helps students adjust their learning plans according to their conditions, avoid learning repetitive content, and ultimately improve students' learning efficiency. Compared with other studies, this study obtains a good oil painting classification model and a personalized oil painting education system that plays a positive role in oil painting teaching. This study has laid the foundation for the development of higher art education.

Deep learning-based deformable image registration with bilateral pyramid to align pre-operative and follow-up magnetic resonance imaging (MRI) scans.

The evaluation of brain tumor recurrence after surgery is based on the comparison between tumor regions on pre-operative and follow-up magnetic resonance imaging (MRI) scans in clinical practice. Accurate alignment of MRI scans is important in this evaluation process. However, existing methods often fail to yield accurate alignment due to substantial appearance and shape changes of tumor regions. The study aimed to improve this misalignment situation through multimodal information and compensation for shape changes. In this work, a deep learning-based deformation registration method using bilateral pyramid to create multi-scale image features was developed. Moreover, morphology operations were employed to build correspondence between the surgical resection on the follow-up and pre-operative MRI scans. Compared with baseline methods, the proposed method achieved the lowest mean absolute error of 1.82 mm on the public BraTS-Reg 2022 dataset. The results suggest that the proposed method is potentially useful for evaluating tumor recurrence after surgery. We effectively verified its ability to extract and integrate the information of the second modality, and also revealed the micro representation of tumor recurrence. This study can assist doctors in registering multiple sequence images of patients, observing lesions and surrounding areas, analyzing and processing them, and guiding doctors in their treatment plans.

Visualization and Segmentation of Lung Tissue in DICOM-format CT Images

Abstract In this project, two tools were developed as a preliminary step towards the creation of future Computer-Aided Diagnosis systems for the automatic detection of lung diseases. The first methodology aimed to extract information from DICOM-format files using Python and the Jupyter Notebook programming environment. The implemented process enables the generation of images in various anatomical planes, using the pixel matrix in Hounsfield units. Additionally, a custom tool was developed for anonymizing and visualizing file information. The techniques employed are independent of the grayscale image generated and are not reliant on the type of window used. The second tool introduces a lung segmentation technique for chest CT images. The segmentation uses the pixel matrix in Hounsfield units to initially identify lung tissue based on its linear X-ray attenuation. Subsequently, the Watershed algorithm based on markers is employed as the primary foundation of the technique. Various morphological operations and transformations on axial slices are applied, resulting in successful lung segmentation.

A quantitative image analysis platform for assessing trophoblast differentiation

Immunofluorescence microscopy is extensively used in characterization of trophoblast differentiation in vitro. However, such data is primarily used to confirm the presence of protein markers or qualitatively compare levels of protein markers across experimental conditions. Imaging data, when processed and analyzed appropriately can provide quantitative and spatial information, and provide biological insight. Towards this end, here we present MATroph, an open-source MATLAB-based computational tool to process images generated by immunofluorescent microscopy. MATroph automatically executes a series of image processing operations, including the classification of red, blue, and green channels from images, background extraction, morphological operations, and image filtering. From the isolated blue channels corresponding to nuclear staining, this tool generates numerical values for cell number. Additionally, relative levels and spatial location of proteins are obtained by mapping red and green channel pixels to blue pixels by assigning minimum pixel distance between the blue and other color objects. Thus, this tool provides information about intracellular protein accumulation areas. Additionally, this tool can also classify cells as single cells or part of colonies, and extract information on protein levels for each; this is particularly useful for quantitative studies on extravillous trophoblast maturation. We provide a user-guide to analyze the relative levels of markers relevant to human trophoblast stem cell self-renewal and differentiation. Importantly, MATroph is composed of a simple MATLAB algorithm, and its implementation requires minimal expertise in programming.

Statistic and morphological image processing for automated lung cancer identification

Statistic and morphological image processing for automated lung cancer identification

Earlier smart prediction of diabetic retinopathy from fundus image under innovative ResNet optimization maneuver

AbstractDiabetic retinopathy (DR) is a complication of diabetes that causes blindness and the early detection of diabetics using retinopathy images remains a challenging task. Hence, a novel, earlier smart prediction of diabetic retinopathy from fundus image under Innovative ResNet Optimization is introduced to effectively detect the earlier stage of DR from Fundus image. Initially, the fundus image is scaled during preprocessing and converted into a grayscale format. As the existing studies neglect some deserving unique features that are crucial for predicting the earliest signs of DR, a novel Fractional Radon Transform with Visibility Graph is introduced for extracting the novel features such as microaneurysms count, dot and blot hemorrhages count, statistical measures, and retinal layer thickness, in which a Generalized Cosine Fractional Radon Transform is used to capture the image’s fine-scale texture information thereby effectively capturing the statistical measures, while a weighted Horizontal Visibility Graph is made to examine the apparent spatial relationships between pixel pairs in the image based on the values of the pixels’ gray levels. Further, the existing works failed to identify the small fine dark areas that were ignored throughout the morphological opening process. In order to overcome this issue, a Morphological Black Hat Transform with Optimized ResNet Algorithm is implemented, where segmentation is made through Enriched Black Hat Transform-based Morphological operation to identify fine dark regions among the pixels inside the eye samples, and the classification is done by using ResNet-driven S-GOA (Socio Grasshopper Optimization Algorithm), to optimally predict the stages of DR. The result obtained showed that the proposed model outperforms existing techniques with high performance and accuracy.

Pneumonia Detection through Deep Learning: A Comparative Exploration of Classification and Segmentation Strategies

The Convolution Neural Network (CNN) algorithm is one of the most widely used methods for identifying and categorizing lung cancer. This paper covers the most suitable architecture and CNN algorithms for lung cancer and pneumonia deduction and classification. The main contributions to the diagnosis and classification of lung cancer with four steps are Nonlinear transfer learning framework (NLTF), Hierarchical Feature Mapping (HFM), Lifelong Partial Dissection (LPD), and Deep Lifelong Convolutional Neural Network (DLCNN). The application of non-local total fuzzy (NLTF) filtering removes various categories of noise after lung CT imageries and enhances cancer areas. The application of Hybrid Fuzzy Morphology (HFM) constructed segmentation to minimize the region of interest (ROI) for cancer using morphology opening and closing processes. Extraction of traits unique to each disease employing Lung Parenchyma Division (LPD) and extraction of deep seismic features using the Geometric Optimal Algorithm (GOA). Training and testing the proposed Deep Learning Convolutional Neural Network (DLCNN) model using the extracted features to classify benign, malignant lung cancers and Recent advancements in deep learning methods have shown accurate results in the investigation and diagnosis of medical image data, including the detection of pneumonia.

A Novel Two-Stage Approach for Automatic Extraction and Multi-View Generation of Litchis

Obtaining consistent multi-view images of litchis is crucial for various litchi-related studies, such as data augmentation and 3D reconstruction. This paper proposes a two-stage model that integrates the Mask2Former semantic segmentation network with the Wonder3D multi-view generation network. This integration aims to accurately segment and extract litchis from complex backgrounds and generate consistent multi-view images of previously unseen litchis. In the first stage, the Mask2Former model is utilized to predict litchi masks, enabling the extraction of litchis from complex backgrounds. To further enhance the accuracy of litchi branch extraction, we propose a novel method that combines the predicted masks with morphological operations and the HSV color space. This approach ensures accurate extraction of litchi branches even when the semantic segmentation model’s prediction accuracy is not high. In the second stage, the segmented and extracted litchi images are passed as input into the Wonder3D network to generate multi-view of the litchis. After comparing different semantic segmentation and multi-view synthesis networks, the Mask2Former and Wonder3D networks demonstrated the best performance. The Mask2Former network achieved a mean Intersection over Union (mIoU) of 79.79% and a mean pixel accuracy (mPA) of 85.82%. The Wonder3D network achieved a peak signal-to-noise ratio (PSNR) of 18.89 dB, a structural similarity index (SSIM) of 0.8199, and a learned perceptual image patch similarity (LPIPS) of 0.114. Combining the Mask2Former model with the Wonder3D network resulted in an increase in PSNR and SSIM scores by 0.21 dB and 0.0121, respectively, and a decrease in LPIPS by 0.064 compared to using the Wonder3D model alone. Therefore, the proposed two-stage model effectively achieves automatic extraction and multi-view generation of litchis with high accuracy.

Unsupervised learning-enabled pulsed infrared thermographic microscopy of subsurface defects in stainless steel

Metallic structures produced with laser powder bed fusion (LPBF) additive manufacturing method (AM) frequently contain microscopic porosity defects, with typical approximate size distribution from one to 100 microns. Presence of such defects could lead to premature failure of the structure. In principle, structural integrity assessment of LPBF metals can be accomplished with nondestructive evaluation (NDE). Pulsed infrared thermography (PIT) is a non-contact, one-sided NDE method that allows for imaging of internal defects in arbitrary size and shape metallic structures using heat transfer. PIT imaging is performed using compact instrumentation consisting of a flash lamp for deposition of a heat pulse, and a fast frame infrared (IR) camera for measuring surface temperature transients. However, limitations of imaging resolution with PIT include blurring due to heat diffusion, sensitivity limit of the IR camera. We demonstrate enhancement of PIT imaging capability with unsupervised learning (UL), which enables PIT microscopy of subsurface defects in high strength corrosion resistant stainless steel 316 alloy. PIT images were processed with UL spatial–temporal separation-based clustering segmentation (STSCS) algorithm, refined by morphology image processing methods to enhance visibility of defects. The STSCS algorithm starts with wavelet decomposition to spatially de-noise thermograms, followed by UL principal component analysis (PCA), fine-tuning optimization, and neural learning-based independent component analysis (ICA) algorithms to temporally compress de-noised thermograms. The compressed thermograms were further processed with UL-based graph thresholding K-means clustering algorithm for defects segmentation. The STSCS algorithm also includes online learning feature for efficient re-training of the model with new data. For this study, metallic specimens with calibrated microscopic flat bottom hole defects, with diameters in the range from 203 to 76 µm, were produced using electro discharge machining (EDM) drilling. While the raw thermograms do not show any material defects, using STSCS algorithm to process PIT images reveals defects as small as 101 µm in diameter. To the best of our knowledge, this is the smallest reported size of a sub-surface defect in a metal imaged with PIT, which demonstrates the PIT capability of detecting defects in the size range relevant to quality control requirements of LPBF-printed high-strength metals.

An enhanced pattern detection and segmentation of brain tumors in MRI images using deep learning technique.

Neuroscience is a swiftly progressing discipline that aims to unravel the intricate workings of the human brain and mind. Brain tumors, ranging from non-cancerous to malignant forms, pose a significant diagnostic challenge due to the presence of more than 100 distinct types. Effective treatment hinges on the precise detection and segmentation of these tumors early. We introduce a cutting-edge deep-learning approach employing a binary convolutional neural network (BCNN) to address this. This method is employed to segment the 10 most prevalent brain tumor types and is a significant improvement over current models restricted to only segmenting four types. Our methodology begins with acquiring MRI images, followed by a detailed preprocessing stage where images undergo binary conversion using an adaptive thresholding method and morphological operations. This prepares the data for the next step, which is segmentation. The segmentation identifies the tumor type and classifies it according to its grade (Grade I to Grade IV) and differentiates it from healthy brain tissue. We also curated a unique dataset comprising 6,600 brain MRI images specifically for this study. The overall performance achieved by our proposed model is 99.36%. The effectiveness of our model is underscored by its remarkable performance metrics, achieving 99.40% accuracy, 99.32% precision, 99.45% recall, and a 99.28% F-Measure in segmentation tasks.

Unobtrusive measurement of gait parameters using seismographs: An observational study

Analyzing irregularities in walking patterns helps detect human locomotion abnormalities that can signal health changes. Traditional observation-based assessments have limitations due to subjective biases and capture only a single time point. Ambient and wearable sensor technologies allow continuous and objective locomotion monitoring but face challenges due to the need for specialized expertise and user compliance. This work proposes a seismograph-based algorithm for quantifying human gait, incorporating a step extraction algorithm derived from mathematical morphologies, with the goal of achieving the accuracy of clinical reference systems. To evaluate our method, we compared the gait parameters of 50 healthy participants, as recorded by seismographs, and those obtained from reference systems (a pressure-sensitive walkway and a camera system). Participants performed four walking tests, including traversing a walkway and completing the timed up-and-go (TUG) test. In our findings, we observed linear relationships with strong positive correlations (R2 > 0.9) and tight 95% confidence intervals for all gait parameters (step time, cycle time, ambulation time, and cadence). We demonstrated that clinical gait parameters and TUG mobility test timings can be accurately derived from seismographic signals, with our method exhibiting no significant differences from established clinical reference systems.

Applications of mathematical morphology operators in civil infrastructures

Civil infrastructures require a permanent attention and maintenance from the moment of commissioning to moment of demolition. One important aspect which is mandatory to be taken into consideration is crack detection. Cracks can appear during the lifetime of the civil infrastructure and require specialized personal for assessment. Depending of the civil infrastructure, this operation can require specialized skills (such as climbing). To overcome this issue with regards to specialized manpower, image processing is used. Nowadays, images can be easily acquired using an unmanned aircraft vehicle system known also as a drone. The main advantages of a drone for civil infrastructure image acquisition are: i) it can be operated at different heights, ii) rapid data collection, iii) cost and time savings, iv) user-friendly interface.The main purpose of our paper resides in improving the accuracy of the pre-trained neural networks when noisy images are used in civil works. Throughout our research, we used a dataset which contains three classes of images: with cracks, without cracks and with noise. To remove the noise presented in images mathematical morphology operators (MMO) are used. Our results reveal that using opening operator filter on a dataset of images which present civil infrastructure cracks outperform the results obtained using only pre-trained neural networks. In addition, the computation time is reduced.

Hand Gestures Recognition Model Using Adaptive Feature Extraction with Attention-Based Hybrid Deep Learning via Optimization Strategy

Research on continuous hand gesture recognition is motivated by applications of deaf people to provide effective communication between one another. Numerous techniques are adapted for effectively identifying the hand gesture. Moreover, the collection of data becomes a challenging task in the existing models. In some instances, hand gesture in low-resolution images becomes a complicated task. In this research work, a deep learning-based hand gesture detection model is designed using hand data points to uncover patterns that are used to convey information. Initially, hand gesture images are obtained from public sources. The collected inputs are preprocessed through Contrast-Limited Adaptive Histogram Equalization and filtering to eliminate the unnecessary blurs in the images. The preprocessed images undergo hand segmentation using four methods color space transformation, skin color detection, active contour, and morphological operation. The segmented image is subjected to data point feature extraction, where the Adaptive Weighted Scale-Invariant Feature Transform is utilized for further enhancement. The hand data point-extracted features are given to the recognition of hand gestures with the support of an attention-based hybrid network, where the Attention-based Hybrid 1D Convolutional Neural Network with Recurrent Neural Network recognizes the hand gestures from the hand data points. In the hybridization network, the values are optimized with the help of the investigated Adaptive Dandelion White Shark Optimizer to enhance recognition effectiveness. The test results are validated with the existing hand gesture recognition models using diverse evaluation metrics. The findings of the recommended method show 97% and 99% in terms of accuracy and NPV. Thus, the developed model is validated to outperform significant performance rather than the existing models.

Enhancing automated vehicle identification by integrating YOLO v8 and OCR techniques for high-precision license plate detection and recognition

Vehicle identification systems are vital components that enable many aspects of contemporary life, such as safety, trade, transit, and law enforcement. They improve community and individual well-being by increasing vehicle management, security, and transparency. These tasks entail locating and extracting license plates from images or video frames using computer vision and machine learning techniques, followed by recognizing the letters or digits on the plates. This paper proposes a new license plate detection and recognition method based on the deep learning YOLO v8 method, image processing techniques, and the OCR technique for text recognition. For this, the first step was the dataset creation, when gathering 270 images from the internet. Afterward, CVAT (Computer Vision Annotation Tool) was used to annotate the dataset, which is an open-source software platform made to make computer vision tasks easier to annotate and label images and videos. Subsequently, the newly released Yolo version, the Yolo v8, has been employed to detect the number plate area in the input image. Subsequently, after extracting the plate the k-means clustering algorithm, the thresholding techniques, and the opening morphological operation were used to enhance the image and make the characters in the license plate clearer before using OCR. The next step in this process is using the OCR technique to extract the characters. Eventually, a text file containing only the character reflecting the vehicle's country is generated. To ameliorate the efficiency of the proposed approach, several metrics were employed, namely precision, recall, F1-Score, and CLA. In addition, a comparison of the proposed method with existing techniques in the literature has been given. The suggested method obtained convincing results in both detection as well as recognition by obtaining an accuracy of 99% in detection and 98% in character recognition.