Image Thresholding Research Articles

Spatial–Temporal Binarization Method via Jointly Optimizing Diffusion Kernel and Quantization Threshold for 3-D Surface Imaging

Spatial–Temporal Binarization Method via Jointly Optimizing Diffusion Kernel and Quantization Threshold for 3-D Surface Imaging

Blockchain-Based Secure and Efficient Secret Image Sharing With Outsourcing Computation in Wireless Networks

Secret Image Sharing (SIS) is the technology that shares any given secret image by generating and distributing <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> shadow images in the way that any subset of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> shadow images can restore the secret image. However, in the existing SIS schemes, the shadow images will be easily tampered and corrupted during the communication, which will pose serious security issues. Recently, blockchain has emerged as a promising paradigm in the field of data communication and information security. To securely communicate and effectively protect the secret image data in wireless networks, we propose a Blockchain-based Secure and Efficient Secret Image Sharing (BC-SESIS) scheme with outsourcing computation in wireless networks. In the proposed BC-SESIS scheme, the shadow images are encrypted and stored in the blockchain to prevent them from being tampered and corrupted. The identity authentication-enabled smart contract is deployed to achieve the ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k, n</i> ) threshold for secret image restoring. Furthermore, to reduce the computational burden of smart contract and users, an efficient outsourcing computation method is designed to outsource the restoring task, which is securely implemented by agent miners in the encryption domain. Theoretical analysis and extensive experiments demonstrate that the BC-SESIS scheme can achieve desirable communication security and high computational efficiency in the wireless networks.

Interpreting Geometric Constructions in Artworks through Capsule Network Modeling

Abstract Interpreting the geometric structure of artworks enhances our intuitive grasp of their deeper meanings. This study employs a Capsule network model, incorporating a dynamic routing algorithm to correlate high and low-level geometric structural features of artworks. Additionally, an attention mechanism is introduced, forming a spatial attention capsule to capture the spatial context of the artwork’s geometric structure. To obtain images, a fixed-focus camera is utilized, followed by median filtering for image preprocessing and threshold segmentation using the maximum inter-class variance method to optimize recognition accuracy. The efficacy of the geometric structure recognition model, grounded in the Capsule network, is confirmed using a dataset of collected artwork images. The model achieves stability after 380 epochs, exhibiting an impressive accuracy of approximately 99.7% and a minimal loss of 0.025. Removing the attention mechanism results in a 4.06 percentage point decrease in model accuracy, whereas incorporating a dynamic routing algorithm boosts efficiency by 7.36%. Thus, the Capsule model proves highly effective in precisely recognizing and interpreting the geometric structures of artworks.

Shadow Segmentation With Image Thresholding for Describing the Harshness of Light Sources.

Light sources are usually described by luminous intensity, color temperature and color rendering index, while the harshness of the light source is often overlooked. It is also referred to as the softness or light quality and can be determined by analyzing the shadows it produces. Shadow detection is often addressed in image analysis research, but the methods usually provide solutions for removing shadows. In this research, a method is proposed for isolating shadows from test images, applying thresholding for segmentation of the shadow into umbral and penumbral regions, calculating the shadow metric, and finally calculating the final numerical evaluation of the quality of the light source, i.e., the degree of its softness or harshness. The method proved to be efficient in analyzing halogen, LED and xenon light sources in conjunction with light-shaping attachments that soften the light. The method is not influenced by the intensity of the light source and focuses exclusively on the quality of the light. The method provides a single value to describe this light property and has the potential to become a standardized method for describing the quality of light sources and light-shaping attachments.

A psychophysical evaluation of techniques for Mooney image generation.

Mooney images can contribute to our understanding of the processes involved in visual perception, because they allow a dissociation between image content and image understanding. Mooney images are generated by first smoothing and subsequently thresholding an image. In most previous studies this was performed manually, using subjective criteria for generation. This manual process could eventually be avoided by using automatic generation techniques. The field of computer image processing offers numerous techniques for image thresholding, but these are only rarely used to create Mooney images. Furthermore, there is little research on the perceptual effects of smoothing and thresholding. Therefore, in this study we investigated how the choice of different thresholding techniques and amount of smoothing affects the interpretability of Mooney images for human participants. We generated Mooney images using four different thresholding techniques, selected to represent various global thresholding methods, and, in a second experiment, parametrically varied the level of smoothing. Participants identified the concepts shown in Mooney images and rated their interpretability. Although the techniques generate physically-different Mooney images, identification performance and subjective ratings were similar across the different techniques. This indicates that finding the perfect threshold in the process of generating Mooney images is not critical for Mooney image interpretability, at least for globally-applied thresholds. The degree of smoothing applied before thresholding, on the other hand, requires more tuning depending on the noise of the original image and the desired interpretability of the resulting Mooney image. Future work in automatic Mooney image generation should pursue local thresholding techniques, where different thresholds are applied to image regions depending on the local image content.

An efficient Low Complex-Functional Link Artificial Neural Network based framework for uneven light image thresholding

An efficient Low Complex-Functional Link Artificial Neural Network based framework for uneven light image thresholding

An efficient hybrid differential evolution-golden jackal optimization algorithm for multilevel thresholding image segmentation.

Image segmentation is a crucial process in the field of image processing. Multilevel threshold segmentation is an effective image segmentation method, where an image is segmented into different regions based on multilevel thresholds for information analysis. However, the complexity of multilevel thresholding increases dramatically as the number of thresholds increases. To address this challenge, this article proposes a novel hybrid algorithm, termed differential evolution-golden jackal optimizer (DEGJO), for multilevel thresholding image segmentation using the minimum cross-entropy (MCE) as a fitness function. The DE algorithm is combined with the GJO algorithm for iterative updating of position, which enhances the search capacity of the GJO algorithm. The performance of the DEGJO algorithm is assessed on the CEC2021 benchmark function and compared with state-of-the-art optimization algorithms. Additionally, the efficacy of the proposed algorithm is evaluated by performing multilevel segmentation experiments on benchmark images. The experimental results demonstrate that the DEGJO algorithm achieves superior performance in terms of fitness values compared to other metaheuristic algorithms. Moreover, it also yields good results in quantitative performance metrics such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and feature similarity index (FSIM) measurements.

Mapping Floods during Cloudy Weather Using Radar Satellite Images

Monitoring floods using optical satellite images in winter is challenging. Because of the thickness of clouds, the electromagnetic bands used by satellites are too narrow and the resulting signals are reflected into space. The purpose of this study is to assess the potential of implementing a high-resolution synthetic aperture radar system (SAR) for the purpose of mapping floods in Jordan while the weather is cloudy. TerraSAR-X satellite was utilized to acquire images of high resolution for flood monitoring. This research employed TerraSAR-X thresholding images to identify flood-prone areas and track floods over time using time-series images. It was possible to determine the places of the landscape that have been impacted by the flood and to establish the degree of damage by conducting an analysis of the changes that have occurred in the landscape. The accuracy of the study's findings was confirmed using backscatter texture analysis on the images, which revealed a small difference between thresholding and texture analysis approaches of less than 3% in the mapped test region's flood area. While monitoring floods, it is recommended to use TerraSAR-X images, particularly in conjunction with other data sources, such as weather predictions and hydrological models. KEYWORDS: Flood mapping, Polarimetric SAR, TerraSAR-X, Texture analysis, Thresholding, Interferometric SAR

CNN segmentation of skin melanoma in pre-processed dermoscopy images

Using medical data to improve diagnosis accuracy has recently become common practice in hospitals. A modern computing environment has enabled real-time diagnosis of medical data using Convolutional Neural Networks (CNNs). To extract and evaluate skin melanoma recorded with digital dermatoscopy images (DDI), we developed a CNN segmentation framework. In this proposal, four phases are proposed: (i) DDI collection and resizing, (ii) DDI enhancement using pre-processing techniques, (iii) CNN segmentation for lesion extraction, (v) Comparing the extracted sections to the ground truth images, and (v) Verifying whether the framework is valid. Using DDI pre-processed with (i) Traditional procedures, (ii) Otsu’s thresholding, (iii) Kapur’s thresholding, and (iv) Fuzzy-Tsallis thresholding, this proposal examines the different CNN segmentation schemes presented in the literature. For mining skin lesions, the Moth-Flame Algorithm (MFA) combined with tri-level thresholding achieves an optimal threshold for the DDI. With Fuzzy-Tsallis thresholding images, the VGG-UNet performs better than the alternatives. This framework helps to achieve better values of Jaccard (88.47±2.13%), Dice (93.08±1.17%), and Accuracy (98.64±0.71%) on the chosen DDI database.

Multiple linear regression based illumination normalization for non-uniform light image thresholding

Thresholding-based two-class image binarization is one of the simplest and most popular approaches. However, the performance of global thresholding degrades under non-uniform lighting conditions. Local thresholding methods are widely used for binarizing uneven light images. The appropriate choice of the initial size of the window and designing the bimodal criteria function are the most challenging tasks for the local thresholding approaches. Therefore, to make it simpler, in this work, a novel approach is developed to improve the efficacy of binarizing any uneven light images. To begin with, a two stage approach is developed to extract valid training sample points from the uneven light images for estimating the illumination surface. In addition, the Multiple-Linear-Regression (MLR) method is applied on the extracted training sample points to estimate the illumination surface. Furthermore, the estimated illumination surface is used to normalize the non-uniform light of the image to binarize the image using Otsu’s global thresholding. The proposed approach is validated on different variants of uneven light images and with six different states of art uneven light image binarization approaches. It is observed from the simulations that the performance of the proposed approach outperforms the other approaches in qualitative as well as quantitative measures. Further, the binarization of uneven document image methods are not effective on object background binarization of uneven images. The proposed approach has the average F-Measure (F1) score of 0.98, average Jaccard Index (JI) score of 0.97, average Percentage of Misclassification Error (PME) score of 1.10 and the computational complexity of 2.64 sec.

Edge Detection and Defects Checking of Binder Clip and Welded Joint using a Python-Based Algorithm: Applications in Quality Inspection

Machine vision is a computer vision system that enables a computer to work on image-based inspection and analysis for different applications. In this computer vision, a camera and sensor were used to view an image for its analysis with the help of some sort of algorithms, then processed to infer the image-based data. Machine vision systems along with Python programs can be used for many interdisciplinary applications like weld inspection, online monitoring in manufacturing auto components etc. In this study, the “Edge detection python algorithm” was developed and run through “Google Colab” notebook to inspect the edges and the boundaries of samples like faying surface-modified friction welded dissimilar joints and a binder clip (paper clamp) to check any defects or cracks and straightness etc. With the help of this Python algorithm, the edge detection was done by Sobel, Scharr, and Prewit operators. An input image of the weld joint and the binder clip were converted into Otsu’s binary threshold image. The matrix vision camera and the CMOS sensor were used in the machine vision set-up to take the images. This written algorithm is helpful to trace the edges of any kind of solids components. The edges of the binder clips and the weld joint/zone were detected. The binder clips were inspected under two different cases namely the clip in folding condition (Case I) and the binder clip in unfolding condition (Case II). The results showed a defect that was identified in the weld zone and no bending was in the binder clips. This kind of study is useful in manufacturing industries for quality inspection purposes with a new machine vision set up for online inspection of fabricated components like nuts and bolts etc.

Influence of threshold selection and image sequence in in-vivo segmentation of enlarged perivascular spaces

BackgroundGrowing interest surrounds perivascular spaces (PVS) as a clinical biomarker of brain dysfunction given their association with cerebrovascular risk factors and disease. Neuroimaging techniques allowing quick and reliable quantification are being developed, but, in practice, they require optimisation as their limits of validity are usually unspecified. New methodWe evaluate modifications and alternatives to a state-of-the-art (SOTA) PVS segmentation method that uses a vesselness filter to enhance PVS discrimination, followed by thresholding of its response, applied to brain magnetic resonance images (MRI) from patients with sporadic small vessel disease acquired at 3 T. ResultsThe method is robust against inter-observer differences in threshold selection, but separate thresholds for each region of interest (i.e., basal ganglia, centrum semiovale, and midbrain) are required. Noise needs to be assessed prior to selecting these thresholds, as effect of noise and imaging artefacts can be mitigated with a careful optimisation of these thresholds. PVS segmentation from T1-weighted images alone, misses small PVS, therefore, underestimates PVS count, may overestimate individual PVS volume especially in the basal ganglia, and is susceptible to the inclusion of calcified vessels and mineral deposits. Visual analyses indicated the incomplete and fragmented detection of long and thin PVS as the primary cause of errors, with the Frangi filter coping better than the Jerman filter. Comparison with existing methodsLimits of validity to a SOTA PVS segmentation method applied to 3 T MRI with confounding pathology are given. ConclusionsEvidence presented reinforces the STRIVE-2 recommendation of using T2-weighted images for PVS assessment wherever possible. The Frangi filter is recommended for PVS segmentation from MRI, offering robust output against variations in threshold selection and pathology presentation.

Factors determining the requirement of surgical intervention and prognosis in cases of traumatic bifrontal contusions: A prospective observational study

Background: Traumatic brain injury, being a notorious cause of mortality and morbidity across the globe, presents with a variety of lesions. One of the distinct patterns of injury is characterized by contusions of both frontal lobes, labeled “traumatic bifrontal contusions” (TBCs). TBC is often associated with the presence of significant edema and mass effect leading to rapid clinical deterioration after a usually benign presentation at the time of first evaluation. Formulating a management plan in a patient with TBC is often more difficult than in a patient with a major intracranial hematoma. Methods: A prospective observational study with aims and objectives to identify predictors of an unfavorable outcome, analysis of the evolution of TBC, evaluation of the specific indications for surgery, and determination of the prognosis. All head trauma patients harboring bifrontal contusions were included in the study. Patients with other associated operable injuries involving blunt trauma abdomen and orthopedic injuries, counter-coupe injuries, and obvious open fractures noted over calvaria were excluded from the study. Glasgow coma scale (GCS) was recorded during the first assessment, followed by non-contrast computerized tomography (NCCT) Head. Results: A total of 53 patients satisfying inclusion and exclusion criteria were included in the study. The average GCS score recorded before surgical intervention was 9. The mean and median best motor response noted was M5. The interval from the time of injury to the first NCCT of the brain at the study hospital ranged from 3 h to 163 h, averaging 17.66 h. The median category w.r.t Marshall’s CT classification observed was “Diffuse Injury IV.” The volume of the contusions in each scan was estimated, and the average anterior cranial fossa volume observed was 125 mL. “Upfront surgery” (“Bifrontal decompressive craniectomy” or “unilateral Fronto-Temporo-Parietal [FTP] decompressive hemicraniectomy”) was carried out on the day of admission based on the findings on the first NCCT brain. About 49% of patients at presentation needed surgical intervention as per existing protocols. The duration of observation for patients who were initially observed but eventually had to undergo surgery ranged from 1 to 5 days, with an average observation period of 2 days. The duration of observation in those who did not subsequently need surgery ranged from 7 to 10 days, with an average duration of 9 days. Conclusion: What leads to the poorly predictable, delayed, and rapid deterioration that sets TBCs apart from other traumatic brain injuries is still unclear. Our study finds that having a low threshold for repeat CT imaging of the patient led to earlier identification of progression, and a low threshold for surgical intervention led to favorable outcomes.

Research of immune clone algorithm applying in the LED lamp automatic lock screw workstation

A new automatic lock screw machine for LED lamp has been researched in the paper, which is based on the immune clone algorithm. Firstly, the robot automatic lock screw system has been setup. Vision sensor captured LED lampshade images in real-time. Median filtering operation has been performed to the captured images. On this basis, a new image segmentation method based on the immune clone algorithm has been researched. The antibody and antigen of LED lampshade image have been defined. The immune affinity function has been setup at the same time. Several artificial immune operators have been designed, which can be used to obtain the optimum image segmentation threshold value in real time. The final results showed that the optimum image threshold value can been obtained after less than ten times iterative computation. Compared with the traditional Ostu method, the new method can reduce the disturbance information around the threaded hole, which made basis for threaded hole recognition and location.

A two-step image segmentation based on clone selection multi-object emperor penguin optimizer for fault diagnosis of power transformer

Power transformer is one of the critical and valuableness apparatus in the secure operation of the power system. The infrared image fault diagnosis can reflect the status of the power transformer. However, how to detect the fault point of the diverse infrared images is a difficult problem. We present a two-stage multilevel threshold image segmentation method to finish the task of power transformers fault diagnosis. The multi-objective emperor penguin optimizer based on the clone selection strategy optimizes the multi-level image segmentation method for discovering the optimal threshold. The 3DOtsu and determination of optimal target number function as the fitness function and we convert them into multi-objective optimization problems. The proposed method is compared with the multi-objective optimization algorithms and novel fault diagnosis methods under the classic images and infrared images of the power transformer. The experiment results show that MOEPO/C has a good performance than others compared algorithms in Feature Similarity Index, Uniformity measure, Peak Signal‑to‑Noise Ratio, and CPU time. Especially, the proposed method obtains high accuracy in power transformer fault diagnosis.

Soft X-ray image recognition and classification of maize seed cracks based on image enhancement and optimized YOLOv8 model

The current investigation on image recognition and internal crack detection of maize seeds primarily relies on visible light imaging. However, due to the low transmissivity of plant cells, even with image enhancement measures, the clarity of internal cracks in the images and the subsequent feature extraction process can be a trade-off. Soft X-rays possess exceptional penetration capability and offer better safety and convenience compared to hard X-rays, making them highly suitable for visualizing internal structures within plant tissues like maize seeds. In this paper, a non-invasive Imaging Technique for Image Enhancement is proposed, combining wavelet thresholding denoising, image standardization, bilateral filtering, and laplacian sharpening. This method is based on soft X-rays and successfully achieves image recognition of cracks present inside Zhengdan 958 maize seeds using an optimized YOLOv8 model. It effectively addresses challenges related to the limited light transmission of maize seeds, difficulty in crack localization, and algorithm generalization issues. The optimized YOLOv8 model demonstrates an average precision (AP) value that is 3.1% higher than that of the original model. Furthermore, by applying image enhancement, the AP value increases by 1.8%. The proposed method exhibits an average recognition accuracy of 99.66% for intact or broken seeds, an average precision of 99.87%, an average recognition recall of 99.48%, and an average single-frame image detection time of 7.49 ms in the single seed detection experiment.

Characterization of Immediate Pressing Tactics in Soccer in the Age of Artificial Intelligence

Abstract This paper focuses on the use of feature extraction techniques as well as parameter estimation to analyze the immediate pressing tactics in soccer games. The motion target detection method is used to capture the movements of the soccer player. By setting the rotation angle of the point cloud, the soccer movement action is represented in the form of a coordinate system. By combining the inter-frame difference method and setting the motion image threshold, the motion target can be obtained. Utilize Hu moments to extract the features of soccer motion. Combine the center of mass and velocity of soccer motion to reduce the error rate of motion feature extraction. Pairwise quaternions are utilized to represent soccer motion parameters to improve motion estimation. The results show that the soccer team has the greatest success rate of practicing immediate pressing tactics in 3s-4s, and the success rate of applying immediate pressing tactics after 4s is significantly lower. Team C has the highest success rate of huddling with defensive immediate pressing tactics, which reaches 56.1%. The success rate of huddling is closest to that of team A and team B, which are 43.54% and 43.97%, respectively.

Assessing a universal neocortical mask for Centiloid quantification

AbstractBackgroundThe Centiloid (CL) project was developed to harmonise the quantification of Aβ‐PET scans to a unified scale. The CL neocortical mask was defined using 11C‐PiB, overlooking potential differences in regional distribution among Aβ tracers. We created a universal mask using an independent dataset of 5 Aβ tracers, and investigated its impact on inter‐tracer agreement, tracer variability and group separation.MethodUsing data from the ADOPIC study (AIBL, ADNI and OASIS3), age‐matched pairs of mild Alzheimer’s disease (AD) (MMSE = 20‐24;CL&gt;25) and healthy controls (MMSE&gt; = 28;CDR = 0;CL&lt;15) were selected: 18F‐Florbetapir (FBP:147 pairs), 18F ‐Florbetaben (FBB:22 pairs), 18F ‐Flutemetamol (FLT:10 pairs), 18F ‐NAV (NAV:42 pairs), 11C‐PiB (PIB:63 pairs). The PET images were smoothed to a uniform 8mm resolution to reduce the influence of different scanner sharpness on the derived masks. The images were then spatially normalised using the SPM CL pipeline and transformed into SUVR (whole cerebellum). For each tracer, the mean AD‐HC difference image was computed and mirrored. The threshold for each difference image was optimised to maximise the overlap with the standard CL mask. The Universal mask was defined as the intersection of all 5 masks. It was then used to recalibrate each tracer into Centiloids. The Universal mask and associated transforms were evaluated on the GAAIN head‐to‐head calibration datasets in terms of inter‐tracer agreement and variance in the young controls (YC). They were also evaluated on the baseline ADOPIC dataset (N = 3565) with the effect‐size between HC/AD and HC/MCI.ResultThe overlap between each tracer specific mask was high (mean Dice = 0.82). The Universal mask was 26% smaller than the Standard one, but the overlap was high (Dice = 0.74). The Universal mask led to a small reduction in the variance of the YC in most tracers (‐3.4%) and a small increase in the R2 between each of the 11C‐PiB/18F‐tracer pairs (+0.24%). In ADOPIC, it led to a higher effect‐size between HC/AD (1.43 vs 1.42) and HC/MCI (0.71 vs 0.70).ConclusionThe universal CL mask led to an increase in inter‐tracer agreement and group separation. Those increases were however relatively small indicating that the existing standard CL mask is suitable for the quantification of all Aβ tracers.

SunSCC: Segmenting, Grouping and Classifying Sunspots From Ground‐Based Observations Using Deep Learning

AbstractWe propose a fully automated system to detect, aggregate, and classify sunspot groups according to the McIntosh scheme using ground‐based white light (WL) observations from the USET facility located at the Royal Observatory of Belgium. The sunspot detection uses a Convolutional Neural Network (CNN), trained from segmentation maps obtained with an unsupervised method based on mathematical morphology and image thresholding. Given the sunspot mask, a mean‐shift algorithm is used to aggregate individual sunspots into sunspot groups. This algorithm accounts for the area of each sunspot as well as for prior knowledge regarding the shape of sunspot group. A sunspot group, defined by its bounding box and location on the Sun, is finally fed into a CNN multitask classifier. The latter predicts the three components Z, p, and c in the McIntosh classification scheme. The tasks are organized hierarchically to mimic the dependency of the second (p) and third (c) components on the first (Z). The resulting CNN‐based segmentation is more accurate than classical unsupervised methods, with an enhancement up to 16% of F1 score in detection of the smallest sunspots, and it is robust to the presence of clouds. The automated clustering method was able to separate groups with an accuracy of 80%, when compared to hand‐made USET sunspot group catalog. The CNN‐based sunspot classifier shows comparable performances to methods using continuum as well as magnetogram images recorded by instruments on space mission. We also show that an ensemble of classifiers allows differentiating reliable and potentially incorrect predictions.

Multilevel thresholding image segmentation algorithm based on Mumford–Shah model

Abstract Image segmentation is one of the important tasks of computer vision and computer image processing, and the purpose of image segmentation is to achieve the extraction and recognition of the target image region. The classical Mumford–Shah (MSh) image segmentation model is used to achieve the segmentation of images. With the goal to get the best segmentation effect on images by minimizing the MSh energy generalization function, a level set strategy is developed, and a model with global information infinite curve evolution is utilized. However, considering the low efficiency of this model for processing level set curves and the general quality of image segmentation. A multi-layer threshold search scheme is proposed to achieve rapid convergence of the target image level set curve. The experimental results showed that the multi-level thresholding image segmentation algorithm based on the MSh model can significantly improve the segmentation effect of images and reduce the segmentation time. The suggested MSK method outperforms the MPO algorithm, SSA algorithm, and EMO algorithm in the picture segmentation convergence time test, respectively, in terms of runtime efficiency by 356, 289, and 71%. Additionally, it performs superbly in both threshold searches and picture quality tests. The research topic has significant reference value for the study of contemporary computer vision imaging technologies.