Incomplete Image Research Articles

Load image inpainting: An improved U-Net based load missing data recovery method

Dealing with large percentage data missing is always a challenge for load data recovery. This paper, drawing on ideas from image inpainting, formulates load missing data recovery problem as load image inpainting and the improved U-Net is proposed to restore the load image. First, the 1-dimensional load data is constructed into 2-dimensional load image. Additionally, missing data presents as irregular black holes on the load image. Then, the improved U-Net which introduces residual network (ResNet) and convolutional block attention module (CBAM) is proposed to specifically restore the incomplete load image. Meanwhile, mean absolute error (MAE) and structural similarity (SSIM) are utilized to evaluate data recovery accuracy and load pattern recovery similarity respectively. Load missing data recovery results based on the actual industrial load dataset are presented to verify the effectiveness of the proposed method.

Biomechanical analysis of odontoid and transverse atlantal ligament in humans with ponticulus posticus variation under different loading conditions: Finite element study

PurposePonticulus posticus (PP) is a variation of the bone bridge that appears in the first cervical vertebra and through which the vertebral artery passes. Odontoid fractures are common spinal bone fractures in older people. This study aims to investigate the effect of neck movements on the odontoid and transverse atlantal ligament (TAL) of people with PP variation from a biomechanical view. MethodC1, C2, and C3 vertebrae of the occipital bone were analyzed using the finite element method (FEM). In this study, solid models were created with the help of normal (N), incomplete (IC), and asymmetric complete (AC) PP tomography images. The necessary elements for the models were assigned, and the material properties were defined for the elements. As boundary conditions, models were fixed from the C3 vertebra, and 74 N loading was applied from the occipital bone. Stress and deformation values in the odontoid and transverse atlantal ligament were obtained by applying 1.8 Nm moment in flexion, extension, bending, and axial rotation directions. ResultsThe stress and deformation values of all three models in odontoid and TAL were obtained, and numerical results were evaluated. In all models, stress and deformation values were obtained in decreasing order in rotation, bending, extension, and flexion movements. The highest stress and strain values were obtained in AC and the lowest values were obtained in N. In all movements of the three models, the stress and deformation values obtained in the TAL were lower than in the odontoid. ConclusionThe greatest stresses and deformations obtained in spines (AC) with PP were found in the odontoid. This may help explain the pathogenesis of odontoid fractures in older people. First, this study explains the mechanism of the formation of neck trauma in people with PP and the need for a more careful evaluation of the direction of impact. Secondly, the study reveals that the rotational motion of the neck independent of PP has more negative effects on the odontoid.

Physiology and Technology of Clinical Gollin Test

This review provides a detailed description of the Gollin test technique based on the recognition of fragmented images. Important stages in the development of this method are considered, too. The attention is paid to a review of our research conducted using the Gollin test to solve various problems in studying the mechanisms of signal extraction from noise, invariant perception, the insight phenomenon, and modeling the functioning of the nervous system. The neurophysiological mechanisms of incomplete image recognition are discussed. Suggestions are made for possible ways of the further development of the technique and its application in fundamental psychophysiology, systems of artificial intelligence, and medicine.

Fusion of Infrared and Visible Images Based on Three-Scale Decomposition and ResNet Feature Transfer

Image fusion technology can process multiple single image data into more reliable and comprehensive data, which play a key role in accurate target recognition and subsequent image processing. In view of the incomplete image decomposition, redundant extraction of infrared image energy information and incomplete feature extraction of visible images by existing algorithms, a fusion algorithm for infrared and visible image based on three-scale decomposition and ResNet feature transfer is proposed. Compared with the existing image decomposition methods, the three-scale decomposition method is used to finely layer the source image through two decompositions. Then, an optimized WLS method is designed to fuse the energy layer, which fully considers the infrared energy information and visible detail information. In addition, a ResNet-feature transfer method is designed for detail layer fusion, which can extract detailed information such as deeper contour structures. Finally, the structural layers are fused by weighted average strategy. Experimental results show that the proposed algorithm performs well in both visual effects and quantitative evaluation results compared with the five methods.

A deep learning-based diagnostic pattern for ultrasound breast imaging: can it reduce unnecessary biopsy?

BackgroundEarly studies have demonstrated the potential of deep learning in bringing revolutionary changes in medical analysis. However, it is unknown which deep learning based diagnostic pattern is more effective for differentiating malignant and benign breast lesions (BLs) and can assist radiologists to reduce unnecessary biopsies.MethodsA total of 506 malignant BLs and 557 benign BLs were enrolled in this study after excluding incomplete ultrasound images. 396 malignant BLs and 447 benign BLs were included in the training cohort while 110 malignant and 110 benign BLs were included in the validation cohort. All BLs in the training and validation cohort were biopsy-proven. The most common convolutional neural networks (VGG-16 and VGG-19) were applied to identify malignant and benign BLs using grey-scale ultrasound images. Two radiologists determined the malignant (suggestion for biopsy) and benign (suggestion for follow-up) BLs with a 2-step reading session. The first step was based on conventional ultrasound (US) images alone to make a biopsy or follow-up decision. The second step was to take deep learning results into account for the decision adjustment. If a deep learning result of a first-classified benign BL was above the cut-off value, then it was re-classified as malignant.ResultsIn terms of area under the curve (AUC), the VGG-19 model yielded the best diagnostic performance in both training [0.939, 95% confidence interval (CI): 0.924–0.954] and testing dataset (0.959, 95% CI: 0.937–0.982). With the aid of deep learning models, the AUC of radiologists improved from 0.805 (95% CI: 0.744–0.865) to 0.827 (95% CI: 0.771–0.875, VGG-16) and 0.914 (95% CI: 0.871–0.957, VGG-19). The unnecessary biopsies decreased from 10.0% (11/110) to 8.2% (9/110) (assisted by VGG-16) and 0.9% (1/110) (assisted by VGG-19).ConclusionsThe application of deep learning patterns in breast US may improve the diagnostic performance of radiologists by offering a second opinion. And thus, the assist of deep learning algorithm can considerably reduce the unnecessary biopsy rate in the clinical management of breast lesions.

A planetary boundary-based method to assess freshwater use at the global and local scales

Many studies have attempted to evaluate the transgression of the water planetary boundary at sub-global levels. Typically, this has been done by assessing water consumption in a country/city or sector against the assigned share of the global limit. Such an approach enables evaluating whether a sub-global unit operates within the safe global limits. However, it ignores spatial water availability and thus may provide an incomplete image of water-related environmental impacts and thus local boundaries. This study demonstrates how the water planetary boundary concept can be integrated within the Environmentally Extended Multi-Region Input-Output (EEMRIO) framework to assess global and local (watershed level) boundaries. Our results demonstrate that even though most countries operate within globally safe limits, for several countries, a large share of water comes from watersheds that have reached unsafe water consumption levels. This highlights the importance of combining local and global level assessments to design more accurate and tailored policy responses targeting specific watersheds that are most at risk.

Inpainting the metal artifact region in MRI images by using generative adversarial networks with gated convolution.

Magnetic resonance imaging (MRI) plays an important role in clinical diagnosis, but it is susceptible to metal artifacts. The generative adversarial network GatedConv with gated convolution (GC) and contextual attention (CA) was used to inpaint the metal artifact region in MRI images. MRI images containing or near the teeth of 70 patients were collected, and the scanning sequence was a T1-weighted high-resolution isotropic volume examination sequence. A total of 10 000 slices were obtained after data enhancement, of which 8000 slices were used for training. MRI images were normalized to [-1,1]. Based on the randomly generated mask, U-Net, pix2pix, PConv with partial convolution, and GatedConv were used to inpaint the artifact region of MRI images. The mean absolute error (MAE) and peak signal-to-noise ratio (PSNR) for the mask were used to compare the results of these methods. The inpainting effect on the test dataset using dental masks was also evaluated. Besides, the artifact area of clinical MRI images was inpainted based on the mask sketched by physicians. Finally, the earring artifacts and artifacts caused by abnormal signal foci were inpainted to verify the generalization of the models. GatedConv could directly and effectively inpaint the incomplete MRI images generated by masks in the image domain. For the results of U-Net, pix2pix, PConv, and GatedConv, the masked MAEs were 0.1638, 0.1812, 0.1688, and 0.1596, respectively, and the masked PSNRs were 18.2136, 17.5692, 18.2258, and 18.3035dB, respectively. Using dental masks, the results of U-Net, pix2pix, and PConv differed more from the real images in terms of alveolar shape and surrounding tissue compared with GatedConv. GatedConv could inpaint the metal artifact region in clinical MRI images more effectively than the other models, but the increase in the mask area could reduce the inpainting effect. Inpainted MRI images by GatedConv and CT images with metal artifact reduction coincided with alveolar and tissue structure, and GatedConv could successfully inpaint artifacts caused by abnormal signal foci, whereas the other models failed. The ablation study demonstrated that GC and CA increased the reliability of the inpainting performance of GatedConv. MRI images are affected by metal, and signal void areas appear near metal. GatedConv can inpaint the MRI metal artifact region in the image domain directly and effectively and improve image quality. Medical image inpainting by GatedConv has potential value for tasks, such as positron emission tomography (PET) attenuation correction in PET/MRI and adaptive radiotherapy of synthetic CT based on MRI.

Deep evidential fusion network for medical image classification

The multi-modality characteristic of medical images calls for the application of information fusion theory in computer aided diagnosis (CAD) algorithm design. Recently, the research of uncertainty estimation in deep neural networks provides a new perspective for information fusion in deep learning algorithms. For medical image classification tasks, due to the difficulty in collecting large-scale datasets, it is a challenging job in the study of deep learning multi-modality medical image classification model. In this paper, we investigate the fusion method based on the belief/uncertainty estimation framework of evidential deep learning (EDL) and Dempster's rule of combination. We also propose a deep evidential fusion method to best utilize the belief assignment and uncertainty estimation for combining the information of multi-modality medical images when only small-scale and even incomplete multi-modality medical image dataset is available. The proposed method has been tested on two real-world medical image classification tasks. To maximize the use of available medical imaging resources, we extended our model to handle the modality missing problem for multi-modality learning. Experiments show that, with the proposed weighted mass calibration method, our fusion model can handle the modality missing problem in real-world applications, making it possible to incorporate more incomplete data for learning.

An image denoising method of picking robot vision based on feature pyramid network

AbstractDeep learning has been widely used in removing image noise, but the blind denoising problem in agriculture limits the accuracy of citrus recognition by picking robots, and most denoising methods do not preserve the texture details of the image well. To solve these problems, this study proposes a multi‐module image denoising method based on feature pyramid network. The algorithm is based on the pyramid network structure, adding modules such as attention mechanism, dilated convolution, and feature fusion to denoise images. The attention mechanism and dilated convolution enhance the extraction of noisy features. The feature fusion module fuses the feature maps of each layer to solve the problem of incomplete image detail texture preservation. The experimental results of this algorithm on different datasets show that the performance of our method on various datasets with different noise levels is superior, and it is solving the problem of real image denoising. It is effective to perform both on and save the image texture details, which proves the practicability of the method in this study. After using this method to remove the real noise in the image, the average score of citrus detection accuracy is 52.4% higher than that before denoising.Practical ApplicationsCitrus picking is a labor‐intensive work. Traditionally, citrus picking depends on manpower. This harvesting method has high cost and low efficiency, which seriously hinders the development of citrus industry. In this study, the pyramid network structure is used to denoise the citrus image by adding modules such as attention mechanism, dilated convolution, and feature fusion, so as to guide the robot to recognize the citrus and improve the production efficiency. It is of great value to the recognition technology of industrial citrus picking robot.

SwapInpaint: Identity-Specific Face Inpainting With Identity Swapping

As face editing scenarios have become popular, the face inpainting technique has become a hot topic. Although some existing methods can inpaint faces with preserved identity information, they fail to solve a more flexible inpainting problem that fills the “holes” with identity-specific content from other faces. In this work, we propose a disentangle and subject-agnostic framework that affects both full and partial-face inpainting with the guidance of a reference face image. The framework consists of an identity encoding module, a content inference module and a generative module. The identity encoding module extracts the identity embedding from the reference image, the content inference module learns to predict the content image, and the generative module integrates the content image and the reference identity embedding to generate the identity-specific inpainted result. To minimize the structure and style gap between the incomplete image and inpainted image, we use a double attribute loss to the generative module and a postprocess of blending operation to the swapped result. We compare our method with state-of-the-art works and demonstrate that our method achieves higher identity similarity and better structural correctness.

An image watermark removal method for secure internet of things applications based on federated learning

AbstractWatermark adding is one of the important means for image security and privacy protection in Internet of things (IOT) applications based on federated learning. It is often inseparable from adversarial training with watermark removal algorithms. The effect of watermark removal algorithms will directly affect the final result of watermark addition. However, the existing watermark removal algorithms have drawbacks such as incomplete image watermark removal, poor image quality after watermark removal, large demand for training data, and incorrect filling, which seriously affects the development of image information security and privacy protection in IOT applications based on federated learning. To solve the above problems, this paper proposes an improved image watermark removal convolutional network model based on deep image prior. First, we improve the U‐Net network model, using six downsamping layers and six deconvolution layers combined with deep image prior method to reduce the loss of details and perceive high‐level features, thereby improving the ability of the network to extract high‐level features of the image. In addition, we design a new type of loss function which is called stair loss, and add L1 loss and perception loss to establish new constraints. In order to verify the effectiveness of our method, a comprehensive experimental comparison was conducted on the public dataset PASCAL VOC 2012 in the same experimental environment with CGAN and the deep prior method. The experimental results show that the improved model combined with the deep image prior method can extract the high‐level feature information and can directly remove the watermark from the picture without pretraining the network, the L1 loss and perceptual loss can better retain the image structure information and speed up the watermark removal of the model, the stair loss corrects the final output more accurately by correcting the output of each layer; our method improves the learning ability of the model, and under the condition of the same training time, the image quality after watermark removal is higher, and the final watermark removal result is better, which is more suitable for distributed structure of IoT application based on federated learning.

A Missing Data Reconstruction Method Using an Accelerated Least-Squares Approximation with Randomized SVD

An accelerated least-squares approach is introduced in this work by incorporating a greedy point selection method with randomized singular value decomposition (rSVD) to reduce the computational complexity of missing data reconstruction. The rSVD is used to speed up the computation of a low-dimensional basis that is required for the least-squares projection by employing randomness to generate a small matrix instead of a large matrix from high-dimensional data. A greedy point selection algorithm, based on the discrete empirical interpolation method, is then used to speed up the reconstruction process in the least-squares approximation. The accuracy and computational time reduction of the proposed method are demonstrated through three numerical experiments. The first two experiments consider standard testing images with missing pixels uniformly distributed on them, and the last numerical experiment considers a sequence of many incomplete two-dimensional miscible flow images. The proposed method is shown to accelerate the reconstruction process while maintaining roughly the same order of accuracy when compared to the standard least-squares approach.

Trajectory prediction based on conditional Hamiltonian generative network for incomplete observation image sequences

The combination of Hamiltonian formalism and neural networks is playing an important role in dealing with chaotic systems. Aiming at the problem of motion control under the condition of unknown physical quantity and incomplete observation set, a trajectory prediction model based on conditional Hamiltonian generating network (CHGN) for incomplete observation image sequences is proposed. CHGN is composed of Conditional AutoEncoder (CVAE), Hamiltonian neural network (HNN) and Velocity–Verlet integrator. CVAE encoder converts the short-term continuous observation image sequence into target motion state features represented by generalized coordinates and generalized momentum, and generates the trajectory prediction image at the specified time. HNN is used to learn potential Hamiltonian physical quantities, so as to understand more chaotic system dynamics information to realize state cognition. Velocity–Verlet integrator predicts the motion state at any moment according to the Hamiltonian learned by HNN at the current moment. The motion state and the specified time are used as the input of CVAE decoder to generate the target prediction image from the potential motion space. Experimental results show that CHGN can accurately predict target trajectories over a long period of time based on incomplete short-term image sequences, and has better performance with minimum mean square error(MSE) on three physical system datasets than existing deep learning methods.

Bifurcation Fusion Network for RGB-D Salient Object Detection

With the rapid development of sensor technology, multi-modal data fusion methods based on deep neural networks provide a reliable guarantee for object recognition and detection in complex scenarios. Most of the existing RGB-D image salient object detection methods improve the salient object detection methods in 2D scenes, which have many problems, such as ineffective fusion of feature information, incomplete image feature extraction and so on. Aiming at these problems, we proposed a salient object detection method based on bifurcated fusion network. First, we use the high- level features of the global context to locate the salient object, then we use the low-level features of the local details to extract the edge information. Second, we model the RGB information and depth information through the gate channel transformation control mechanism, and construct the bifurcation backbone network model and generate the initial salient map. Finally, based on the initial salient map and low-level features, the final salient map is generated. Experimental results show that the proposed method can fully utilize the multi-layer feature information of the image and effectively detect the salient object.

Patient-Generated Health Photos and Videos Across Health and Well-being Contexts: Scoping Review.

BackgroundPatient-generated health data are increasingly used to record health and well-being concerns and engage patients in clinical care. Patient-generated photographs and videos are accessible and meaningful to patients, making them especially relevant during the current COVID-19 pandemic. However, a systematic review of photos and videos used by patients across different areas of health and well-being is lacking.ObjectiveThis review aims to synthesize the existing literature on the health and well-being contexts in which patient-generated photos and videos are used, the value gained by patients and health professionals, and the challenges experienced.MethodsGuided by a framework for scoping reviews, we searched eight health databases (CINAHL, Cochrane Library, Embase, PsycINFO, PubMed, MEDLINE, Scopus, and Web of Science) and one computing database (ACM), returning a total of 28,567 studies. After removing duplicates and screening based on the predefined inclusion criteria, we identified 110 relevant articles. Data were charted and articles were analyzed following an iterative thematic approach with the assistance of NVivo software (version 12; QSR International).ResultsPatient-generated photos and videos are used across a wide range of health care services (39/110, 35.5% articles), for example, to diagnose skin lesions, assess dietary intake, and reflect on personal experiences during therapy. In addition, patients use them to self-manage health and well-being concerns (33/110, 30%) and to share personal health experiences via social media (36/110, 32.7%). Photos and videos create significant value for health care (59/110, 53.6%), where images support diagnosis, explanation, and treatment (functional value). They also provide value directly to patients through enhanced self-determination (39/110, 35.4%), social (33/110, 30%), and emotional support (21/110, 19.1%). However, several challenges emerge when patients create, share, and examine photos and videos, such as limited accessibility (16/110, 14.5%), incomplete image sets (23/110, 20.9%), and misinformation through photos and videos shared on social media (17/110, 15.5%).ConclusionsThis review shows that photos and videos engage patients in meaningful ways across different health care activities (eg, diagnosis, treatment, and self-care) for various health conditions. Although photos and videos require effort to capture and involve challenges when patients want to use them in health care, they also engage and empower patients, generating unique value. This review highlights areas for future research and strategies for addressing these challenges.

HfZrOx-based capacitive synapses with highly linear and symmetric multilevel characteristics for neuromorphic computing

A hardware based artificial neural network (ANN), which holds the potential to alleviate the computation load and energy of a digital computer, has propelled the development of memory devices that can resemble the synapse. Memcapacitors, especially based on ferroelectric materials, with theoretically no static power, nondestructive readout, and multiple polarization states, are expected to have good energy efficiency and endurance as emerging artificial synapses. However, conventional ferroelectric devices are characterized with extremely high remnant polarization, which requires high energy for polarization state updating and always leads to low linearity and symmetry in updating properties. Here, we show a memcapacitive synapse based on an Au/HfZrOx (HZO)/Au ferroelectric memcapacitor with moderate remnant polarization that can offer unexceptionable updating properties for building an ANN. The memcapacitor demonstrates more than 64 weight states with an ultralow weight updating energy of ≤3.0 fJ/μm2. Both potentiation and depression synaptic characteristics show an ultralow non-linearity of <10−2. Based on these properties, a two-layer restricted Boltzmann machine is built based on this memcapacitive synapse, and it can be trained to reconstruct incomplete images. The reconstructed images show reduced Euclidean distance to originals in comparison with that of the incomplete images. Furthermore, the memcapacitive synapse is also tested by a handwritten digits recognition task based on a simple perceptron, and the pattern recognition accuracy is as high as 93.4%. These results indicate that the HZO-based capacitive synapse devices have great potential for future high-efficiency neuromorphic systems.

Microbial fuel cell systems; developments, designs, efficiencies, and trends: A comparative study between the conventional and innovative systems

The microbial fuel cell (MFC) technology has appeared in the late 20th century and received considerable attention over the last decade due to its multiple and unique potential in converting the substrates into electricity and valuable productions. Extensive efforts have been paid to improve the MFCs performance, leading to the publication of a massive amount of research that developed various aspects of these systems. Most of these improvements have focused on optimization parameters, which is currently inappropriate to provide an innovational developing vision for MFC systems. The convergent results in most of the previous conventional studies (12,643 studies according to the WOS database) have reduced the value of MFCs by drawing an incomplete image for the performance of the systems. Therefore, this paper aimed to provide a comprehensive comparison between the highly reliable studies that innovatively developed the MFC systems and the conventional MFCs studies. The current paper discusses the novel MFCs development history, designs, efficiency, and challenges compared to conventional MFCs. The discussion has displayed the high efficiency of the novel MFCs in removing over 90% of substrates and generating power of 800 mW m−2. The paper also analyzed the literature trends, history and suggested recommendations for future studies. This is the first paper highlighting the substantial differences between the innovative and conventional MFC systems, nominating it to be a vital reference for novel MFCs studies in the future.

Improved understanding of regional groundwater drought development through time series modelling: the 2018–2019 drought in the Netherlands

Abstract. The 2018–2019 drought in north-western and central Europe caused severe damage to a wide range of sectors. It also emphasised the fact that, even in countries with temperate climates, adaptations are needed to cope with increasing future drought frequencies. A crucial component of drought management strategies is to monitor the status of groundwater resources. However, providing up-to-date assessments of regional groundwater drought development remains challenging due to the limited availability of high-quality data. This limits many studies to small selections of groundwater monitoring sites, giving an incomplete image of drought dynamics. In this study, a time series modelling-based method for data preparation was developed and applied to map the spatio-temporal development of the 2018–2019 groundwater drought in the south-eastern Netherlands, based on a large set of monitoring data. The data preparation method was evaluated for its usefulness and reliability for data validation, simulation, and regional groundwater drought assessment. The analysis showed that the 2018–2019 meteorological drought caused extreme groundwater drought throughout the south-eastern Netherlands, breaking 30-year records almost everywhere. Drought onset and duration were strongly variable in space, and higher-elevation areas suffered from severe drought well into 2020. Groundwater drought development appeared to be governed dominantly by the spatial distribution of rainfall and the landscape type. The time series modelling-based data preparation method was found to be a useful tool to enable a spatially detailed record of regional groundwater drought development. The automated time series modelling-based data validation improved the quality and quantity of useable data, although optimal validation parameters are probably context dependent. The time series simulations were generally found to be reliable; however, the use of time series simulations rather than direct measurement series can bias drought estimations, especially at a local scale, and underestimate spatial variability. Further development of time-series-based validation and simulation methods, combined with accessible and consistent monitoring data, will be valuable to enable better groundwater drought monitoring in the future.

Measuring Dynamics in Evacuation Behaviour with Deep Learning.

Bounded rationality is one crucial component in human behaviours. It plays a key role in the typical collective behaviour of evacuation, in which heterogeneous information can lead to deviations from optimal choices. In this study, we propose a framework of deep learning to extract a key dynamical parameter that drives crowd evacuation behaviour in a cellular automaton (CA) model. On simulation data sets of a replica dynamic CA model, trained deep convolution neural networks (CNNs) can accurately predict dynamics from multiple frames of images. The dynamical parameter could be regarded as a factor describing the optimality of path-choosing decisions in evacuation behaviour. In addition, it should be noted that the performance of this method is robust to incomplete images, in which the information loss caused by cutting images does not hinder the feasibility of the method. Moreover, this framework provides us with a platform to quantitatively measure the optimal strategy in evacuation, and this approach can be extended to other well-designed crowd behaviour experiments.

Evaluation of VDT-Induced Visual Fatigue by Automatic Detection of Blink Features.

This study evaluates the progression of visual fatigue induced by visual display terminal (VDT) using automatically detected blink features. A total of 23 subjects were recruited to participate in a VDT task, during which they were required to watch a 120-min video on a laptop and answer a questionnaire every 30 min. Face video recordings were captured by a camera. The blinking and incomplete blinking images were recognized by automatic detection of the parameters of the eyes. Then, the blink features were extracted including blink number (BN), mean blink interval (Mean_BI), mean blink duration (Mean_BD), group blink number (GBN), mean group blink interval (Mean_GBI), incomplete blink number (IBN), and mean incomplete blink interval (Mean_IBI). The results showed that BN and GBN increased significantly, and that Mean_BI and Mean_GBI decreased significantly over time. Mean_BD and Mean_IBI increased and IBN decreased significantly only in the last 30 min. The blink features automatically detected in this study can be used to evaluate the progression of visual fatigue.