Amount Of Blur Research Articles

Feasibility of Encord Artificial Intelligence Annotation of Arterial Duplex Ultrasound Images.

DUS measurements for popliteal artery aneurysms (PAAs) specifically can be time-consuming, error-prone, and operator-dependent. To eliminate this subjectivity and provide efficient segmentation, we applied artificial intelligence (AI) to accurately delineate inner and outer lumen on DUS. DUS images were selected from a cohort of patients with PAAs from a multi-institutional platform. Encord is an easy-to-use, readily available online AI platform that was used to segment both the inner lumen and outer lumen of the PAA on DUS images. A model trained on 20 images and tested on 80 images had a mean Average Precision of 0.85 for the outer polygon and 0.23 for the inner polygon. The outer polygon had a higher recall score than precision score at 0.90 and 0.85, respectively. The inner polygon had a score of 0.25 for both precision and recall. The outer polygon false-negative rate was the lowest in images with the least amount of blur. This study demonstrates the feasibility of using the widely available Encord AI platform to identify standard features of PAAs that are critical for operative decision making.

Image defocus deblurring method based on gradient difference of boundary neighborhood

BackgroundFor static scenes with multiple depth layers, the existing defocused image deblurring methods have the problems of edge ringing artifacts or insufficient deblurring degree due to inaccurate estimation of blur amount, In addition, the prior knowledge in non blind deconvolution is not strong, which leads to image detail recovery challenge. MethodsTo this end, this paper proposes a blur map estimation method for defocused images based on the gradient difference of the boundary neighborhood, which uses the gradient difference of the boundary neighborhood to accurately obtain the amount of blurring, thus preventing boundary ringing artifacts. Then, the obtained blur map is used for blur detection to determine whether the image needs to be deblurred, thereby improving the efficiency of deblurring without manual intervention and judgment. Finally, a non blind deconvolution algorithm is designed to achieve image deblurring based on the blur amount selection strategy and sparse prior. ResultsExperimental results show that our method improves PSNR and SSIM by an average of 4.6% and 7.3%, respectively, compared to existing methods. ConclusionsExperimental results show that our method outperforms existing methods. Compared with existing methods, our method can better solve the problems of boundary ringing artifacts and detail information preservation in defocused image deblurring.

Restoration of a blurred photographic image of a moving object obtained at the resolution limit

Objectives. When processing images of the Earth’s surface obtained from satellites, the problem of restoring a blurry image of a moving object is of great practical importance. The aim of this work is to study the possibility of improving the quality of restoration of blurry images obtained at the limit of the resolution of the camera.Methods. Digital signal processing methods informed by the theory of incorrect and ill-conditioned problems were used.Results. The proposed method for restoring a blurred photographic image of a moving object differs from traditional approaches in that the discrete convolution equation, to which the problem of restoring a blurred image is reduced, is obtained by approximating the corresponding integral equation based on the Kotelnikov interpolation series rather than on the traditional basis of the quadrature formula. In the work, formulas are obtained for calculating the kernel of the convolution obtained using the Kotelnikov interpolation series. The discrete convolution inversion problem, which belongs to the class of ill-posed problems, requires regularization. Results of traditional approaches to restoring blurred images using the quadrature formula with Tikhonov regularization and the proposed method based on the Kotelnikov interpolation series are compared. Although the quality of the blurred image restoration is almost the same in both cases, in the quadrature formula the blur value is expressed as an integer number of pixels, while, when using the Kotelnikov series, this value can also be specified in fractions of a pixel.Conclusions. The expediency of discretizing the convolution describing the image distortion of the blur type on the basis of the Kotelnikov interpolation series when processing a blurred image obtained at the limit of the resolution of the camera is demonstrated. In this case, the amount of blur can be expressed in fractions of a pixel. This situation typically arises when processing satellite photography of the Earth’s surface.

Multiscale Convolutional Network for Repairing Coal Slime Foam Images.

Visual feature information regarding flotation foam is crucial for the flotation process. Owing to a large amount of noise and blur in the foam images collected in the floatation field, feature extraction and segmentation of foam images pose considerable challenges. Furthermore, the visual properties of foam are strongly correlated with current flotation conditions. Therefore, this study presents a method to repair blurred pixels in foam images. In addition to enhancing the image dataset necessary for network model training, the restored images can provide high-quality images extracting foam-feature information. In addition, this research presents a novel fifth-order residual structure that enlarges the network structure by stacking, enhancing the learning ability of complex networks. Experimental results demonstrate that the suggested method can achieve a satisfactory repair effect for foam images under various blurring conditions, laying a foundation for guiding the intelligent adjustment of flotation field parameters.

Using evidence-based psychological approaches to accommodation anomalies

ABSTRACT Introduction Accommodation anomalies are frequently caused or exacerbated by psychological problems such as anxiety. Patients share many features with those with other anxiety based somatic symptoms such as stomach-ache, palpitations and headaches. They can be difficult to treat, and the ophthalmic literature rarely goes beyond diagnosis and ocular treatment. This study reports characteristics and outcomes of a short case series of patients with accommodation spasms and weaknesses assessed objectively, and outlines a psychological approach to treatment Methods 23 patients (13 severe accommodative weakness or “paralysis,” 10 accommodative spasm) aged between 8–30 years, were referred to our laboratory after diagnosis by their referring clinician and exclusion of pathology or drug-related causes. Their accommodation and convergence were assessed objectively with a laboratory photorefractive method, as well as by conventional orthoptic testing and dynamic retinoscopy. All interactions with the patients used an evidence-based psychological approach, to give them insight into how stress and anxiety can cause or exacerbate eye symptoms and help them to break a vicious cycle of anxiety and risk of deterioration. Results 83% were female and 57% had previously diagnosed anxiety or dyslexia (with many more acknowledging being “worriers”). Inconsistency of responses was the rule and all showed normal responses at some time during their visit. Responses were poorly related to the visual stimuli presented and objective responses often differed from subjective. Dissociation between convergence and accommodation was more common, compared to our large, previously reported, control groups. No participant had true paralysis of accommodation. Responses often improved dramatically within one session after discussion and explanation of the strong relationship between anxiety and accommodative anomalies. None have returned for further advice or treatment. Conclusions Our approach explicitly addresses psychological factors in causing, or worsening, accommodation (and co-existing convergence) anomalies. Many of these patients do not realize that a certain amount of blur is normal in everyday life. Ocular symptoms are often a sign of anxiety, not the primary problem. By recognizing this, patients can be helped to address the triggering issues and symptoms often subside or resolve spontaneously. Well-meaning professionals, offering only ocular treatments, can deflect attention away from the real cause and can unwittingly be making things worse.

Identification of One-dimensional Directional Blur Amount for Sharpening of Blurred Concrete Structure Images Acquired by UAV

Identification of One-dimensional Directional Blur Amount for Sharpening of Blurred Concrete Structure Images Acquired by UAV

Defocus to focus: Photo-realistic bokeh rendering by fusing defocus and radiance priors

We consider the problem of realistic bokeh rendering from a single all-in-focus image. Bokeh rendering mimics aesthetic shallow depth-of-field (DoF) in professional photography, but these visual effects generated by existing methods suffer from simple flat background blur and blurred in-focus regions, giving rise to unrealistic rendered results. In this work, we argue that realistic bokeh rendering should (i) model depth relations and distinguish in-focus regions, (ii) sustain sharp in-focus regions, and (iii) render physically accurate Circle of Confusion (CoC). To this end, we present a Defocus to Focus (D2F) framework to learn realistic bokeh rendering by fusing defocus priors with the all-in-focus image and by implementing radiance priors in layered fusion. Since no depth map is provided, we introduce defocus hallucination to integrate depth by learning to focus. The predicted defocus map implies the blur amount of bokeh and is used to guide weighted layered rendering. In layered rendering, we fuse images blurred by different kernels based on the defocus map. To increase the reality of the bokeh, we adopt radiance virtualization to simulate scene radiance. The scene radiance used in weighted layered rendering reassigns weights in the soft disk kernel to produce the CoC. To ensure the sharpness of in-focus regions, we propose to fuse upsampled bokeh images and original images. We predict the initial fusion mask from our defocus map and refine the mask with a deep network. We evaluate our model on a large-scale bokeh dataset. Extensive experiments show that our approach is capable of rendering visually pleasing bokeh effects in complex scenes. In particular, our solution receives the runner-up award in the AIM 2020 Rendering Realistic Bokeh Challenge.

Leveraging Blur Information for Plenoptic Camera Calibration

This paper presents a novel calibration algorithm for plenoptic cameras, especially the multi-focus configuration, where several types of micro-lenses are used, using raw images only. Current calibration methods rely on simplified projection models, use features from reconstructed images, or require separated calibrations for each type of micro-lens. In the multi-focus configuration, the same part of a scene will demonstrate different amounts of blur according to the micro-lens focal length. Usually, only micro-images with the smallest amount of blur are used. In order to exploit all available data, we propose to explicitly model the defocus blur in a new camera model with the help of our newly introduced Blur Aware Plenoptic (BAP) feature. First, it is used in a pre-calibration step that retrieves initial camera parameters, and second, to express a new cost function to be minimized in our single optimization process. Third, it is exploited to calibrate the relative blur between micro-images. It links the geometric blur, i.e., the blur circle, to the physical blur, i.e., the point spread function. Finally, we use the resulting blur profile to characterize the camera’s depth of field. Quantitative evaluations in controlled environment on real-world data demonstrate the effectiveness of our calibrations.

Online Projector Deblurring Using a Convolutional Neural Network.

Projector deblurring is an important technology for dynamic projection mapping (PM), where the distance between a projector and a projection surface changes in time. However, conventional projector deblurring techniques do not support dynamic PM because they need to project calibration patterns to estimate the amount of defocus blur each time the surface moves. We present a deep neural network that can compensate for defocus blur in dynamic PM. The primary contribution of this paper is a unique network structure that consists of an extractor and a generator. The extractor explicitly estimates a defocus blur map and a luminance attenuation map. These maps are then injected into the middle layers of the generator network that computes the compensation image. We also propose a pseudo-projection technique for synthesizing physically plausible training data, considering the geometric misregistration that potentially happens in actual PM systems. We conducted simulation and actual PM experiments and confirmed that: (1) the proposed network structure is more suitable than a simple, more general structure for projector deblurring; (2) the network trained with the proposed pseudo-projection technique can compensate projection images for defocus blur artifacts in dynamic PM; and (3) the network supports the translation speed of the surface movement within a certain range that covers normal human motions.

CNN-Based Restoration of a Single Face Image Degraded by Atmospheric Turbulence

Atmospheric turbulence significantly affects imaging systems which use light that has propagated through long atmospheric paths. Images captured under such condition suffer from a combination of geometric deformation and blur. We present a deep learning-based solution to the problem of restoring a single turbulence-degraded face image where the amount of geometric distortion and blur at each pixel location is first estimated in terms of variance maps using two separate networks. The estimated variance maps are then used by the Turbulence Distortion Removal Network (TDRN) to restore the image. Furthermore, a confidence-guided image gradient-based loss is proposed to train TDRN. Comprehensive experiments on synthetic and real face images show that the proposed framework is capable of alleviating blur and geometric distortion caused by atmospheric turbulence, and can significantly improve the visual quality. In addition, an ablation study is performed to demonstrate the improvements obtained by different modules in the proposed method.

Blur Representation in the Amblyopic Visual System Using Natural and Synthetic Images.

PurposeAmblyopia is diagnosed as a reduced acuity in an otherwise healthy eye, which indicates that the deficit is not happening in the eye, but in the brain. One suspected mechanism explaining these deficits is an elevated amount of intrinsic blur in the amblyopic visual system compared to healthy observers. This “internally produced blur” can be estimated by the “equivalent intrinsic blur method”, which measures blur discrimination thresholds while systematically increasing the external blur in the physical stimulus. Surprisingly, amblyopes do not exhibit elevated intrinsic blur when measured with an edge stimulus. Given the fundamental ways in which they differ, synthetic stimuli, such as edges, are likely to generate contrasting blur perception compared to natural stimuli, such as pictures. Because our visual system is presumably tuned to process natural stimuli, testing artificial stimuli only could result in performances that are not ecologically valid.MethodsWe tested this hypothesis by measuring, for the first time, the perception of blur added to natural images in amblyopia and compared discrimination performance for natural images and synthetic edges in healthy and amblyopic groups.ResultsOur results demonstrate that patients with amblyopia exhibit higher levels of intrinsic blur than control subjects when tested on natural images. This difference was not observed when using edges.ConclusionsOur results suggest that intrinsic blur is elevated in the visual system representing vision from the amblyopic eye and that distinct statistics of images can generate different blur perception.

Defocus Blur Segmentation Using Local Binary Patterns with Adaptive Threshold

Enormous methods have been proposed for the detection and segmentation of blur and non-blur regions of the images. Due to the limited available information about blur type, scenario and the level of blurriness, detection and segmentation is a challenging task. Hence, the performance of the blur measure operator is an essential factor and needs improvement to attain perfection. In this paper, we propose an effective blur measure based on local binary pattern (LBP) with adaptive threshold for blur detection. The sharpness metric developed based on LBP used a fixed threshold irrespective of the type and level of blur, that may not be suitable for images with variations in imaging conditions, blur amount and type. Contrarily, the proposed measure uses an adaptive threshold for each input image based on the image and blur properties to generate improved sharpness metric. The adaptive threshold is computed based on the model learned through support vector machine (SVM). The performance of the proposed method is evaluated using two different datasets and is compared with five state-of-the-art methods. Comparative analysis reveals that the proposed method performs significantly better qualitatively and quantitatively against all of the compared methods.

Defocus Blur Segmentation Using Genetic Programming and Adaptive Threshold

Detection and classification of the blurred and the non-blurred regions in images is a challenging task due to the limited available information about blur type, scenarios and level of blurriness. In this paper, we propose an effective method for blur detection and segmentation based on transfer learning concept. The proposed method consists of two separate steps. In the first step, genetic programming (GP) model is developed that quantify the amount of blur for each pixel in the image. The GP model method uses the multi-resolution features of the image and it provides an improved blur map. In the second phase, the blur map is segmented into blurred and non-blurred regions by using an adaptive threshold. A model based on support vector machine (SVM) is developed to compute adaptive threshold for the input blur map. The performance of the proposed method is evaluated using two different datasets and compared with various state-of-the-art methods. The comparative analysis reveals that the proposed method performs better against the state-of-the-art techniques.

Deep Multi-Scale Feature Learning for Defocus Blur Estimation

This paper presents an edge-based defocus blur estimation method from a single defocused image. We first distinguish edges that lie at depth discontinuities (called depth edges, for which the blur estimate is ambiguous) from edges that lie at approximately constant depth regions (called pattern edges, for which the blur estimate is well-defined). Then, we estimate the defocus blur amount at pattern edges only, and explore an interpolation scheme based on guided filters that prevents data propagation across the detected depth edges to obtain a dense blur map with well-defined object boundaries. Both tasks (edge classification and blur estimation) are performed by deep convolutional neural networks (CNNs) that share weights to learn meaningful local features from multi-scale patches centered at edge locations. Experiments on naturally defocused images show that the proposed method presents qualitative and quantitative results that outperform state-of-the-art (SOTA) methods, with a good compromise between running time and accuracy.

Convolutional neural networks trained with a developmental sequence of blurry to clear images reveal core differences between face and object processing.

Although convolutional neural networks (CNNs) provide a promising model for understanding human vision, most CNNs lack robustness to challenging viewing conditions, such as image blur, whereas human vision is much more reliable. Might robustness to blur be attributable to vision during infancy, given that acuity is initially poor but improves considerably over the first several months of life? Here, we evaluated the potential consequences of such early experiences by training CNN models on face and object recognition tasks while gradually reducing the amount of blur applied to the training images. For CNNs trained on blurry to clear faces, we observed sustained robustness to blur, consistent with a recent report by Vogelsang and colleagues (2018). By contrast, CNNs trained with blurry to clear objects failed to retain robustness to blur. Further analyses revealed that the spatial frequency tuning of the two CNNs was profoundly different. The blurry to clear face-trained network successfully retained a preference for low spatial frequencies, whereas the blurry to clear object-trained CNN exhibited a progressive shift toward higher spatial frequencies. Our findings provide novel computational evidence showing how face recognition, unlike object recognition, allows for more holistic processing. Moreover, our results suggest that blurry vision during infancy is insufficient to account for the robustness of adult vision to blurry objects.

Refractive blur affects judgement of pedestrian walking direction at night.

Many individuals drive with uncorrected refractive errors, which has implications for night driving, where poor visibility contributes to the increased crash risk relative to daytime. This study explored how small amounts of refractive blur affects the judgment of the walking direction of night-time pedestrians and whether different types of retro-reflective clothing influence this effect. Judgement of the walking direction of night-time pedestrians was investigated for 20 young participants with normal vision (mean age, 21.8±1.6years) for two levels of binocular blur (+0.50DS, +1.00DS) compared to baseline (best-corrected refractive correction). Participants seated in a stationary car with low beam headlamps observed a pedestrian wearing three clothing conditions: retro-reflective vest (1) and retro-reflective biomotion clothing (incorporating thin (2) or thick (3) retro-reflective strips), who walked across the road in three directions (straight across, away or towards the car). The order of conditions was randomised among participants. Participants reported the perceived pedestrian walking direction and how confident they rated their response. Outcome measures included the proportion of correct responses (response accuracy) and confidence ratings. Blur had a significant effect on accuracy in judging pedestrian walking direction; accuracy decreased significantly with increasing blur (p<0.001), with all blur levels being significantly different from one another. The effect of pedestrian clothing was also significant (p < 0.001); direction judgements were least accurate for vest, followed by both thin and thick biomotion, where accuracy judgements were similar. There was also a significant interaction between blur and clothing (p < 0.05). Similar trends were found for confidence ratings across the blur and clothing conditions. Greater confidence was significantly associated with increased response accuracy for the biomotion clothing, but not the vest. Findings highlight that even small amounts of blur (+0.50DS), that do not reduce visual acuity below the legal driving limits, reduce the ability to accurately judge pedestrian walking direction at night. Retro-reflective clothing in a biomotion configuration facilitated the highest accuracy and confidence in judgment of pedestrian walking direction, for both thin and thick strips compared to vest, for all blur levels.

A motion parameters estimating method based on deep learning for visual blurred object tracking

Tracking the specific object in the blurred scenes is one of the challenging problems in computer vision and image processing. The accuracy and performance of trackers within the blur frames usually demonstrate a severe decrease. Accordingly, this problem needs to be corrected for better tracking results. Thus, this study seeks to present the best solution. To this end, a novel deep learning approach is proposed for object tracking in the presence of motion blur and fast motion. The hidden information in the blurring kernel is useful for tracking a specific blurred object through a series of consecutive frames. In this study, this matter is evaluated from a new perspective to solve the problems of blurred object tracking and objects with highly fast motions using a convolutional neural network (CNN) and a particle filter. Therefore, the proposed framework has two phases. First, the kernel leading to blurring is estimated by CNN, and then by a particle filter and the probability distribution of motion information that has been achieved by the kernel estimation the object is tracked. The results demonstrate that the suggested method can enhance the accuracy of tracking compared with the state-of-the-art, especially when the amount of blur is high.

Autofocus microscope system based on blur measurement approach

Blurred (out-of-focus) images hinder the process of accurate cell counting in medical images. Cell counting is considered an important method to quantify cells for disease diagnosis and medical research. The hemocytometer is used to count cells as it is a cheaper and simple method. The specimen which contains cells is loaded into the hemocytometer and placed on a microscope. In this paper, a new autofocus technique is proposed to automatically adjust the microscope knobs by controlling the movement of adjusting knobs. This method is based on measuring and evaluation of the amount of blur annoyance in cell images. Whereas, adjusting knobs of microscope is a time consuming especially for beginners. Also, the automatic adjustment avoids losing the knob gear if it is used for several times or used in a wrong way. A CCD camera is attached to the microscope to capture images of specimen under test. An efficient blur metric is used to evaluate the amount of blur in captured images. The microscope knob is attached to a stepper motor to control its movement. The movement is stopped when the well-focused image is obtained. The proposed method has proved that it is an efficient method to automatically adjust the microscope knobs and get a well-focused image. The proposed method is compared with another recent approach that is based on an evaluation of a contrast measurement in images to automatically control the microscope knobs. The results proved that the output in-focus images by using the proposed approach for auto-focusing the microscope system have low blur values and much closer to the quality of the original reference images. Moreover, the proposed method which is based on blur measurement gives a higher image quality than one of the most recent approaches that depends on contrast measurement.

Depth Estimation from a Single Image Based on Cauchy Distribution Model

Most approaches to estimate a scene’s 3D depth from a single image often model the point spread function (PSF) as a 2D Gaussian function. However, those methods are suffered from some noises, and difficult to get a high quality of depth recovery. We presented a simple yet effective approach to estimate exactly the amount of spatially varying defocus blur at edges, based on a Cauchy distribution model for the PSF. The raw image was re-blurred twice using two known Cauchy distribution kernels, and the defocus blur amount at edges could be derived from the gradient ratio between the two re-blurred images. By propagating the blur amount at edge locations to the entire image using the matting interpolation, a full depth map was then recovered. Experimental results on several real images demonstrated both feasibility and effectiveness of our method, being a non-Gaussian model for DSF, in providing a better estimation of the defocus map from a single un-calibrated defocused image. These results also showed that our method was robust to image noises, inaccurate edge location and interferences of neighboring edges. It could generate more accurate scene depth maps than the most of existing methods using a Gaussian based DSF model.

Solving the depth ambiguity in single-perspective images

Scene depth estimation is gaining importance as more and more AR/VR and robot vision applications are developed. Conventional depth-from-defocus techniques can passively provide depth maps from a single image. This is especially advantageous for moving scenes. However, they suffer a depth ambiguity problem where two distinct depth planes can have the same amount of defocus blur in the captured image. We solve the ambiguity problem and, as a consequence, introduce a passive technique that provides a one-to-one mapping between depth and defocus blur. Our method relies on the fact that the relationship between defocus blur and depth is also wavelength dependent. The depth ambiguity is thus solved by leveraging (multi-) spectral information. Specifically, we analyze the difference in defocus blur of two channels to obtain different scene depth regions. This paper provides the derivation of our solution, a robustness analysis, and validation on consumer lenses.