Search

We present a preemptive image-based method to reduce motion blurring. Motion blur appears when there is a relative motion between the scene and the viewer/camera. A preemptive method pre-filters the content before being displayed in order to mitigate the occurrence of motion blur. Our experiments and user study have shown that such preemptive methods are fundamentally subject to producing visual artifacts as a consequence of unavoidable ringing or intensity oscillations. Frequency-domain analysis shows that the energy weakened at certain frequencies leads to those artifacts. We present a method to process alphanumeric content so that it has lower energy on frequencies eliminated by a given motion blur kernel. Our processed image, when motion blurred, will have a sharper appearance and less artifacts as compared to various alternative approaches. We demonstrate the effectiveness of the proposed technique with simulated and real-world experiments as well as user feedback. Our results show that our approach yields content robust to motion blur while still being perceptually similar to the original text. [ABSTRACT FROM AUTHOR]

We present 3D point-cloud registration techniques suited for scenarios where robustness to outliers and missing regions is necessary, besides being applicable to both rigid and non-rigid configurations. Our techniques exploit advantages from deep learning models for dense point matching and from recent advances in probabilistic modeling of point-cloud registration. Such a combination produces context awareness and resilience to outliers and missing information. We demonstrate their effectiveness by comparing them to state-of-the-art methods and showing that ours achieve superior results on existing and proposed datasets. [ABSTRACT FROM AUTHOR]

Videos often contain subtle motions and color variations that cannot be easily observed. Examples include, for instance, head motion and changes in skin face color due to blood flow controlled by the heart pumping rhythm. A few techniques have been developed to magnify these subtle signals. However, previous techniques were targeted specifically towards magnification of either motion or color variations. Trying to magnify both aspects applying two of these techniques in sequence does not produce good results. We present a method for magnifying subtle motions and color variations in videos, which can be performed either separately or simultaneously. Our approach is based on the Riesz pyramid, which was previously used only for motion magnification. Besides modifying the local phases of the coefficients of this pyramid, we show how altering its local amplitudes and its residue can be used to magnify intensity/color variations. We demonstrate the effectiveness of our technique in multiple videos by magnifying both subtle motion and color variations simultaneously. [Display omitted] • Technique can be applied to multiple signals defined at different frequency bands. • Color magnification by scaling amplitude coefficients and residues of Riesz Pyramids. • A chrominance-based masking technique for defining regions for signal magnification. [ABSTRACT FROM AUTHOR]

Digital images are everywhere, from social media to news and scientific papers. This paper describes an extensive user study to evaluate the ability of an average individual to spot edited images. By design, our study avoids lucky guesses. After observing an image, subjects were asked if it is authentic or not. Whenever a subject indicated that an image has been altered, (s)he had to provide evidence to support the answer by pointing at the suspected region in the image. We collected 17,208 individual answers from 393 volunteers, using 177 images selected from public forensic databases. Our results indicate that the average individual is not good at distinguishing original from edited images, answering correctly on 58% of all images, and only identifying the modified ones 46.5% of the time. This performance is superior to random guessing, but poor compared to results achieved by computational techniques. [ABSTRACT FROM AUTHOR]

Automatic detection of planar regions in point clouds is an important step for many graphics, image processing, and computer vision applications. While laser scanners and digital photography have allowed us to capture increasingly larger datasets, previous techniques are computationally expensive, being unable to achieve real-time performance for datasets containing tens of thousands of points, even when detection is performed in a non-deterministic way. We present a deterministic technique for plane detection in unorganized point clouds whose cost is O ( n log n ) in the number of input samples. It is based on an efficient Hough-transform voting scheme and works by clustering approximately co-planar points and by casting votes for these clusters on a spherical accumulator using a trivariate Gaussian kernel. A comparison with competing techniques shows that our approach is considerably faster and scales significantly better than previous ones, being the first practical solution for deterministic plane detection in large unorganized point clouds. [ABSTRACT FROM AUTHOR]

Abstract: Experimental data is subject to uncertainty as every measurement apparatus is inaccurate at some level. However, the design of most computer vision and pattern recognition techniques (e.g., Hough transform) overlooks this fact and treats intensities, locations and directions as precise values. In order to take imprecisions into account, entries are often resampled to create input datasets where the uncertainty of each original entry is characterized by as many exact elements as necessary. Clear disadvantages of the sampling-based approach are the natural processing penalty imposed by a larger dataset and the difficulty of estimating the minimum number of required samples. We present an improved voting scheme for the General Framework for Subspace Detection (hence to its particular case: the Hough transform) that allows processing both exact and uncertain data. Our approach is based on an analytical derivation of the propagation of Gaussian uncertainty from the input data into the distribution of votes in an auxiliary parameter space. In this parameter space, the uncertainty is also described by Gaussian distributions. In turn, the votes are mapped to the actual parameter space as non-Gaussian distributions. Our results show that resulting accumulators have smoother distributions of votes and are in accordance with the ones obtained using the conventional sampling process, thus safely replacing them with significant performance gains. [Copyright &y& Elsevier]

Abstract: The analysis of large volumes of unordered multidimensional data is a problem confronted by scientists and data analysts every day. Often, it involves searching for data alignments that emerge as well-defined structures or geometric patterns in datasets. For example, straight lines, circles, and ellipses represent meaningful structures in data collected from electron backscatter diffraction, particle accelerators, and clonogenic assays. Also, customers with similar behavior describe linear correlations in e-commerce databases. We describe a general approach for detecting data alignments in large unordered noisy multidimensional datasets. In contrast to classical techniques such as the Hough transforms, which are designed for detecting a specific type of alignment on a given type of input, our approach is independent of the geometric properties of the alignments to be detected, as well as independent of the type of input data. Thus, it allows concurrent detection of multiple kinds of data alignments, in datasets containing multiple types of data. Given its general nature, optimizations developed for our technique immediately benefit all its applications, regardless the type of input data. [Copyright &y& Elsevier]

Several cellular mechanisms affect nuclear morphology which can therefore be used to assess certain processes. Here, we present an analytic tool to quantify the number of cells in a population that present characteristics of senescence, apoptosis or nuclear irregularities through nuclear morphometric analysis. The tool presented here is based on nuclear image analysis and evaluation of size and regularity of adhered cells in culture. From 46 measurements of nuclear morphometry, principal component analysis filtered four measurements that best separated regular from irregular nuclei. These measurements, namely aspect, area box, radius ratio and roundness were combined into a single nuclear irregularity index (NII). Normal nuclei are used to set the parameters for a given cell type, and different nuclear phenotypes are separated in an area versus NII plot. The tool was validated with b-gal staining for senescence and annexin or caspases inhibitor for apoptosis as well as several treatments that induce different cellular phenotypes. This method provides a direct and objective way of screening normal, senescent, apoptotic and nuclear irregularities which may occur during failed mitosis or mitotic catastrophe, which may be very useful in basic and clinical research. [ABSTRACT FROM AUTHOR]

Abstract: The Hough transform (HT) is a popular tool for line detection due to its robustness to noise and missing data. However, the computational cost associated to its voting scheme has prevented software implementations to achieve real-time performance, except for very small images. Many dedicated hardware designs have been proposed, but such architectures restrict the image sizes they can handle. We present an improved voting scheme for the HT that allows a software implementation to achieve real-time performance even on relatively large images. Our approach operates on clusters of approximately collinear pixels. For each cluster, votes are cast using an oriented elliptical-Gaussian kernel that models the uncertainty associated with the best-fitting line with respect to the corresponding cluster. The proposed approach not only significantly improves the performance of the voting scheme, but also produces a much cleaner voting map and makes the transform more robust to the detection of spurious lines. [Copyright &y& Elsevier]

Abstract: Creating models of real scenes is a complex task for which the use of traditional modeling techniques is inappropriate. For this task, laser rangefinders are frequently used to sample the scene from several viewpoints, with the resulting range images integrated into a final model. In practice, due to surface reflectance properties, occlusions and accessibility limitations, certain areas of the scenes are usually not sampled, leading to holes and introducing undesirable artifacts in the resulting models. We present an algorithm for filling holes on surfaces reconstructed from point clouds. The algorithm is based on moving least squares and can interpolate both geometry and shading information. The reconstruction process is mostly automatic and the sampling rate of the given samples is preserved in the reconstructed areas. We demonstrate the use of the algorithm on both real and synthetic datasets to obtain complete geometry and plausible shading. [Copyright &y& Elsevier]

Describes a pipeline and a system implementation for improving model reconstruction from incomplete information available from range images in computer graphics. Algorithms for identifying approximate bilateral and rotational symmetric patterns in point clouds; Segmentation and reconstruction of planar surfaces; Texture reconstruction for planar areas.

• A fast cylinder detection technique which handles arbitrary cylinder directions. • A circle-recognition technique which is faster than traditional approaches. • A noise filtering strategy for circle recognition. • A false-positive test for cylinder detection. Cylinder detection is an important step in reverse engineering of industrial sites, as such environments often contain a large number of cylindrical pipes and tanks. However, existing techniques for cylinder detection require the specification of several parameters which are difficult to adjust because their values depend on the noise level of the input point cloud. Also, these solutions often expect the cylinders to be either parallel or perpendicular to the ground. We present a cylinder-detection technique that is robust to noise, contains parameters which require little to no fine-tuning, and can handle cylinders with arbitrary orientations. Our approach is based on a robust linear-time circle-detection algorithm that naturally discards outliers, allowing our technique to handle datasets with various density and noise levels while using a set of default parameter values. It works by projecting the point cloud onto a set of directions over the unit hemisphere and detecting circular projections formed by samples defining connected components in 3D. The extracted cylindrical surfaces are obtained by fitting a cylinder to each connected component. We compared our technique against the state-of-the-art methods on both synthetic and real datasets containing various densities and noise levels, and show that it outperforms existing techniques in terms of accuracy and robustness to noise, while still maintaining a competitive running time. [ABSTRACT FROM AUTHOR]

• An O(nlogn) plane detection technique virtually independent of parameter tuning. • A planarity test based on robust statistics which is robust to noise. • An iterative grow-merge procedure capable of retrieving delimited planar patches. Plane detection is a key component for many applications, such as industrial reverse engineering and self-driving cars. However, existing plane-detection techniques are sensitive to noise and to user-defined parameters. We introduce a fast deterministic technique for plane detection in unorganized point clouds that is robust to noise and virtually independent of parameter tuning. It is based on a novel planarity test drawn from robust statistics and on a split and merge strategy. Its parameter values are automatically adjusted to fit the local distribution of samples in the input dataset, thus leading to good reconstruction of even small planar regions. We demonstrate the effectiveness of our solution on several real datasets, comparing its performance to state-of-art plane detection techniques, and showing that it achieves better accuracy, while still being one of the fastest. [ABSTRACT FROM AUTHOR]

Although many adaptive sampling and reconstruction techniques for Monte Carlo (MC) rendering have been proposed in the last few years, the case for which one should be used for a specific scene is still to be made. Moreover, developing a new technique has required selecting a particular rendering system, which makes the technique tightly coupled to the chosen renderer and limits the amount of scenes it can be tested on to those available for that renderer. In this paper, we propose a renderer-agnostic framework for testing and benchmarking sampling and denoising techniques for MC rendering, which allows an algorithm to be easily deployed to multiple rendering systems and tested on a wide variety of scenes. Our system achieves this by decoupling the techniques from the rendering systems, hiding the renderer details behind an API. This improves productivity and allows for direct comparisons among techniques originally developed for different rendering systems. We demonstrate the effectiveness of our API by using it to instrument four rendering systems and then using them to benchmark several state-of-the-art MC denoising techniques and sampling strategies. [ABSTRACT FROM AUTHOR]

Image compositing combines visual elements from multiple images aiming to produce natural-looking results. Poisson-image-editing methods can generate seamless compositions, but introduce color changes in the inserted elements, which often generate unrealistic and unpleasing results. Recently, Henz et al. have presented an approach for controlling the amount of color changes in the inserted image patches (Henz et al., 2015 [1] ). We improve their work by using new sets of color basis vectors tailored to maximize color separation on transition zones, and by independently controlling the amount of adjustment on individual color channels. With our technique, artists have greater control over the final composites׳ color, besides significantly enhancing their freedom to achieve effects that were unreachable by previous methods. We performed two user studies to evaluate the perceptual effectiveness of the proposed technique. The studies show that our method provides the flexibility to produce even more natural and pleasing composites than previous seamless-cloning techniques. [ABSTRACT FROM AUTHOR]

We present a real-time technique for simulating accommodation and low-order aberrations (e.g., myopia, hyperopia, and astigmatism) of the human eye. Our approach models the corresponding point spread function, producing realistic depth-dependent simulations. Real-time performance is achieved with the use of a novel light-gathering tree data structure, which allows us to approximate the contributions of over 300 samples per pixel under 6 ms per frame. For comparison, with the same time budget, an optimized ray tracer exploring specialized hardware acceleration traces two samples per pixel. We demonstrate the effectiveness of our approach through a series of qualitative and quantitative experiments on images with depth from real environments. Our results achieved SSIM values ranging from 0.94 to 0.99 and PSNR ranging from 32.4 to 43.0 in objective evaluations, indicating good agreement with the ground truth. [ABSTRACT FROM AUTHOR]

Oral cancer is the sixth most common kind of human cancer. Brush cytology for counting Argyrophilic Nucleolar Organizer Regions (AgNORs) can help early mouth cancer detection, lowering patient mortality. However, the manual counting of AgNORs still in use today is time-consuming, labor-intensive, and error-prone. The goal of our work is to address these shortcomings by proposing a convolutional neural network (CNN) based method to automatically segment individual nuclei and AgNORs in microscope slide images and count the number of AgNORs within each nucleus. We systematically defined, trained and tested 102 CNNs in the search for a high-performing solution. This included the evaluation of 51 network architectures combining 17 encoders with 3 decoders and 2 loss functions. These CNNs were trained and evaluated on a new AgNOR-stained image dataset of epithelial cells from oral mucosa containing 1,171 images from 48 patients, with ground truth annotated by specialists. The annotations were greatly facilitated by a semi-automatic procedure developed in our project. Overlapping nuclei, which tend to hide AgNORs, thus affecting their true count, were discarded using an automatic solution also developed in our project. Besides the evaluation on the test dataset, the robustness of the best performing model was evaluated against the results produced by a group of human experts on a second dataset. The best performing CNN model on the test dataset consisted of a DenseNet-169 + LinkNet with Focal Loss (DenseNet-169 as encoder and LinkNet as decoder). It obtained a Dice score of 0.90 and intersection over union (IoU) of 0.84. The counting of nuclei and AgNORs achieved precision and recall of 0.94 and 0.90 for nuclei, and 0.82 and 0.74 for AgNORs, respectively. Our solution achieved a performance similar to human experts on a set of 291 images from 6 new patients, obtaining Intraclass Correlation Coefficient (ICC) of 0.91 for nuclei and 0.81 for AgNORs with 95% confidence intervals of [0.89, 0.93] and [0.77, 0.84], respectively, and p-values < 0.001, confirming its statistical significance. Our AgNOR-stained image dataset is the most diverse publicly available AgNOR-stained image dataset in terms of number of patients and the first for oral cells. CNN-based joint segmentation and quantification of nuclei and NORs in AgNOR-stained images achieves expert-like performance levels, while being orders of magnitude faster than the later. Our solution demonstrated this by showing strong agreement with the results produced by a group of specialists, highlighting its potential to accelerate diagnostic workflows. Our trained model, code, and dataset are available and can stimulate new research in early oral cancer detection. • A CNN architecture for automatic joint segmentation and counting of nuclei and AgNORs. • An AgNOR-stained image dataset from oral mucosa with 1,171 images from 48 patients. • Training and evaluation of 102 CNN models for AgNOR-stained image segmentation. • A semi-automatic image annotation strategy to reduce the workload from specialists to produce ground truth image annotations. • An algorithm to identify overlapping nuclei and exclude them from AgNOR counting. [ABSTRACT FROM AUTHOR]

Highlights • A portable, low-cost, easy-to-manufacture smartphone-based campimeter; • The results of our prototype are consistent with commercial campimeters (Pearson's coefficient > 0.98); • Its reproducibility is also comparable to commercial campimenters; • Given its portability and low cost, our mobile campimeter provides a promising alternative for patient screening in schools and community health centers; for visual evaluation of patients laying in beds or with mobility restrictions; for keeping track of the visual field at home; and for use in communities with limited access to medical services. Graphical abstract Abstract Campimetry is an important test to detect and monitor central and peripheral ocular dysfunctions, which might indicate the existence of serious conditions such as glaucoma, or the occurrence of strokes or brain tumors. Commercially-available campimeters are expensive and lack portability. We present a portable, low-cost, easy-to-manufacture smartphone-based campimeter. We evaluated our prototype in a user-study, which has shown that its results are consistent with the ones obtained with the Humphrey Field Analyzer - HFA II-i campimeter, with a Pearson correlation coefficient above 0.98 for all sampling positions on the visual field. Moreover, its reproducibility is also comparable to the Humprey campimeter. Given its portability and low cost, our mobile campimeter provides a promising alternative for patient screening in schools and community health centers, as well as for visual evaluation of patients with mobility restrictions, for keeping track of the visual field at home, and for use in communities with limited access to medical services. [ABSTRACT FROM AUTHOR]

The field of image composition is constantly trying to improve the ways in which an image can be altered and enhanced. While this is usually done in the name of aesthetics and practicality, it also provides tools that can be used to maliciously alter images. In this sense, the field of digital image forensics has to be prepared to deal with the influx of new technologies, in a constant arms-race. In this paper, the current state of this arms-race is analyzed, surveying the state-of-the-art. We provide a gentle introduction to both fields, along with theoretical grounding to aid the discussion. Experiments were performed to understand the impact of composition techniques on common forensics traces. We show that even though research in forensics is not focused on advanced forms of image composition, it possesses the basic tools to detect it. [ABSTRACT FROM AUTHOR]

Background: Retinal arterial narrowing is associated with higher office blood pressure (BP) and ambulatory blood pressure monitoring, and increased incidence of cardiovascular disease, but it is still unknown if the vessel caliber is associated with BP measured at the time of retinography acquisition. Methods: Retinal arteriolar and venular calibers were measured by the microdensitometric method in 448 patients with hypertension. Participants underwent 24-hours ambulatory blood pressure (24-h ABP) monitoring simultaneously with the retinography acquisition. Association between arteriolar and venular calibers with increase of 10 mmHg in the mean 24-hours, daily, and nightly BP, and with BP measured at the time of retinography, was evaluated by ANOVA and multivariate analyses. Results: Mean 24-hours, daytime and nighttime systolic and diastolic BP were inversely associated with the arteriolar caliber, but not with the venular caliber. Arteriolar caliber decreased -0.8 (95% CI -1.4 to -0.2) μm per 10-mmHg increase in 24-hours mean systolic BP, adjusted for age, gender, fellow vessel, and duration of hypertension (P = 0.01). The corresponding decreasing in arteriolar caliber by 10 mmHg of increasing in mean diastolic BP was -1.1 μm (-2.0 to -0.2, P = 0.02). The decrease of arteriolar caliber by the same increasing of BP measured at the time of retinography was lower and not statistically significant, particularly for mean diastolic BP and outer arterioles calibers: -1.0 (-1.8 to -0.2) μm in the daytime BP average versus -0.3 (-0.9 to 0.3) at the moment of retinography acquisition. Conclusions: These findings suggest that the caliber of arteriolar retinal vessels in patients with uncontrolled hypertension are not significantly influenced by blood pressure measured at the time of retinography acquisition. [ABSTRACT FROM AUTHOR]

Objective: Abnormalities in retinal vessels are frequent, but its association with findings in other vascular sites has been scarcely investigated. This study aimed to examine the association between ultrasound-measured carotid intima-media thickness (IMT) and retinal arteriolar and venular diameters, in hypertensive patients. Methods: In this cross-section study, 173 hypertensive patients had both retinography taken and digitized to determine vessel diameters by an edge-detecting computerized method and carotid ultrasound for semi-automated carotid IMT measurement. The association between the mean common carotid IMT and retinal arterioles and venules diameters was assessed by using multiple linear regression models. Results: The mean (±SD) arteriolar and venular diameters were 102. 8 (±11.6) μm and 128.9 (±15.5) μm, respectively, and common carotid IMT was 0.87 (±0.19) mm. A significant and independent association was demonstrated for carotid IMT and retinal arteriolar caliber (adjusted β −0.245, p = 0.001) and for carotid IMT and retinal venular caliber (adjusted β 0.191, p = 0.009) after controlling for age, gender, systolic blood pressure, total cholesterol and HDL (high-density lipoprotein) cholesterol, prior cardiovascular disease, carotid plaque and the retinal fellow vessel. Conclusion: In patients with hypertension, carotid intima-media thickness, a marker of macrovascular damage, is significantly and independently associated with microvascular damage, determined by retinal arteriolar and venular calibers. [ABSTRACT FROM AUTHOR]