Search

Pixel‐level labeling of regions of interest in an image is a key step in building a labeled training dataset for supervised deep learning networks of images. However, traditional manual labeling of cancerous regions in digital pathological images by doctors is time‐consuming and inefficient. To address this issue, this paper proposes an automatic labeling method for whole slide images, which combines clustering and edge detection techniques. The proposed method utilizes the multi‐level feature fusion model and the Long‐Short Term Memory network to discriminate the cancerous nature of the whole slide images, thereby improving the classification accuracy of the whole slide images. Subsequently, the automatic labeling of cancerous regions is achieved by integrating a density‐based clustering algorithm and an edge point extraction algorithm, both based on the discriminated results of the cancerous properties of whole slide images. The experimental results demonstrate the effectiveness of the proposed method, which offers an efficient and accurate solution to the challenging task of cancerous region labeling in digital pathological images. [ABSTRACT FROM AUTHOR]

License plate detection is an important task in Intelligent Transportation Systems (ITS) and has a wide range of applications in vehicle management, traffic control, and public safety. In order to improve the accuracy and speed of mobile recognition, an improved lightweight YOLOv5s model is proposed for license plate detection. First, an improved Stemblock network is used to replace the original Focus layer in the network, which ensures strong feature expression capability and reduces a large number of parameters to lower the computational complexity; then, an improved lightweight network, ShuffleNetv2, is used to replace the backbone network of the YOLOv5s, which makes the model lighter and ensures the detection accuracy at the same time. Then, a feature enhancement module is designed to reduce the information loss caused by the rearrangement of the backbone network channels, which facilitates the information interaction in the feature fusion process; finally, the low‐, medium‐ and high‐level features in the Shufflenetv2 network structure are fused to form the final high‐level output features. Experimental results on the CCPD dataset show that compared to other methods this paper obtains better performance and faster speed in the license plate detection task, in which the average precision mean value reaches 96.6%, and can achieve a detection speed of 43.86 frame/s, and the parameter volume is reduced to 5.07 M. [ABSTRACT FROM AUTHOR]

Image restoration with impulse noise is an important task in image processing. Taking into account the statistical distribution of impulse noise, the ℓ1‐norm data fidelity and total variation (ℓ1TV$\ell _1TV$) model has been widely used in this area. However, the ℓ1TV$\ell _1TV$ model usually performs worse when the noise level is high. To overcome this drawback, several nonconvex models have been proposed. In this paper, an efficient iterative algorithm is proposed to solve nonconvex models arising in impulse noise. Compared to existing algorithms, the proposed algorithm is a completely explicit algorithm in which every subproblem has a closed‐form solution. The key idea is to transform the original nonconvex models into an equivalent constrained minimization problem with two separable objective functions, where one is differentiable but nonconvex. As a consequence, the proximal linearized alternating direction method of multipliers is employed to solve it. Extensive numerical experiments are presented to demonstrate the efficiency and effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Neural architecture search can be used to find convolutional neural architectures that are precise and robust while enjoying enough speed for industrial image processing applications. In this paper, our goal is to achieve optimal convolutional neural networks (CNNs) for multiple‐templates matching for applications such as licence plates detection (LPD). We perform an iterative local neural architecture search for the models with minimum validation error as well as low computational cost from our search space of about 32 billion models. We describe the findings of the experience and discuss the specifications of the final optimal architectures. About 20‐times error reduction and 6‐times computational complexity reduction is achieved over our engineered neural architecture after about 500 neural architecture evaluation (in about 10 h). The typical speed of our final model is comparable to classic template matching algorithms while performing more robust and multiple‐template matching with different scales. [ABSTRACT FROM AUTHOR]

X‐ray flaw detection is widely used in non‐destructive area. The intuitive defect information can be obtained through the X‐ray film, which is usually digitized into high greyscale image by a 12‐bit or 16‐bit, called super 8‐bit, industrial scanner. When an ordinary 8‐bit monitor displays a super 8‐bit greyscale image, it appears loss of detail information, blurring of the image appears and other problems. Therefore, in this paper, a pseudo‐colour enhancement algorithm for displaying high‐bit RAW images on low‐bit monitor was proposed according to the chromatographic mapping relationship based on the visual characteristics of human eye. First, a high grey‐scale pseudo‐colour enhancement algorithm, called HOTM‐HGL, based on hot metal coding was proposed based on the standard film, whose enhancement effect is better than current mainstream algorithms. Second, aiming at the non‐standard film, a new stretching function called RAW‐Optical‐Stretching was reconstructed to improve HOTM‐HGL algorithm, called HOTM‐HGLS algorithm, whose display effect on ordinary monitors was improved in further. Finally, HOTM‐HGLS algorithm was applied in the detection of X‐ray film defect, which was convenient for the capture of defect information in the weld. Compared with the existing algorithms, various indicators have been greatly improved, enriching the amount of information and strengthening the image recognition effects. [ABSTRACT FROM AUTHOR]

In this paper, we take advantage of the reconstruction properties of the sampling Kantorovich (SK) algorithm to estimate the volume of the human brain for the quantification of Alzheimer's biomarkers. At first, the goodness of the reconstructions is evaluated, comparing it to different interpolation methods by means of the Peak Signal to Noise Ratio (PSNR) index; then the stereological Cavalieri/Point‐counting technique is used to infer volumetric data starting from the knowledge of the planar sections. The comparison of the achieved results with synthetic references confirms the good performances of the new methodology. [ABSTRACT FROM AUTHOR]

In this paper, a variable projection approach based on the BFGS (Broyden–Fletcher–Goldfarb–Shanno) method for image reconstruction problems is proposed, which is an alternative to the common alternating minimisation scheme. The image restoration is expressed as a nonlinear least‐squares problem with reduced parameter space. To improve the efficiency of the algorithm, the BFGS method is proposed to be used to optimise the reduced objective function. The large‐scale problem considered in this paper is projected on to a small Krylov subspace using Lanczos bidiagonalisation. The regularisation parameter is selected by a weighted generalised cross validation criterion. Numerical examples demonstrate the efficiency and effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

A common type problem of optimization is to find simultaneously n$$ n $$ parameters that globally minimize an objective function of n$$ n $$ variables. Such problems are seen in signal and image processing and in various applications of mathematical analysis of several complex variables and Clifford algebras. Objective functions are usually assumed to be Lipschitzian with maybe unknown Lipschitz constants. A number of methods have been established to discard the sets called "bad sets" in a partition that is impossible to contain any optimal point, as well as to treat the unknown Lipschitz bound problem along with the algorithm. In the present paper, a simple criterion of eliminating bad sets is proposed for the first time. The elimination method leads to a concise and rigorous proof of convergence. The algorithm, on the range space side, converges to the global minimum with an exponential rate, while on the domain space side, converges with equal accuracy to the set of all the global minimizers. To treat the unknown Lipschitz constant dilemma, we propose a practical pseudo‐Lipshitz bound process. The methodology is of fundamental nature with straightforward mathematical formulation applicable to multivariate objective functions defined on any compactly connected manifolds in higher dimensions. The method is tested against an extensive number of benchmark functions in the literature. The experimental results exhibit considerable effectiveness and applicability of the algorithm. [ABSTRACT FROM AUTHOR]

Crack detection in building structures is an important approach to evaluating the safety of these structures. However, in some cases under special circumstances, it is very difficult to identify all features of cracks by visual inspection. To tackle this problem and offer a higher potential for practical implementations, developing an automatic crack detection method seems essential. This paper establishes a novel algorithm for surface crack detection in building walls based on image processing techniques to enhance crack visibility. One of the most prevalent issues in surface crack detection from digital crack images is non‐uniform illumination of background which makes narrow and tiny cracks indistinguishable. In this regard, an integrated approach, combining adaptive image threshold using local first‐order statistics, contrast‐limited adaptive histogram equalization, and noise filtering using non‐linear diffusion filtering, is proposed to extract the whole skeleton of the crack from digital crack images with non‐uniform illumination. Several realistic crack images, suffering from noise and uneven lighting of background, are processed through the proposed algorithm to demonstrate the robustness and high accuracy of the method. [ABSTRACT FROM AUTHOR]

The Back‐Projection Algorithm (BPA) is a time‐domain‐matched filtering technique to form synthetic aperture radar (SAR) images. To produce high‐quality BPA images, precise navigation data for the radar platform must be known. Errors in position, velocity, or attitude result in improperly formed images that are corrupted by shifting and blurring. The contribution of this paper is the development of analytical expressions that characterise the relationship between navigation errors and image formation errors from an inertial navigation point of view, where trajectory estimation errors in position, velocity, and attitude propagate through time and cause compounding errors in the vehicle state vector. These analytical expressions are verified via simulated image formation and real‐data image formation. [ABSTRACT FROM AUTHOR]

Recently, image processing schemes are widely used to improve disease detection performance in many medicinal fields. Cancer is considered as one of the most deadly disease and early diagnosis of cancer is the complicated task in the field of medicine. In this paper, we present the two pretrained convolutional neural network (CNN) based on ensemble models such as VGG19 and VGG16 for cancer diagnosis that classifies both normal and abnormal images. The dilemma associated with CNN hyperparameter tuning complicates while diagnosing cancer. Hence, we propose multistrategy based artificial electric field (M‐AEF) algorithm for hyper‐parameter tuning in CNN thereby finding the optimal values. The exponentially decaying learning rates are more helpful to train CNN and prevent it from a local minimum. Thus, random minority over‐sampling and random majority under‐sampling address the imbalanced issue present in the dataset. The images are obtained from three different datasets namely the Kaggle dataset, International Collaboration on Cancer Reporting (ICCR) dataset, and cancer programming dataset for cancer detection. The experimental results are executed in MATLAB software and various performance analyses are carried out. Finally, the proposed method demonstrated better and higher cancer detection performance than other methods. [ABSTRACT FROM AUTHOR]

Summary: In this paper we describe an FPGA implementation of the Scale Invariant Feature Transform (SIFT) algorithm. The FPGA is required as its a lightweight device which makes it ideal for vision‐guided hybrid neuro‐prostheses utilised for upper limbs replacement. SIFT point detection is needed for computation of coordinates of the object‐to‐grasp in a wearable multi‐camera system. A modified SIFT algorithm is proposed and an implementation of it into C/C++ language on Xilinx ZCU102 FPGA board. The proposed hybrid hardware/software solution is compared to other hardware or hybrid implementations of the SIFT algorithm and with the baseline software detector OpenSIFT. The algorithm optimised for FPGA gives an average precision of 0.84 and the average recall of 0.94 in SIFT‐point detection compared to the baseline. The proposed solution has lower dissipated power than other solutions like CPU or GPU, and it has better computational speed. This solution allows for processing medium‐sized images in real‐time with low power consumption. [ABSTRACT FROM AUTHOR]

In this paper, we present a new algorithm for the detection of distorted and overlapping circlelike objects in noisy grayscale images. Its main step is an edge detection using rotated difference kernel estimators. To the resulting estimated edge points, circles are fitted in an iterative manner using a circular clustering algorithm. A new measure of similarity can assess the performance of algorithms for the detection of circlelike objects, even if the number of detected circles does not coincide with the number of true circles. We apply the algorithm to scanning electron microscope images of a high‐velocity oxygen fuel (HVOF) spray process, which is a popular coating technique. There, a metal powder is fed into a jet, gets accelerated and heated up by means of a mixture of oxygen and fuel, and finally deposits as coating upon a substrate. If the process is stopped before a continuous layer is formed, the molten metal powder solidifies in form of small, almost circular so‐called splats, which vary with regard to their shape, size, and structure and can overlap each other. As these properties are challenging for existing image processing algorithms, engineers analyze splat images manually up to now. We further compare our new algorithm with a baseline approach that uses the Laplacian of Gaussian blob detection. It turns out that our algorithm performs better on a set of test images of round, spattered, and overlapping circles. [ABSTRACT FROM AUTHOR]

Abstract: This paper reports the latest developments for the photogrammetric open‐source tool called GRAPHOS (inteGRAted PHOtogrammetric Suite). GRAPHOS includes some recent innovations in the image‐based 3D reconstruction pipeline, from automatic feature detection/description and network orientation to dense image matching and quality control. GRAPHOS also has a strong educational component beyond its automated processing functions, reinforced with tutorials and didactic explanations about algorithms and performance. The paper highlights recent developments carried out at different levels: graphical user interface (GUI), didactic simulators for image processing, photogrammetric processing with weight parameters, dataset creation and system evaluation. [ABSTRACT FROM AUTHOR]

The affinity propagation algorithm has been extensively applied in various fields. However, it is still faces two severe challenges in actual applications: one is that the algorithm may be nonconvergent; and the other is that the convergence speed is low. Aiming at solving these two problems, an adaptive affinity propagation algorithm based on a new strategy of dynamic damping factor and preference is proposed in this paper. On one hand, the dynamic damping factor changes the factor value according to the check state of oscillation to eliminate and escape from the oscillation. On the other hand, dynamic preference adjusts the value of the preference based on the bisection and memory tuple to reduce the search scope of the target preferences continuously. Simulation results show that the proposed algorithms can solve the potential nonconvergence problem effectively and reduce the time consumed significantly. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc. [ABSTRACT FROM AUTHOR]

Summary: This paper presents an algorithm with low computational complexity for classifying and recognizing characters based on a random sampling and high‐dimensional binary spaces for the development of real‐time applications. Character classification is performed using uniform random sampling as the feature selection process, subsequently performing encoding as binary strings. Associative memories are commonly used as general classifiers with linear criteria to discriminate between data points. In most classifiers, the ability to efficiently detect class membership depends entirely on the expressiveness of the attributes used to encode the data. Each binary pattern encodes the distinct characteristics of several glyphs. Character features are represented as elements of a high‐dimensional binary space, where a criterion of the cluster is defined under the L1 metric. The reduction in computational complexity is analyzed. The reduction in the number of character features through random sampling techniques makes it feasible to manage all the character information in physical architectures; therefore, this approach might use resources on a hardware platform with integer operators typically implemented at the hardware‐register level. Finally, this approach is implemented in a parallel architecture Field‐Programmable Gate Array (FPGA) and tested using a Database (DB) of different fonts, including distortions, therein showing that the efficiency is comparable to the other well‐known approaches. [ABSTRACT FROM AUTHOR]

Summary: This paper proposes an all‐hardware architecture to perform the subpixel refinement operation in the scale invariant transform algorithm. Although the literature describes several hardware implementations of this algorithm, due to its complexity, most of them are based on simplifications of it. These implementations normally exclude the subpixel refinement stage, which, however, is an essential process to obtain accurate results in image matching applications.The architecture has been described in very high–speed integrated circuit hardware description language at register transfer level and synthesized on a Xilinx Zynq 7020 device. The latency of the proposed architecture to generate a refinement operation is 211 clock cycles, and the throughput achieved exploiting pipeline techniques is 64 cycles. The architecture uses fixed‐point data representation and has been tested with images from known databases, yielding very good performance compared with the floating‐point software implementation of the algorithm. [ABSTRACT FROM AUTHOR]

Organic light-emitting diode (OLED) aging is the root cause for image sticking artifact and considered as the toughest problem besides the low yield problem of active-matrix organic light-emitting diode (AMOLED) displays. Digital driving can eliminateMura artifact and allow a similar yield like LCD. However, it is more prone toOLED aging than analog driving, so that the lifetime will become shorter. In this paper, we pursue the approach to measure the pixel current and compensate OLED I-V drift. Information gained from electrical measurements during the lifetime of the display may be correlated to electro-optical drift, particularly the current efficiency. The aging model has to consider the dependence of I-V drift and efficiency loss on the operation point/voltage for each subframe. Specific compensation algorithms have been developed. Two AMOLED prototypes (1.5 and 2.8 in.) were validated. Burned-in pattern can be compensated, so the concept has been proven as effective. With the method described in this paper, digital AMOLED may reach a similar and even significantly higher lifetime than an analog AMOLED. [ABSTRACT FROM AUTHOR]

Example-based methods are widely adopted in image super-resolution (SR) to generate clear, high-resolution (HR) images from low-resolution (LR) images. This paper reports our study of example-based algorithms on LR facial images that exploit the relationship between LR and HR image patch pairs in a database using a Markov random field (MRF) model. We aimed to restore each part in a face with patches related to the parts. We generated patches with information on their original positions from a set of normalized facial images where their facial feature points were approximately in the same position. The nearer candidate patch's position to the target position yielded higher compatibility of the facial parts. Our algorithm restored LR images by combining the proposed facial parts' compatibility function with the conventional function to find the best set of estimated HR patches. The final SR results were obtained by stitching the inferred HR patches from an iteration process. An experiment on a set of facial images demonstrates that the combined compatibility function achieves the best quality in the resulting image, i.e. 30.39 [dB], in terms of the peak signal-to-noise ratio (PSNR) compared to the previously achieved quality of 29.65 [dB]. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc. [ABSTRACT FROM AUTHOR]

In this paper, an RGB-to-RGBG conversion algorithm based on the weighting factor (WF) has been proposed. The gray level of each RGBG sub-pixel is represented by the weighted sum of the original gray levels. The weighting factors are adaptively calculated by minimizing the square error. Furthermore, the color fringing artifact is significantly improved by using this method. Peak signal-to-noise ratio of U component and peak signal-to-noise ratio of V component of the image processed by WF is larger than that processed by direct assignment and FRB. The mean square error of the image processed by the WF is 14% and 53% smaller than that of image processed by direct assignment and FRB, respectively. The proposed algorithm has been implemented on a field-programmable gate array, and the displayed image has good visual effect. [ABSTRACT FROM AUTHOR]

This paper studies the applicability of the Mean Shift algorithm as support in interpreting geophysical images produced, on this occasion, from magnetic prospection data. The data obtained from a magnetic survey carried out in Gilena (Seville province, Spain) by the La Rábida Archaeophysics Group will be used for the research. Its applicability is illustrated by comparing, on the one hand, some reduction-to-pole algorithms and on the other, the (well-known) k-means algorithm. Finally, the paper shows the results obtained by applying the Mean Shift algorithm as an alternative method to 'unsupervised clustering' of anomalies that appear in images obtained from geophysical data, in which the a priori knowledge of the number of classes is difficult or impossible. [ABSTRACT FROM AUTHOR]

This paper illustrates the use of image processing techniques for separating seismic waves. Because of the non-stationarity of seismic signals, the continuous wavelet transform is more suitable than the conventional Fourier transforms for the representation, and thus the analysis, of seismic processes. It provides a 2D representation, called a scalogram, of a 1D signal where the seismic events are well localized and isolated. Supervised methods based on this time-scale representation have already been used to separate seismic events, but they require strong interactions with the geophysicist. This paper focuses on the use of the watershed algorithm to segment time-scale representations of seismic signals, which leads to an automatic estimation of the wavelet representation of each wave separately. The computation of the inverse wavelet transform then leads to the reconstruction of the different waves. This segmentation, tracked over the different traces of the seismic profile, enables an accurate separation of the different wavefields. This method has been successfully validated on several real data sets. [ABSTRACT FROM AUTHOR]

Uncontrolled illumination is one of the most widely researched and most encountered face recognition challenges in recent years. In this study, the authors propose the division of algorithms into two categories: (i) relighting and (ii) unlighting. Relighting methods try to match the probe's illumination conditions using a subset of representative gallery images, while unlighting methods seek to suppress the variations. A total of 64 state-of-the-art methods are summarised and categorised in each of the groups. To make this work concise and easy to follow, they restricted themselves to selected conferences/journals and they limited the number of approaches reviewed. Also, eight past state-of-the-art approaches are used in both identification and verification experiments. However, only significant reported results from all methods were compared and organised in tables. The author's main objective is not to provide an exhaustive analysis of each category, but to present a collection of papers that can be useful in identifying research directions. Results indicate that unlighting methods are a better and a practical solution to address illumination challenges. [ABSTRACT FROM AUTHOR]

In high-efficient motion picture coding such as systems to compress moving image information below several 100 kbit/s, some visible spatial and temporal distortions are unavoidable. The spatial distortion is perceived by humans as a spatial degradation or noise on the image. On the other hand, the temporal distortion, which is caused by frame dropping, occurs as unnaturalness of motions in the processed image sequence. Here, spatial and temporal distortions are in a trade-off relationship. Finding the visually best point from this trade-off is a key feature of good codees. This paper describes a newly developed coding control algorithm aimed at keeping spatial and temporal distortions in a good balance. In the algorithm, the trade-off relationship is calculated first from generated information amount vs. the SNR characteristics of the current input frame. Next, an optimal distribution is determined from the viewpoint of human perception. Finally, a coding parameter set is chosen for realizing the distribution and reproduces visually good images. This paper shows the principal of the coding control algorithm and describes an application of the algorithm to an MC-DCT coding system and simulation results. [ABSTRACT FROM AUTHOR]

SUMMARY Efficient interactive foreground extraction from color images is of great practical importance in computer vision. In recent years, an approach based on optimization using graph-cuts has been widely used. However, an interactive foreground extraction approach, which is intuitive and efficient for users, is required for practical applications. In this paper, we propose a novel interactive foreground extraction method based on color saliency. In our method, the user provides only some foreground pixels as the initial reference. To achieve extraction of multiple target objects, the likelihoods of the foreground and background are defined by a Gaussian mixture model and a color saliency map based on the provided reference pixels. These likelihoods are added to the cost of the proposed graph. Finally, image segmentation is performed by optimizing the proposed graph using the graph-cut algorithm. [ABSTRACT FROM AUTHOR]

ABSTRACT In circular synthetic aperture radar (CSAR), targets are usually scanned over the complete azimuthal aperture of 360°. A major challenge inhibiting successful CSAR image production is encountered in two-dimensional imaging of relatively large scenes (i.e. wide-field scenarios). For such cases, the spatially variant radar signature gives rises to image degradations known as layover effects. In this paper, the imaging results for hypothetical and real complex targets using their CSAR data at C band are demonstrated to characterize these effects. In real experiments, a ground-based, outdoor CSAR system is exploited thanks to the circular balcony of a building that provides 270° view of targets. A spherical back-projection algorithm is used to focus near-field data and the reconstructed images are also cleaned out from clutter to more easily visualize the layover artifacts. © 2015 Wiley Periodicals, Inc. Microwave Opt Technol Lett 57:489-497, 2015 [ABSTRACT FROM AUTHOR]

In this paper, we concentrate on the maximal inclusion problem of locating the zeros of the sum of maximal monotone operators in the framework of proximal point method. Such problems arise widely in several applied mathematical fields such as signal and image processing. We define two new maximal monotone operators and characterize the solutions of the considered problem via the zeros of the new operators. The maximal monotonicity and resolvent of both of the defined operators are proved and calculated, respectively. The traditional proximal point algorithm can be therefore applied to the considered maximal inclusion problem, and the convergence is ensured. Furthermore, by exploring the relationship between the proposed method and the generalized forward-backward splitting algorithm, we point out that this algorithm is essentially the proximal point algorithm when the operator corresponding to the forward step is the zero operator. Copyright © 2013 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Subjective pattern recognition is a class of pattern recognition problems, where we not only merely know a few, if any, the strategies our brains employ in making decisions in daily life but also have only limited ideas on the standards our brains use in determining the equality/inequality among the objects. Face recognition is a typical example of such problems. For solving a subjective pattern recognition problem by machinery, application accuracy is the standard performance metric for evaluating algorithms. However, we indeed do not know the connection between algorithm design and application accuracy in subjective pattern recognition. Consequently, the research in this area follows a 'trial and error' process in a general sense: try different parameters of an algorithm, try different algorithms, and try different algorithms with different parameters. This phenomenon can be observed clearly in the nearly 30 years research of the face recognition: although huge advances have been made, no algorithm has ever been shown a potential to be consistently better than most of the algorithms developed earlier; it was even shown that a naïve algorithm can work, in the sense of accuracy, at least no worse than many newly developed ones in a few benchmarks. We argue that, the primary objective of subjective pattern recognition research should be moved to theoretical robustness from application accuracy so that we can evaluate and compare algorithms without or with only few 'trial and error' steps. We in this paper introduce an analytical model for studying the theoretical stabilities of multicandidate Electoral College and Direct Popular Vote schemes (aka regional voting scheme and national voting scheme, respectively), which can be expressed as the a posteriori probability that a winning candidate will continue to be chosen after the system is subjected to noise. This model shows that, in the context of multicandidate elections, generally, Electoral College is more stable than Direct Popular Vote, that the stability of Electoral College increases from that of Direct Popular Vote as the size of the subdivided regions decreases from the original nation size, up to a certain level, and then the stability starts to decrease approaching the stability of Direct Popular Vote as the region size approaches the original unit cell size; and that the stability of Electoral College approaches that of Direct Popular Vote in the two extremities as the region size increases to the original national size or decreases to the unit cell size. It also shows a special situation of white noise dominance with negligibly small concentrated noise, where Direct Popular Vote is surprisingly more stable than Electoral College, although the existence of such a special situation is questionable. We observe that 'high stability' in theory indeed always reveals itself in 'high accuracy' in applications. Extensive experiments on two human face benchmark databases applying an Electoral College framework embedded with standard baseline and newly developed holistic algorithms have been conducted. The impressive improvement by Electoral College over regular holistic algorithms verifies the stability theory on the voting systems. It also shows an evidential support for adopting theoretical stability instead of application accuracy as the primary objective for subjective pattern recognition research. [ABSTRACT FROM AUTHOR]

Position angle measurements of Sloan Digital Sky Survey (SDSS) galaxies, as measured by the surface brightness profile fitting code of the SDSS photometric pipeline (Lupton et al. 2001), are known to be strongly biased, especially in the case of almost face-on and highly inclined galaxies. To address this issue we developed a reliable algorithm which determines position angles by means of isophote fitting. In this paper we present our algorithm and a catalogue of position angles for 26397 SDSS galaxies taken from the deep co-added Stripe 82 (equatorial stripe) images. Data are published on-line at http://www.vo.elte.hu/galmorph. (© 2013 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim) [ABSTRACT FROM AUTHOR]

Purpose: The most common metrics for resolution analysis in medical imaging are valid only for (approximately) linear systems. While analogues to these metrics have been used in attempts to describe resolution performance in nonlinear systems, the analysis is incomplete since distortion effects are often ignored. The authors have developed a methodology to analyze the amplitude modulation and waveform distortion properties of nonlinear systems with specific application to medical image processing algorithms. Methods: Using sinusoidal basis functions, two metrics were derived which distinguish amplitude modulation from nonlinear waveform distortion: principle frequency response and distortion power spectrum, respectively. Additionally, two figures of merit were developed to describe the relative impact of nonlinear distortion as a result of image processing: distortion index (DI) and ΣDI. Three nonlinear denoising algorithms, the median, bilateral, and wavelet denoising filters, were selected as example functions to demonstrate the utility of the metrics derived in this study. Results: Each filter showed very different resolution and waveform distortion properties. In particular, the amplitude and extent of nonlinear distortion depended strongly on image context and the type of nonlinear mechanism employed. Nonlinear waveform distortion constituted up to 30% of the median filter output signal power in high contrast-to-noise ratio (CNR) scenarios. Conversely, nonlinear distortion never exceeded 1% of the bilateral filter output signal power. The wavelet denoising response contained between 1% and 9% distortion which varied weakly as a function of CNR. Conclusions: The analytical metrics described in the paper demonstrate the importance of considering both resolution- and distortion-related effects in characterizing the performance of nonlinear imaging systems with specific application to image processing algorithms. Findings with three common nonlinear algorithms demonstrate a range of CNR values over which it is important to consider the impact of the nonlinear nature of each algorithm. Background context is also shown to influence the degree to which the nonlinear nature of the algorithm influences resolution and distortion. While no single metric can yet anticipate observer performance in nonlinear systems, the approach described can demonstrate the range of imaging contexts over which such nonlinear effects are important to consider. [ABSTRACT FROM AUTHOR]

Soil erosion is defined as a displacement of solid particles originating from soil, rock and other sediments by the forces of wind and water. Erosion affects soil micro-topography and surface roughness and may lead to clogging of drainage systems, flooding and destruction of the upper part of the soil structure, thereby causing damage to cultivated land. Thus, quantification of changes in the amount and rate of soil erosion is vital for agricultural planning as well as for setting up different soil-conservation systems. This paper describes an image-based scheme for quantifying amounts of erosion and estimating the change in volume of raised beds resulting from irrigation or rainstorms in cultivated fields. Unlike existing methods that are labour-intensive and error-prone, the proposed approach is autonomous, accurate and can be applied with low-cost digital cameras. Emphasis is placed on robustness to actual field conditions, including variations in illumination and shading and imaging from general vantage points. To accommodate varying field conditions, we propose the use of colour image-processing, illumination-invariant algorithms and linear photogrammetric models. Linear models eliminate the complex task of approximating camera-position parameters, and introduction of colour-driven image processing facilitates a computationally robust algorithm for volume estimation. Thus, the end-product is a model that can be used by those who are unskilled in photogrammetry and image processing, with little or no guidance. Experiments show that estimates of volume and erosion reach accuracy levels of about 0.07 m3 ha−1. [ABSTRACT FROM AUTHOR]

Seals have been frequently used to certify that individuals or organizations have authorized or approved a document that bears these impressions. Much attention has been focused on the detection of forged seal impressions to expose and prevent seal-related frauds. This paper describes an image-processing technique that detects seal impressions transferred from a genuine document to a target document using transcription media. The proposed method utilizes a three-dimensional (3-D) scanner to generate a pressure trace map of the suspect seal impression. After utilizing a noise-reduction algorithm to improve image quality, the pressure map is aligned with a 2-D image of the same seal impression. The pressure ratio, determined by comparing the pressure map and inked impression of a suspect seal, can be used to determine whether the seal is genuine or was transferred to the target document. The results show that the proposed technique successfully identified transcribed seal impressions with an error rate of <1%. [ABSTRACT FROM AUTHOR]

By the term 'personal vehicle,' we mean a simple and lightweight vehicle expected to emerge as a personal ground transportation device. The motorcycle, electric wheelchair, and motor-powered bicycle are examples of the personal vehicle and have been developed for personal transportation use. Recently, a new type of intelligent personal vehicle called the Segway has been developed, which is controlled and stabilized by using on-board intelligent multiple sensors. The demand for such personal vehicles is increasing: (1) to enhance human mobility, (2) to support mobility for elderly persons, and (3) to reduce environmental load. With the rapid growth of the personal vehicle market, the number of accidents caused by human error is also increasing. These accidents are associated with driving capabilities; to enhance or support driving capabilities as well as to prevent accidents, intelligent assistance is necessary. One of the most important elementary functions for personal vehicles is robust lane detection. In this paper, we develop a robust lane detection method for personal vehicles in outdoor environments. The proposed lane detection method employs a 360° omnidirectional camera and unique robust image processing algorithm. In order to detect lanes, a combination of the template matching technique and the Hough transform is employed. The validity of the proposed lane detection algorithm was confirmed with a prototype vehicle under various types of sunshine conditions. © 2011 Wiley Periodicals, Inc. Electr Eng Jpn, 177(4): 23-32, 2011; Published online in Wiley Online Library (). DOI 10.1002/eej.21193 [ABSTRACT FROM AUTHOR]

Purpose: Image segmentation techniques using fuzzy connectedness (FC) principles have shown their effectiveness in segmenting a variety of objects in several large applications. However, one challenge in these algorithms has been their excessive computational requirements when processing large image datasets. Nowadays, commodity graphics hardware provides a highly parallel computing environment. In this paper, the authors present a parallel fuzzy connected image segmentation algorithm implementation on NVIDIA's compute unified device Architecture (cuda) platform for segmenting medical image data sets. Methods: In the FC algorithm, there are two major computational tasks: (i) computing the fuzzy affinity relations and (ii) computing the fuzzy connectedness relations. These two tasks are implemented as cuda kernels and executed on GPU. A dramatic improvement in speed for both tasks is achieved as a result. Results: Our experiments based on three data sets of small, medium, and large data size demonstrate the efficiency of the parallel algorithm, which achieves a speed-up factor of 24.4x, 18.1x, and 10.3x, correspondingly, for the three data sets on the NVIDIA Tesla C1060 over the implementation of the algorithm on CPU, and takes 0.25, 0.72, and 15.04 s, correspondingly, for the three data sets. Conclusions: The authors developed a parallel algorithm of the widely used fuzzy connected image segmentation method on the NVIDIA GPUs, which are far more cost- and speed-effective than both cluster of workstations and multiprocessing systems. A near-interactive speed of segmentation has been achieved, even for the large data set. [ABSTRACT FROM AUTHOR]

In this paper a novel parameter optimization approach for cell detection tool and counting cells procedure in phase contrast images are presented. Manual counting of the attached cells in phase contrast images is time-consuming and subjective. For evaluation of electroporation efficiency of attached cells, we often perform manual counting of the cells which is needed to determine the percentage of electroporated cells under different experimental conditions. Here we present an automated cell counting procedure based on novel artificial neural network optimization of Image-based Tool for Counting Nuclei algorithm parameters to fit the training image set based on counts from an expert. Comparing the results of automated cell counting to user manual counting a 90,31% average agreement was achieved which is reasonably good especially taking into account inter-person error which can be up to 10%. Even more, our procedure can also be used for fluorescent cell images with similar counting accuracy (>90%) enabling us to determine electroporation efficiency. In our experiments, the electroporation efficiency determined by manual cell counting was virtually the same as the one obtained by the automated procedure. [ABSTRACT FROM AUTHOR]

There are many cases where it is desirable to reconstruct at high resolution a small volume from a larger sample. Here we describe the outcomes of a reconstruction trial based on real samples aimed at delineating the practical limits to which a small region of interest can be viewed from a large sample. Our approach has been to artificially truncate the sinograms of whole sample scans to simulate region of interest tomography. A simple filtered back projection algorithm has been applied, with the sinograms extended laterally in a simple manner to make up for the truncated portions. The impact of the degree of truncation (from 0% down to 99%), the number of projections used, as well as the position of the region of interest, on the faithfulness of the reconstruction is evaluated for a range of sample types. We have assessed the nature of, and extent to which, artefacts are introduced and the degree to which simple strategies can minimize them to an acceptable level without the need for complex reconstruction algorithms, projection stitching strategies or very large detectors. It is found that for a wide range of objects the effect of truncation on feature detection is negligible and that excellent images can be reconstructed if the number of projections is calculated not on the basis of the number of pixels on the camera, but on the number of pixels that would be required to scan the whole sample at the chosen pixel resolution. This paper demonstrates that in many cases more sophisticated reconstruction strategies are not necessary. [ABSTRACT FROM AUTHOR]

Image processing is generally based on grayscale information, such as statistical gray histograms, gradients, textures, etc. However, concrete techniques that use this co-occurrence processing have been chiefly limited to texture identification. Since the gray histogram is the most influential for extracting the global image properties, it has always been desirable to improve or extend it. From this viewpoint, Kashiwagi's proposal of a new frequency extraction paradigm called the frequency image (FI) is noteworthy. Along with other histograms, the co-occurrence histogram or co-occurrence matrix is also an influential basic image feature, especially for texture feature analysis. In this paper we introduce a new texture feature image paradigm called the 'co-occurrence frequency image' (CFI), which is a complete extension of the FI. © 2010 Wiley Periodicals, Inc. Electron Comm Jpn, 93(12): 50-59, 2010; Published online in Wiley Online Library (). DOI 10.1002/ecj.10145 [ABSTRACT FROM AUTHOR]

During a dynamic mechanical loading, we cannot use a phase-shifting technique because the mechanical parameters evolve according to the time. This problem can be avoided by the development of algorithms which can extract the mechanical information from only one fringe pattern. In this way, we present two algorithms, the modulated phase correlation (MPC) and the polynomial modulated phase correlation (pMPC). These processes are based on the use of the virtual fringe pattern which locally approaches the real fringe morphology. The similarity degree between real and virtual fringe pattern is estimated by digital correlation technique. When the best similarity is obtained, we suppose that the virtual phase function is very close to the real phase function. Some examples are presented to show the low noise sensitivity of these techniques. So, we propose to use the MPC or the pMPC algorithms to extract the relief from a single interferogram obtained by digital speckle-pattern interferometry. In this paper, we present experimental tests of impact loading on plates. The frame rate is adapted to the dynamic conditions of loading. Recorded fringe patterns and results of the unwrapped phase demodulated with our algorithms are shown. [ABSTRACT FROM AUTHOR]

Although automated object surface reconstruction via feature-based matching is commonly employed in both stereoscopic close range and topographic photogrammetry, it has rarely been used in conjunction with multi-image, convergent photogrammetric networks. A prerequisite for feature-based matching of distinct points is the application of interest operators to provide the dense arrays of candidate feature points within the images forming the network. This paper describes an evaluation of three interest operators, the Förstner, SUSAN and FAST algorithms, the aim being to assess which is optimal for feature-based matching in convergent close range photogrammetry. Following a brief review of the development of interest operators, a description of the three operators is provided, with the recently developed FAST operator being discussed in more detail. The merits of image pre-processing via the Wallis filter are also outlined, after which the performance of the interest operators is experimentally assessed within an eight-image network on the basis of accuracy of interest-point localisation, detection rate and speed. The findings of the evaluation are that, of the Förstner, SUSAN and FAST operators, the FAST, which has not been employed to a significant extent in photogrammetry to date, is optimal for feature-based matching in multi-image close range networks. [ABSTRACT FROM AUTHOR]

3D image processing algorithms for real-time calibration of the baseline length in a single-camera stereo system are presented in this paper, and the performance of less than 0.03 mm depth measurement in precision and about 0.45 s processing time in the inspection are also presented based on the applications to the experimental equipment. It is technically noted that the baseline of this single-camera stereo system was precisely calibrated by the image processing procedure. The scope of application of this simply configured stereo system could be expanded to the wider fields of industrial 3D measurements. © 2009 Wiley Periodicals, Inc. Electron Comm Jpn, 92(12): 50–59, 2009; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecj.10155 [ABSTRACT FROM AUTHOR]

In recent years, cell biologists have benefited greatly from using confocal microscopy to study intracellular organelles. For high-level image analysis, 3D boundary extraction of cell structure is a preliminary requisite in confocal cellular imaging. To detect the object boundaries, most investigators have used gradient/Laplacian operator as a principal tool. In this paper we propose a higher order statistics (HOS) based boundary extraction algorithm for confocal cellular image data set using kurtosis. After the initial pre-processing, kurtosis boundary map is estimated locally for the entire volume using a cubic sliding window and subsequently the noisy kurtosis value is removed by thresholding. Voxels having positive kurtosis value with zero-crossing on its surface are then identified as boundary voxels. Typically used in signal processing, kurtosis for 3D cellular image processing is a novel application of HOS. Its reliable and robust nature of computing makes it very suitable for volumetric cellular boundary extraction. [ABSTRACT FROM AUTHOR]

Common methods for quantification of colocalization in fluorescence microscopy typically require cross-talk free images or images where cross-talk has been eliminated by image processing, as they are based on intensity thresholding. Quantification of colocalization includes not only calculating a global measure of the degree of colocalization within an image, but also a classification of each image pixel as showing colocalized signals or not. In this paper, we present a novel, automated method for quantification of colocalization and classification of image pixels. The method, referred to as SpecDec, is based on an algorithm for spectral decomposition of multispectral data borrowed from the field of remote sensing. Pixels are classified based on hue rather than intensity. The hue distribution is presented as a histogram created by a series of steps that compensate for the quantization noise always present in digital image data, and classification rules are thereafter based on the shape of the angle histogram. Detection of colocalized signals is thus only dependent on the hue, making it possible to classify also low-intensity objects, and decoupling image segmentation from detection of colocalization. Cross-talk will show up as shifts of the peaks of the histogram, and thus a shift of the classification rules, making the method essentially insensitive to cross-talk. The method can also be used to quantify and compensate for cross-talk, independent of the microscope hardware. [ABSTRACT FROM AUTHOR]

In a range of imaging problems, particularly those where the images are of man-made objects, edges join at points which comprise three or more distinct boundaries between textures. In such cases the set of edges in the plane forms what a mathematician would call a planar graph. Smooth edges in the graph meet one another at junctions, called ‘vertices’, the ‘degrees’ of which denote the respective numbers of edges that join there. Conventional image reconstruction methods do not always draw clear distinctions among different degrees of junction, however. In such cases the algorithm is, in a sense, too locally adaptive; it inserts junctions without checking more globally to determine whether another configuration might be more suitable. In this paper we suggest an alternative approach to edge reconstruction, which combines a junction classification step with an edge-tracking routine. The algorithm still makes its decisions locally, so that the method retains an adaptive character. However, the fact that it focuses specifically on estimating the degree of a junction means that it is relatively unlikely to insert multiple low-degree junctions when evidence in the data supports the existence of a single high-degree junction. Numerical and theoretical properties of the method are explored, and theoretical optimality is discussed. The technique is based on local least-squares, or local likelihood in the case of Gaussian data. This feature, and the fact that the algorithm takes a tracking approach which does not require analysis of the full spatial data set, mean that it is relatively simple to implement. [ABSTRACT FROM AUTHOR]

In this paper, we consider the approximation of dense block Toeplitz-plus-Hankel matrices by sums of Kronecker products of Toeplitz-plus-Hankel matrices. We present an algorithm for efficiently computing the matrix approximation that requires the factorization of matrices of much smaller dimension than that of the original. The main results are described for block Toeplitz matrices with Toeplitz-plus-Hankel blocks, but the algorithms can be readily adjusted for other related structures that arise in image processing applications, such as block Toeplitz with Toeplitz blocks and block Toeplitz-plus-Hankel with Toeplitz-plus-Hankel blocks. Our work extends the techniques in Kamm and Nagy (SIAM J. Matrix Anal. Appl. 2000; 22:155–172) and Nagy et al. (SIAM J. Matrix Anal. Appl. 2004; 25:829–841), which consider similar matrices, but with the added restriction that the matrices have a banded/block-banded structure. We illustrate the effectiveness of our algorithm by using the output of the algorithm to construct preconditioners for systems from two different applications: diffuse optical tomography and atmospheric image deblurring. Copyright © 2007 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Segmentation of crossing fibres is a complex problem of image processing. In the present paper, various solutions are presented basing on tools of morphological image processing. Two new image transforms are introduced – the lineal distance transform and the chord length transform. Both transforms are applied to two-dimensional images and their results are three-dimensional images. Thus, the segmentation problem originally formulated for crossing fibres observed in a two-dimensional image can be reformulated as a segmentation problem in a three-dimensional image. This can be solved by a segmentation in the three-dimensional image. Algorithms for the lineal distance transform and the chord length transform are given and their use in image analysis is demonstrated. Furthermore, the chord length distribution function of the foreground of a binary image can efficiently be estimated via the chord length transform. [ABSTRACT FROM AUTHOR]

Airborne topographic data collection requires removal of errors that arise due to surface features that obstruct the ground from the sensor. Typically, this has been based on manual correction and/or automated filtering. To some degree, the latter has provided a method for identifying and removing unwanted surface obstructions in large topographic data-sets. However, the algorithms used are unintelligent in that they cannot reliably differentiate between the various types of obstructions and the ground. If coincident optical support imagery is available, the use of intelligent correction routines becomes possible. This paper describes an automated approach for removing obstruction errors using optical support imagery and simple image processing routines. Orthorectification and classification of support imagery enable obstruction errors to be identified in the digital surface model (DSM) and corrected intelligently to produce a digital terrain model (DTM). The results show that support imagery can be used with basic image processing routines to remove obstructions intelligently and automatically from large topographic data-sets. Since the approach can differentiate between types of obstructions, the removal of each type of error can be customised, making this a very flexible approach to topographic data correction. [ABSTRACT FROM AUTHOR]

In this paper, we propose a thresholding algorithm. This algorithm works under a severe constraint: each pixel in a processed image must be derived from only information of its neighboring pixels. This constraint is very important for a low-cost device such as a mobile camera, because it makes it possible to process each pixel in parallel. The proposed algorithm deals with gray-scale images, and determines the threshold based on edge information. The proposed algorithm is represented by local and parallel image processing and has been tested using 104 scenery images. The result shows that the proposed algorithm can binarize images. © 2006 Wiley Periodicals, Inc. Electr Eng Jpn, 157(2): 50–56, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/eej.20267 [ABSTRACT FROM AUTHOR]

Gradients play an important role in 2D image processing. Many edge detection algorithms are gradient-based. We are interested in 3D boundary detection which can be considered as an extension of 2D edge detection in 3D space. In this paper, an algorithm to automatically and quantitatively measure the suitability of gradient magnitudes in detection of 3D boundary points of confocal image stacks is presented. A Measurement Function is defined to evaluate the suitability of each gradient magnitude chosen to be the threshold for 3D boundary detection. The application of Gauss's Divergence Theorem provides a solution to calculate the Measurement Function numerically. The gradient magnitude at which the maximum of the Measurement Function is achieved can be utilized as the most appropriate threshold for gradient-based boundary detection and other operations like volume visualization. [ABSTRACT FROM AUTHOR]

This paper presents an experimental assessment of the iterative multiscaling approach (IMSA) in imaging inhomogeneous dielectric targets. The IMSA is used to address the inversion of scattering data provided by the Institute Fresnel in Marseille, France, in order to effectively exploit the available information. Since inversion methods based on the use of the “state” equation, as with the IMSA, require knowledge of the radiated field in the investigation area, different numerical models of the illuminating setup will be considered to evaluate the robustness of the inversion algorithm in case of an approximate knowledge of the incident field arising from a limited set of measured samples. © 2005 Wiley Periodicals, Inc. Microwave Opt Technol Lett 47: 588–594, 2005; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/mop.21238 [ABSTRACT FROM AUTHOR]

In this paper, the authors propose a new object recognition algorithm called the kernel mutual subspace method. The mutual subspace method proposed by Maeda is a superior technique for implementing robust object recognition by performing a principal component analysis on multiple input images. However, like with the ordinary subspace method, a shortcoming of this technique is that performance deteriorates when the category distribution has a nonlinear structure. To solve this problem, the authors theoretically derived a new object recognition algorithm called the kernel mutual subspace method by applying the kernel nonlinear principal component analysis, which is known as a powerful nonlinear principal component analysis method, to the mutual subspace method. When the proposed technique was applied to an individual identification problem based on facial images, it was apparent that the relationship between the degrees of freedom of the object motion and the subspace dimensionality indicating a high recognition rate could be consistently explained through experiments that used the proposed method, which did not differ significantly from the conventional method at the highest precision. They also showed that the proposed technique could be effective for large-scale recognition problems and that its recognition dictionary has a more compact structure. © 2005 Wiley Periodicals, Inc. Electron Comm Jpn Pt 2, 88(6): 45–53, 2005; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjb.20190 [ABSTRACT FROM AUTHOR]