Статьи журнала - Компьютерная оптика
Все статьи: 2609
Статья научная
The subject of this paper is the urgent problem of detecting palladium nanoparticles on car-bon materials in grayscale scanning electron microscope images, the solution of which can be useful in many technological processes of the chemical industry. This is nontrivial problem and, currently, there is no method that would have all the necessary qualities for its solution. This work is based on our previously developed method for detecting nanoparticles based on exponential approximation, which showed the best accuracy for scanning electron microscope images in absence of essential background irregularities. However, it has two significant shortcomings: 1) high demands on computing resources and 2) in the presence of background irregularities it produces a large number of false positives. This paper proposes a method that preserves the basic assumptions and general concept and, accordingly, the main advantages of earlier proposed approach, however, it contains a number of significant improvements that allow eliminating the above-mentioned shortcomings. Experiments show that the proposed method reduces the number of false positives by 60-70% for SEM images with background irregularities while decreasing the nanoparticle detection time by approximately two to three times compared with the previously proposed approach.
Бесплатно
Статья научная
Image inpainting is a process of filling missing and damaged parts of image. By using the Mumford-Shah image model, the image inpainting can be formulated as a constrained optimization problem. The Mumford-Shah model is a famous and effective model to solve the image inpainting problem. In this paper, we propose an adaptive image inpainting method based on multiscale parameter estimation for the modified Mumford-Shah model. In the experiments, we will handle the comparison with other similar inpainting methods to prove that the combination of classic model such the modified Mumford-Shah model and the multiscale parameter estimation is an effective method to solve the inpainting problem.
Бесплатно
An adaptive radial object recognition algorithm for lightweight drones in different environments
Статья научная
The paper proposes a group of radial shape object recognition methods capable of finding many different-sized circular objects in an image with high accuracy in minimum time and conditions of uneven brightness of frame areas. The methods are not computationally demanding, making them suitable for use in computer vision systems of light unmanned vehicles, which cannot carry powerful computing devices on board. The methods are also suitable for unmanned vehicles traveling at high speed, where image processing must be performed in real-time. The proposed algorithms are robust to noise. When combined into a single group, the developed algorithms constitute a customizable set capable of adapting to different imaging conditions and computing power. This property allows the method to be used for detecting objects of interest in different environments: from the air, from the ground, underwater, and when moving the vehicle between these environments. We proposed three methods: a hybrid FRODAS method combines the FRST and Hough methods to increase accuracy and reduce the time to search for circles in the image; a PaRCIS method based on sequential image compression and reconstruction to increase the speed of searching for multiple circles of different radii and removing noise; an additional modification of LIPIS is used with any of the primary or developed methods to reduce the sensitivity to sharp variations in the frame's brightness. The paper presents comparative experiments demonstrating the advantages of the developed methods over classical circle recognition methods regarding accuracy and speed. It shows the advantage of recognizing circles of different brightness. Experiments on recognizing multiple real-world objects in photographs taken on the ground, in the air, and underwater, with complex scenes under distortion and blurring with different degrees of illumination, demonstrate the effectiveness of the set of methods.
Бесплатно
Статья научная
One of the problems solved by analyzing the data of long-term Video EEG monitoring is the differentiation of epileptic and artifact events. For this, not only multichannel EEG signals are used, but also video data analysis, since traditional methods based on the analysis of EEG wavelet spectrograms cannot reliably distinguish an epileptic seizure from a chewing artifact. In this paper, we propose an algorithm for detecting artifact events based on a joint analysis of the level of the optical flow and the ridges of wavelet spectrograms. The preliminary results of the analysis of real clinical data are given. The results show the possibility in principle of reliable distinguishing non-epileptic events from epileptic seizures.
Бесплатно
Статья научная
Many different filters can be used to reduce multiplicative speckle noise on radar images. Most of these filters have some parameters whose values influence the result of filtering. Finding optimal values of such parameters may be a non-trivial task. In this paper, a formal automated method for finding optimal parameters of speckle noise reduction filters is proposed. Using a specially designed test image, optimal parameters for the most commonly used filters were found using several image quality assessment metrics, including the Structural Similarity Index (SSIM) and Gradient Magnitude Similarity Deviation (GMSD). The use of filters with optimal parameters allows processing (detection, segmentation, etc.) of radar images with minimal influence of speckle noise.
Бесплатно
An efficient U-shaped transformer network for low-light power image denoising
Статья научная
Unmanned aerial vehicle (UAV) inspection of transmission lines has been widely applied in recent years. However, in low-light weather conditions, random noise often appears in the captured transmission line images due to the combined effects of brightness, electromagnetic interference, and camera sensor limitations. This noise significantly undermines the quality and accuracy of the inspection. To address this challenge, we propose a novel transformer-based image denoising method called EUformer. First, we propose the Global Feature Compensator (GFC) module, which adaptively captures remote pixel dependencies for improved global image modelling. Second, we designed the Mixed-Gated feed-forward network (MG-FFN), to enhance the aggregation of local contextual information. Finally, the loss function is optimized by introducing a new regular term, effectively addressing negative effects such as artefacts in the reconstructed images. To assess the denoising capabilities of the EUformer model proposed in this study for transmission line images, we developed a benchmark dataset specifically for low-light transmission line image denoising. The results of extensive experiments demonstrate that the EUformer model achieves competitive performance while maintaining low complexity.
Бесплатно
An efficient algorithm for non-rigid object registration
Статья научная
An efficient algorithm for registration of two non-rigid objects based on geometrical transformation of the template object to target object is proposed. The transformation is considered as warping of the template onto the target. To choose the most suitable transformation from all possible warps, a registration algorithm should satisfy deformation constraints referred to as regularization of non-rigid objects. In this work, we use variational functionals for affine transformations. With the help of computer simulation, the proposed method for searching the optimal geometrical transformation is compared with that of common algorithms.
Бесплатно
An efficient algorithm for overlapping bubbles segmentation
Статья научная
Image processing is an effective method for characterizing various two-phase gas/liquid flow systems. However, bubbly flows at a high void fraction impose significant challenges such as diverse bubble shapes and sizes, large overlapping bubble clusters occurrence, as well as out-of-focus bubbles. This study describes an efficient multi-level image processing algorithm for highly overlapping bubbles recognition. The proposed approach performs mainly in three steps: overlapping bubbles classification, contour segmentation and arcs grouping for bubble reconstruction. In the first step, we classify bubbles in the image into a solitary bubble and overlapping bubbles. The purpose of the second step is overlapping bubbles segmentation. This step is performed in two subsequent steps: at first, we classify bubble clusters into touching and communicating bubbles. Then, the boundaries of communicating bubbles are split into segments based on concave point extraction. The last step in our algorithm addresses segments grouping to merge all contour segments that belong to the same bubble and circle/ellipse fitting to reconstruct the missing part of each bubble. An application of the proposed technique to computer generated and high-speed real air bubble images is used to assess our algorithm. The developed method provides an accurate and computationally effective way for overlapping bubbles segmentation. The accuracy rate of well segmented bubbles we achieved is greater than 90 % in all cases. Moreover, a computation time equal to 12 seconds for a typical image (1 Mpx, 150 overlapping bubbles) is reached.
Бесплатно
An efficient block-based algorithm for hair removal in dermoscopic images
Статья научная
Hair occlusion in dermoscopy images affects the diagnostic operation of the skin lesion. Segmentation and classification of skin lesions are two major steps of the diagnostic operation required by dermatologists. We propose a new algorithm for hair removal in dermoscopy images that includes two main stages: hair detection and inpainting. In hair detection, a morphological bottom-hat operation is implemented on Y-channel image of YIQ color space followed by a binarization operation. In inpainting, the repaired Y-channel is partitioned into 256 non-overlapped blocks and for each block, white pixels are replaced by locating the highest peak, using a histogram function and a morphological close operation. The proposed algorithm reports a true positive rate (sensitivity) of 97.36 %, a false positive rate (fall-out) of 4.25 %, and a true negative rate (specificity) of 95.75 %. The diagnostic accuracy achieved is recorded at a high level of 95.78 %.
Бесплатно
An improved gray-scale transformation method for pseudo-color image enhancement
Статья научная
Image enhancement is a very important process of image preprocessing and it plays a critical role in the improvement of image quality and the follow-up image analysis, which makes the research of image enhancement algorithm a hot research field. Image enhancement not only needs to strengthen image determination and recognition, but also needs to avoid the consequential color distortion. Pseudo-color enhancement is the technique to map different gray scales of a black-and-white image into a color image. As humans have extremely strong ability in distinguishing different colors visually and relatively weak capacity in discriminating gray scales, so, color the gray-scale changes which cannot be differentiated by human eyes so that they can tell them apart. The mapping function in conventional gray-scale transform method is not working well in dark and low-contrast images. So, this paper comes up with an improved gray-scale transformation algorithm. This algorithm can achieve the enhancement, preserve the image colors, process dark and low-contrast images, reinforce the enhancement and improve the blocking effect. The experiment proves that the enhanced image obtained by the method of this paper can have improved average brightness, natural colors and more detail information and it has good application value.
Бесплатно
An improved video watermarking algorithm with extraction using a mobile device camera
Статья научная
The use of screen-capture-resistant digital watermarks is a promising way to store information invisibly in a video stream for later retrieval by the user using a smartphone camera. However, the development of algorithms that implement this scenario is associated with the problem of balancing between the imperceptibility of embedding and robustness. A serious problem is the extraction of watermarks using a mobile device. Most people use the vertical positioning of the smartphone when shooting, which excludes the possibility of only marked video sequences entering the frame. The extraction algorithm first finds the screen area in the image and then extracts the watermark under various distortion conditions. This study proposes an approach to improve the efficiency of the algorithm for embedding digital watermarks into video data based on rectangular patterns, which provides resistance to screen shooting. The proposed approach to increasing the embedding imperceptibility provided an increase in the PSNR and SSIM values by 17.18 % and 7.90 %, respectively. The use of a neural network at the extraction stage reduced the BER value by 64.64 %.
Бесплатно
Analysis of a robust edge detection system in different color spaces using color and depth images
Статья научная
Edge detection is very important technique to reveal significant areas in the digital image, which could aids the feature extraction techniques. In fact it is possible to remove un-necessary parts from image, using edge detection. A lot of edge detection techniques has been made already, but we propose a robust evolutionary based system to extract the vital parts of the image. System is based on a lot of pre and post-processing techniques such as filters and morphological operations, and applying modified Ant Colony Optimization edge detection method to the image. The main goal is to test the system on different color spaces, and calculate the system’s performance. Another novel aspect of the research is using depth images along with color ones, which depth data is acquired by Kinect V.2 in validation part, to understand edge detection concept better in depth data. System is going to be tested with 10 benchmark test images for color and 5 images for depth format, and validate using 7 Image Quality Assessment factors such as Peak Signal-to-Noise Ratio, Mean Squared Error, Structural Similarity and more (mostly related to edges) for prove, in different color spaces and compared with other famous edge detection methods in same condition...
Бесплатно
Analysis of logistics distribution path optimization planning based on traffic network data
Статья
With the development of economy, the distribution problem of logistics becomes more and more complex. Based on the traffic network data, this study analyzed the vehicle routing problem (VRP), designed a dynamic vehicle routing problem with time window (DVRPTW) model, and solved it with genetic algorithm (GA). In order to improve the performance of the algorithm, the genetic operation was improved, and the output solution was further optimized by hill climbing algorithm. The analysis of example showed that the improved GA algorithm had better performance in path optimization planning, the total cost of planning results was 31.44 % less than that of GA algorithm, and the total cost of planning results increased by 11.48 % considering the traffic network data. The experimental results show that the improved GA algorithm has good performance and can significantly reduce the cost of distribution and that research on VRP based on the traffic network data is more in line with the actual situation of logistics distribution, which is conducive to the further application of the improved GA algorithm in VRP.
Бесплатно
Статья научная
Angular characteristics of a dynamic hologram, recorded by a "fan" of plane waves in a reversible photochromatic medium, are studied under various correlations between the intensities of these waves. It is shown that the maximum increase of the relative diffraction efficiency with the increase of the angle between the reference and object waves is observed for thin holograms. There is such a PCM thickness beginning from which the relative dependence of the hologram diffraction efficiency upon the angle ceases to depend upon the PCM thickness, reaching some maximum distribution. Coincidence is shown of the angular characteristics of the holograms, recorded under the condition that the reference wave intensity is much greater than the object wave intensity, and of the holograms, recorded by a "fan" of plane waves of equal intensity. The hologram diffraction efficiency change is studied under the readout wave deviation from the Bragg angle. The reversibility of photochemical transformations in a number of photochromatic media (PCM) allows them to be used as non-linear media for a dynamic hologram recording [1-4]. In the works, accomplished up to now, on studying the dynamic hologram diffraction efficiency (HDE) in reversible PCM it has been considered that hologram recording is carried out by two plane waves, the surfaces of equal intensity of the recorded interference grating being perpendicular to the photochromatic layer faces [5-6]. In the present work the angular HDE dependence is investigated, knowing which, one can estimate the possibility of recording in such media the holograms of complex spatially modulated fields.
Бесплатно
Статья научная
With the development of computer technology, there are more and more algorithms and models for data processing and analysis, which brings a new direction to radar target recognition. This study mainly analyzed the recognition of high resolution range profile (HRRP) in radar target recognition and applied the generalized regression neural network (GRNN) model for HRRP recognition. In order to improve the performance of HRRP, the fruit fly optimization algorithm (FOA) algorithm was improved to optimize the parameters of the GRNN model. Simulation experiments were carried out on three types of aircraft. The improved FOA-GRNN (IFOA-GRNN) model was compared with the radial basis function (RBF) and GRNN models. The results showed that the IFOA-GRNN model had a better convergence accuracy, the highest average recognition rate (96.4 %), the shortest average calculation time (275 s), and a good recognition rate under noise interference. The experimental results show that the IFOA-GRNN model has a good performance in radar target recognition and can be further promoted and applied in practice.
Бесплатно
Статья научная
The article provides a brief introduction to hydrological monitoring and the methods of water body identification and flow velocity estimation based on unmanned aerial vehicle (UAV) remote sensing technology. Then, a case study of hydrological monitoring using UAV remote sensing technology was conducted on Gangnan Reservoir in Hebei Province. The effectiveness of the convolutional neural network (CNN) algorithm was verified, and measurements were made on the reservoir’s water area and average flow velocity in both flood and non-flood periods during 2020, 2021, and 2022. It was found that the CNN algorithm effectively identified water areas in UAV remote sensing images. Compared to non-flood periods, there was a significant increase in the water area of the reservoir during flood periods, as well as a noticeable increase in average flow velocity upstream; however, there was no significant change in average flow velocity downstream of the reservoir.
Бесплатно
Applied aspects of modern non-blind image deconvolution methods
Статья научная
The focus of this paper is the study of modern non-blind image deconvolution methods and their application to practical tasks. The aim of the study is to determine the current state-of-the-art in non-blind image deconvolution and to identify the limitations of current approaches, with a focus on practical application details. The paper proposes approaches to examine the influence of various effects on the quality of restoration, the robustness of models to errors in blur kernel estimation, and the violation of the commonly assumed uniform blur model. We developed a benchmark for validating non-blind deconvolution methods, which includes datasets of ground truth images and blur kernels, as well as a test scheme for assessing restoration quality and error robustness. Our experimental results show that those neural network models lacking any pre-optimization, such as quantization or knowledge distillation, fall short of classical methods in several key properties, such as inference speed or the ability to handle different types of blur. Nevertheless, neural network models have made notable progress in their robustness to noise and distortions. Based on the results of the study, we provided recommendations for more effective use of modern non-blind image deconvolution methods. We also developed suggestions for improving the robustness, versatility and performance quality of the models by incorporating additional practices into the training pipeline.
Бесплатно
Applying neural networks in coordinated group signal transformation to improve image quality
Статья научная
The rapid development of the Internet of Things and wireless sensor networks combined with the introduction of image analysis systems and computer vision technologies has led to the emergence of a new class of systems – multimedia Internet of Things and multimedia wireless sensing networks. The combination of the specifics of the Internet of Things, which requires simultaneous and long-term operation of a large number of autonomous devices, with the need to transmit video data poses the problem of creating new energy-efficient methods of image compression. The paper considers applying coordinated group signal transformation as such an algorithm, which performs compression based on the input signals’ correlation. Correlation between the image color channels makes this possible. However, it was necessary to supplement this method by clustering the original images using machine learning methods for better image reconstruction at reception. The criterion for clustering was the change of image gradient. The use of radial neural network in the clustering algorithm increased the speed of the proposed method. The resulting algorithm provides at least fourfold image compression with high-quality image restoration. Moreover, for multimedia Internet of Things systems, in which quality losses are acceptable, it is possible to provide large compression ratios without increasing computational complexity, i.e., without increasing power consumption.
Бесплатно
Статья научная
In the current study, a general approach to the formation of a storage model and development of tools for representation of multidimensional heterogeneous data that would allow real-time operation with these data, is proposed. This approach is based on the previously formulated requirements for models of representing multidimensional heterogeneous data. A functional diagram for combining heterogeneous multidimensional data and adding them to an existing data model has been created. The advantages of data analysis using such model compared to working with disparate data are discussed. Development of the tool for integrating heterogeneous data in the context of solving the problem of combining aerial photography data obtained from unmanned aerial vehicles is shown. The fundamental possibility of combining aerial photography data from different spectrums, as well as using derived data such as object detection results as an additional layer of heterogeneous data within the general model, is demonstrated.
Бесплатно
Arrhythmia detection using resampling and deep learning methods on unbalanced data
Статья научная
Due to cardiovascular diseases millions of people die around the world. One way to detect abnormality in the heart condition is with the help of electrocardiogram signal (ECG) analysis. This paper’s goal is to use machine learning and deep learning methods such as Support Vector Machines (SVM), Random Forests, Light Gradient Boosting Machine (LightGBM), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (BLSTM) to classify arrhythmias, where particular interest represent the rare cases of disease. In order to deal with the problem of imbalance in the dataset we used resampling methods such as SMOTE Tomek-Links and SMOTE ENN to improve the representation ration of the minority classes. Although the machine learning models did not improve a lot when trained on the resampled dataset, the deep learning models showed more impressive results. In particular, LSTM model fitted on dataset resampled using SMOTE ENN method provides the most optimal precision-recall trade-off for the minority classes Supraventricular beat and Fusion of ventricular and normal beat, with recall of 83 % and 88 % and precision of 74 % and 66 % for the two classes respectively, whereas the macro-weighted recall is 92 % and precision is 82 %.
Бесплатно
