Статьи журнала - Компьютерная оптика
Все статьи: 2629
Neural network algorithm for optical-SAR image registration based on a uniform grid of points
Статья научная
The paper considers the problem of satellite multimodal image registration, in particular, optical and SAR (Synthetic Aperture Radar). Such algorithms are used in object detection, change detection, navigation. The paper considers algorithms for optical-to-SAR image registration in conditions of rough image pre-alignment. It is known that optical and SAR images have an inaccuracy in registration with georeference (up to 100 pixels with a spatial resolution of 10 m/pixel). This paper presents a neural network algorithm for optical-to-SAR image registration based on descriptors calculated for a uniform grid of points. First, algorithm find uniform grid of points for both images. Next, the neural network calculates descriptors for each point and finds descriptor distances between all possible pairs of points between optical and SAR images. Using obtained descriptor distances, a matching is made between the points on the optical and SAR images. The found matches between points are used to calculate the geometric transformation between images using the RANSAC algorithm with a limited (to combinations of translation, rotation and uniform scaling) affine transformation model. The accuracy of the proposed algorithm for optical-to-SAR image registration was investigated with different distortions in rotation and scale.
Бесплатно
Neural network recognition system for video transmitted through a binary symmetric channel
Статья научная
The demand for transmitting video data is increasing annually, necessitating the use of high-quality equipment for reception and processing. The paper presents a neural network recognition system for videos transmitted via a binary symmetrical channel. The presence of digital noise in the data makes it challenging to recognize objects in videos even with advanced neural networks. The proposed system consists of a noise interference detector, a noise purification system based on an adaptive median filter, and a neural network for recognition. The experiment results demonstrate that the proposed system effectively reduces video noise and accurately identifies multiple objects. This versatility makes the system applicable in various fields such as medicine, life safety, physics, and chemistry. The direction of further research may be to improve the model neural network, increasing the database for training or using other noises for modeling.
Бесплатно
Neural network regularization in the problem of few-view computed tomography
Статья научная
The computed tomography allows to reconstruct the inner morphological structure of an object without physical destructing. The accuracy of digital image reconstruction directly depends on the measurement conditions of tomographic projections, in particular, on the number of recorded projections. In medicine, to reduce the dose of the patient load there try to reduce the number of measured projections. However, in a few-view computed tomography, when we have a small number of projections, using standard reconstruction algorithms leads to the reconstructed images degradation. The main feature of our approach for few-view tomography is that algebraic reconstruction is being finalized by a neural network with keeping measured projection data because the additive result is in zero space of the forward projection operator. The final reconstruction presents the sum of the additive calculated with the neural network and the algebraic reconstruction. First is an element of zero space of the forward projection operator. The second is an element of orthogonal addition to the zero space. Last is the result of applying the algebraic reconstruction method to a few-angle sinogram. The dependency model between elements of zero space of forward projection operator and algebraic reconstruction is built with neural networks. It demonstrated that realization of the suggested approach allows achieving better reconstruction accuracy and better computation time than state-of-the-art approaches on test data from the Low Dose CT Challenge dataset without increasing reprojection error.
Бесплатно
Neural network task specialization via domain constraining
Статья научная
This paper introduces a concept of neural network specialization via task-specific domain constraining, aimed at enhancing network performance on data subspace in which the network operates. The study presents experiments on training specialists for image classification and object detection tasks. The results demonstrate that specialization can enhance a generalist's accuracy even without additional data or changing training regimes -- solely by constraining class label space in which the network performs. Theoretical and experimental analyses indicate that effective specialization requires modifying traditional fine-tuning methods and constraining data space to semantically coherent subsets. The specialist extraction phase before tuning the network is proposed for maximal performance gains. We also provide analysis of the evolution of the feature space during specialization. This study paves way to future research for developing more advanced dynamically configurable image analysis systems, where computations depend on the specific input. Additionally, the proposed methods can help improve system performance in scenarios where certain data domains should be excluded from consideration of the generalist network.
Бесплатно
New information technology for phytocenoses regional monitoring using remote sensing data
Статья научная
A new information technology for plant communities monitoring using remote sensing data, oriented for application at the regional level, is proposed. The technology is based on maintaining a base of reference polygons, accumulating data on the boundaries of specific plant communities and related semantic information. This database provides a source of verified and up-to-date information for solving problems of rational nature management. To expand the database of reference polygons, two algorithms for finding new ones are presented: a reliable algorithm (analyzing several growing seasons) and an urgent algorithm (based on the current growing season). The advantage of the proposed system is the integration of data storage, processing, and analysis, which enables the automation of the creation of new and the monitoring of existing polygons, as well as the solution of a wide range of problems based on remote sensing data and artificial intelligence algorithms. Practical tasks in studying of phytocenoses in the Samara Region, implemented using the proposed monitoring technology, are considered: updating forest inventory data, monitoring the status of a rare reintroduced species (Paeonia Tenuifolia), searching for new reference polygons across a vast territory of several steppe protected areas, and searching for areas of presence of an invasive plant species (Elaeagnus angustifolia L).
Бесплатно
Noise minimized high resolution digital holographic microscopy applied to surface topography
Статья научная
The topography of surface relief gratings was studied by digital holographic microscopy. The applicability of the method for quantitative measurements of surface microstructure at nanoscale was demonstrated. The method for wavefront reconstruction of surface relief from a digital hologram recorded in off-axis configuration was also applied. The main feature is noise filtration due to the presence of noise in the recorded intensity distribution and the use of all orders of the hologram. Reconstruction results proved a better effectiveness of our approach for topography studying of relief grating patterned on a ChG As2S3 - Se nanomultilayers in comparison with standard Fourier Transform and Atom Force Microscope methods.
Бесплатно
Noise reduction and mammography image segmentation optimization with novel QIMFT-SSA method
Статья научная
Breast cancer is one of the most dreaded diseases that affects women worldwide and has led to many deaths. Early detection of breast masses prolongs life expectancy in women and hence the development of an automated system for breast masses supports radiologists for accurate diagnosis. In fact, providing an optimal approach with the highest speed and more accuracy is an approach provided by computer-aided design techniques to determine the exact area of breast tumors to use a decision support management system as an assistant to physicians. This study proposes an optimal approach to noise reduction in mammographic images and to identify salt and pepper, Gaussian, Poisson and impact noises to determine the exact mass detection operation after these noise reduction. It therefore offers a method for noise reduction operations called Quantum Inverse MFT Filtering and a method for precision mass segmentation called the Optimal Social Spider Algorithm (SSA) in mammographic images. The hybrid approach called QIMFT-SSA is evaluated in terms of criteria compared to previous methods such as peak Signal-to-Noise Ratio (PSNR) and Mean-Squared Error (MSE) in noise reduction and accuracy of detection for mass area recognition. The proposed method presents more performance of noise reduction and segmentation in comparison to state-of-arts methods. supported the work.
Бесплатно
Статья научная
In this paper we investigate non-Markovian evolution of a two-level system (qubit) in a bosonic bath under influence of an external classical fluctuating environment. The interaction with the bath has the Lorentzian spectral density, and the fluctuating environment (stochastic field) is represented by a set of Ornstein-Uhlenbeck processes. Each of the subenvironments of the composite environment is able to induce non-Markovian dynamics of the two-level system. By means of the numerically exact method of hierarchical equations of motion, we study steady states of the two-level system, evolution of the reduced density matrix and the equilibrium emission spectra in dependence on the frequency cutoffs and the coupling strengths of the subenvironments. Additionally, we investigate the impact of the rotating wave approximation (RWA) for the interaction with the bath on accuracy of the results.
Бесплатно
Non-stability of MM-wave radar imaging of the car in dynamics
Статья научная
One of the important requirement to the radioimages formed by the systems of the automatic vehicle classification and identification or automobile imaging radar is the quality of forming radioimages. In ideals the quality of radioimages can be equal to optical images, because car radar must not only to determinate availability of the obstacle, but to recognized and identificated it too. The conducted theoretical and first experimental investigations have shown that the radar images of obstacles formed by radar are characterized by the non-stability of the radioimages, which can not permit to identificated and recognized the targets. Unsteadies of the car radar imaging in dynamics are analyzing and discussed in this paper. The methods of the decreasing of the radar imaging unsteadies are discussed.
Бесплатно
Novel approach of simplification detected contours on X-ray medical images
Статья научная
This paper gives description of a method for simplifying the number of points representing detected contours of the bones on digital X-ray images. Such simplification permits simplify way for correction the location of these points in the cases, if the analyzed image has poor quality, and to reduces the time of analysis it to get the reference lines and angles for diagnosis purposes of the area under investigation.
Бесплатно
Novel zoning rule for designing square Fresnel zone plate
Статья научная
An improved zoning rule is presented for designing a square Fresnel zone plate lens (FZPL). This new rule results in a higher gain when the FZPL is used as an antenna element or can enhance the focusing properties of the square FZPL when used to collimate an incident plane wave. The derivation of this improved zoning rule is presented along with simulated results for some typical cases.
Бесплатно
Numerical approach to compound quantum repeater scheme with coherent states
Статья научная
A numerical model of a quantum repeater operating with Schrödinger cat states is constructed. The model describes the performance of such a system in the presence of decoherence effects, namely, noise in the quantum channel and the efficiency of the photon-number-resolving detector. In the framework of the numerical model, a theoretical analysis of the system functioning is carried out for the elementary link by calculating its performance characteristics. Namely, we calculate photodetector click probabilities and fidelity for various sets of decoherence parameters. These estimates are necessary in the context of further experimental research at the junction with other branches of quantum communications, so that to use the entanglement distribution when it comes to operating quantum teleportation and quantum key distribution protocols based on entanglement. The model will be developed further as a versatile drag-and-drop software simulating the full-fledged entanglement swapping protocol operation.
Бесплатно
Статья научная
In the study, we concern the features of modeling a diffraction equation obtained when solving the scalar Helmholtz wave equation in the parabolic and first Rytov approximations. The task is considered in the 2D case for a plane wave transmitted through a micron-sized plasma object. We develop a comprehensive guide for choosing optimal calculation conditions to make the employed modeling procedure be the most efficient and computationally inexpensive. Methods for controlling calculation errors are presented as well. The intensity and phase shift maps are simulated for the diffracted wave in the object's near-field region and analyzed in view of the observed regularities. The applicability of the parabolic and first Rytov approximations is examined in a numerical experiment depending on the radiation wavelength and object size. The results of the study can be useful to implement diffraction imaging techniques aimed at gaining insights into the optical properties of rapidly evolving phase objects.
Бесплатно
Numerical simulation of 2D electrodynamic problems with unstructured triangular meshes
Статья научная
We present a generalization of standard leap-frog plus Yee mesh approach for Cauchy problem in electrodynamics simulations on unstructured triangulated mesh. The presented approach still inherits from finite-difference time-domain and do not use techniques developed in finite-volume time-domain approach. In the paper the whole flow from mesh creation to actual simulation is presented. The proposed computation flow is parallel ready and can be implemented for distributed systems (computation servers, graphical processing units, etc.). We studied the influence of non-regular triangulation on stability and dispersion properties of numerical solution.
Бесплатно
Статья научная
The response of fiber specklegram sensors (FSSs) is given as function of variations in the intensity distribution of the modal interference pattern or speckle pattern induced by external disturbances. In the present work, the behavior of a FSS sensing scheme under thermal perturbations is studied by means of computational simulations of the speckle patterns. These simulations are generated by applying the finite element method (FEM) to the modal interference in optical fibers as a function of the thermal disturbance and the length of the sensing zone. A correlation analysis is per-formed on the images generated in the simulations to evaluate the dependence between the changes in the speckle pattern grains and the intensity of the applied disturbance. The numerical simulation shows how the building characteristic of the length of sensing zone, combined with image processing, can be manipulated to control the metrological performance of the sensors.
Бесплатно
Numerically focused optical coherence microscopy with structured illumination aperture
Статья научная
In optical coherence microscopy (OCM) with a given numerical aperture ( NA ) of the objectives the transverse resolution can be increased by increasing the numerical aperture of illumination ( NAi ). However, this may also lead to attenuation of the signal with defocus preventing the effective numerically focused 3D imaging of the required sample volume. This paper presents an approach to structuring the illumination aperture, which allows combining the advantages of increased transverse resolution (peculiar to high NAi ) with small attenuation of the signal with defocus (peculiar to low NAi ) for high-resolution numerically focused 3D imaging in OCM.
Бесплатно
Статья научная
This research addresses the problem of automatic object detection in images under limited-visibility conditions, where objects are partially occluded, the background is complex, and lighting and viewpoints vary widely. The proposed approach combines pretraining on a programmatically generated synthetic dataset of 18,000 images - produced using the Visualization Toolkit (VTK) library - with fine-tuning on a compact real-image dataset of 2,000 annotated photographs (500 per class). Six deep neural network architectures - Faster R-CNN ResNet-50 FPN, SSD MobileNet V3, YOLOv11n, EfficientDet-D7, DETR-DC5, and CenterNet- were evaluated across three training regimes: synthetic-only, real-only, and combined (90% synthetic / 10% real). Hybrid training yielded the most substantial improvements: YOLOv11n achieved mAP@0.5 = 0.91 and mAP@0.75 = 0.86 (Precision = 0.89, Recall = 0.90, F1 = 0.89, 82 FPS), compared to 0.79 (synthetic-only) and 0.78 (real-only), representing a gain of up to +15 percentage points in mAP@0.5. EfficientDet-D7 reached mAP@0.5 = 0.87 and mAP@0.75 = 0.81, while CenterNet achieved mAP@0.5 = 0.88 at 35 FPS. Robustness analysis under simulated occlusion demonstrated that hybrid-trained models maintain reliable detection even under severe conditions: YOLOv11n retained mAP@0.5 = 0.78 at 50% occlusion and mAP@0.5 = 0.65 at 25% object visibility, while the degradation in mAP under 75% occlusion did not exceed 20% of the baseline level. The results confirm the viability of synthetic data as a standalone pretraining resource and validate the proposed hybrid pipeline for applications in autonomous driving, video surveillance, and industrial inspection.
Бесплатно
On chip optical neural networks based on mmi microring resonators for image classification
Статья научная
We propose a new on-chip optical neural network (OONN) based on multimode interference-microring resonators (MMI-RRs). The suggested structure eliminates the need for wavelength division multiplexers (WDM) to create an optical neuron on a single chip. New microring resonator structure based on 4×4 MMI coupler with a size of 24µm × 2900 µm is used for the basic elements of the computation matrix, as a result a higher bandwidth and free spectral range (FSR) can be achieved. The Si3N4 platform along with the graphene sheet is designed to modulate the signals and weights of the neural networks at a very high speed. The Si3N4 can provide wide range of operating wavelengths and can work directly with the wavelengths of color images. The structure's benefits include rapid computing speed, little loss, and the ability to handle both positive and negative values. The OONN has been applied to the MNIST dataset with a speed faster than 2.8 to 14x times compared with the conventional GPU methods.
Бесплатно
On the automation of gestalt perception in remotely sensed data
Статья научная
Gestalt perception, the laws of seeing, and perceptual grouping is rarely addressed in the con-text of remotely sensed imagery. The paper at hand reviews the corresponding state as well in ma-chine vision as in remote sensing, in particular concerning urban areas. Automatic methods can be separated into three types: 1) knowledge-based inference, which needs machine-readable knowl-edge, 2) automatic learning methods, which require labeled or un-labeled example images, and 3) perceptual grouping along the lines of the laws of seeing, which should be pre-coded and should work on any kind of imagery, but in particular on urban aerial or satellite data. Perceptual group-ing of parts into aggregates is a combinatorial problem. Exhaustive enumeration of all combina-tions is intractable. The paper at hand presents a constant-false-alarm-rate search rationale. An open problem is the choice of the extraction method for the primitive objects to start with. Here super-pixel-segmentation is used.
Бесплатно
One-shot learning with triplet loss for vegetation classification tasks
Статья научная
Triplet loss function is one of the options that can significantly improve the accuracy of the One-shot Learning tasks. Starting from 2015, many projects use Siamese networks and this kind of loss for face recognition and object classification. In our research, we focused on two tasks related to vegetation. The first one is plant disease detection on 25 classes of five crops (grape, cotton, wheat, cucumbers, and corn). This task is motivated because harvest losses due to diseases is a serious problem for both large farming structures and rural families. The second task is the identification of moss species (5 classes). Mosses are natural bioaccumulators of pollutants; therefore, they are used in environmental monitoring programs. The identification of moss species is an important step in the sample preprocessing. In both tasks, we used self-collected image databases. We tried several deep learning architectures and approaches. Our Siamese network architecture with a triplet loss function and MobileNetV2 as a base network showed the most impressive results in both above-mentioned tasks. The average accuracy for plant disease detection amounted to over 97.8 % and 97.6 % for moss species classification.
Бесплатно
