Статьи журнала - Компьютерная оптика
Все статьи: 2629
Document image analysis and recognition: a survey
Статья научная
This paper analyzes the problems of document image recognition and the existing solutions. Document recognition algorithms have been studied for quite a long time, but despite this, currently, the topic is relevant and research continues, as evidenced by a large number of associated publications and reviews. However, most of these works and reviews are devoted to individual recognition tasks. In this review, the entire set of methods, approaches, and algorithms necessary for document recognition is considered. A preliminary systematization allowed us to distinguish groups of methods for extracting information from documents of different types: single-page and multi-page, with text and handwritten contents, with a fixed template and flexible structure, and digitalized via different ways: scanning, photographing, video recording. Here, we consider methods of document recognition and analysis applied to a wide range of tasks: identification and verification of identity, due diligence, machine learning algorithms, questionnaires, and audits. The groups of methods necessary for the recognition of a single page image are examined: the classical computer vision algorithms, i.e., keypoints, local feature descriptors, Fast Hough Transforms, image binarization, and modern neural network models for document boundary detection, document classification, document structure analysis, i.e., text blocks and tables localization, extraction and recognition of the details, post-processing of recognition results. The review provides a description of publicly available experimental data packages for training and testing recognition algorithms. Methods for optimizing the performance of document image analysis and recognition methods are described.
Бесплатно
EBS-YOLO: Foreign object detection algorithm for transmission lines based on improved Yolov10
Статья научная
When a foreign body touches a transmission line it may have serious consequences. If it is not handled in time it may lead to accidents such as short circuits and blackouts, affecting the normal operation of the power system and the stability of social life. In order to detect foreign objects on transmission lines, this paper proposes an EBS-YOLO method based on Yolov10. Firstly, in the structure of the backbone network, we adopt C2f-Efficient Multi-Scale-Conv plus (C2f-EMSCP) as the convolutional layer for feature extraction, replacing part of the C2f standard convolutional layer, and obtaining a richer feature representation by combining different scales of feature mapping. Secondly, a Bidirectional Feature Pyramid Network (BiFPN) is used, which enables the model to fuse features of different scales better. Then, the SEAMHead module with multi-head attention is utilized to augment the original features, enhance head detection, and reduce the effect of object occlusion. Finally, in order to solve the consistency problem between the predicted and real bounding boxes, the SIoU loss is used to replace the original CIoU loss in Yolov10. The experimental results show that EBS-YOLO achieves an average detection accuracy of 90.4 %, which is 4.1 % better than Yolov10, and Recall and Precision are improved by 5.3 % and 1.8 %, respectively. Compared with other methods, our EBS-YOLO has higher accuracy in detecting foreign objects on transmission lines.
Бесплатно
Статья научная
In this paper, attempts have been made to study the joint effects of apodization and aperture masking on the diffraction images of coherently illuminated straight edge. The Edge-Ringing, Edge-Shift and Edge-Eradient of the edge images have been evaluated for different values of apodization using edge masking of circular apertures. We have considered rotationally symmetric, aberrated coherent optical system. These investigations have lead to the use of certain pupil functions in conjunction with optimal apodizers to assess the quality of edge images. Any obstruction placed in the light path of an optical system prevents waves from a portion of the wavefront in reaching the focal zone. This results in the change in the light flux at every point of the diffraction pattern. This is in turn, depends on the shape and size of the obstruction.
Бесплатно
Статья научная
In the context of modern digital document management, the automation of document pro-cessing, particularly in accounting, is a crucial factor in enhancing the efficiency of business pro-cesses. However, automated document processing encounters a range of specific challenges, both linguistic and structural characteristics of the data. Traditional text processing methods that rely on classical optical character recognition (OCR) algorithms do not provide sufficient accuracy in extracting data from document images, which limits their use in automated accounting systems. These challenges are particularly evident when processing documents with complex structures, specific element placement, and text content. This paper proposes a solution to this problem by applying a model based on a transformer neural network architecture, specifically adapted for working with document images. Within the scope of this study, the transformer model is trained on a dataset of accounting document images with varying element placements and text with Cy-rillic characters. The focus on Cyrillic text is particularly relevant, as research in this area has pre-dominantly concentrated on documents in English or other Latin-based scripts. This article in-cludes the results of training evaluated through specialized performance metrics. As a result of the experiment, at the final stage of training the model, the confidence loss was 0.156, which indicates that the model effectively minimizes the prediction error. The obtained accuracy of 0.868 showed a relatively high accuracy of forecasts. The Recall value of 0.905 indicates that the model effectively identifies most of the positive examples. The indicator F1=0.886 reflects a good balance between accuracy and memorability. The accuracy of 0.96798 indicates that the model's predictions are highly accurate. The use of the transformer model significantly improves the accuracy of extracting key in-formation, such as date, number, and organization name, from accounting documents containing Cyrillic text. The findings of this study affirm the potential of this method for implementation in automated accounting systems, contributing to enhanced efficiency and precision in processing accounting documents.
Бесплатно
Efficiency of object identification for binary images
Статья научная
In this paper, a comparative analysis of the correlation-extreme method, the method of contour analysis and the method of stochastic gradient identification in the objects identification for a binary image is carried out. The results are obtained for a situation where possible deformations of an identified object with respect to a pattern can be reduced to a similarity model, that is, the pattern and the object may differ in scale, orientation angle, shift along the base axes, and additive noise. The identification of an object is understood as the recognition of its image with an estimate of the strain parameters relative to the template.
Бесплатно
Статья научная
This paper presents the diffraction characteristics of electrically controlled multiplexed three-layer holographic diffraction structures formed in photopolymer materials with a high proportion of nematic liquid crystals. The results obtained demonstrate the possibility of using multilayer holographic diffraction structures as the main element for electrically controlled optical spectral filters for dense wavelength division multiplexing communication networks.
Бесплатно
Enhanced dynamic programming-based method for text line recognition in documents
Статья научная
On-premise text recognition is in demand. Customers want to recognize bank cards to pay online, passports to fill in tickets' information and many more using their smartphones. As main approach to text recognition in the last two decades is artificial neural networks the resulting solutions tend to be resource-hungry and not fitting on mobile devices. In our paper, we introduce an enhanced method based on dynamic programming and a fully convolutional network for text line recognition that allows this classic model to demonstrate competitive results with much heavier architectures. The main idea is the addition of the special pin into the network alphabet that allows to apply dynamic programming to analyze the raw neural network output effectively. As our main focus is the recognition of identity documents we employ public dataset MIDV-500 and its extension MIDV-2019 as a test sample. We compare our resulting recognizer with several published models, including TrOCR, Paddle OCR, and Tesseract OCR 5, to demonstrate its superiority in accuracy and performance trade-off. Our method is about 200 times faster than TrOCR, and in the most cases is about 2 times faster than Paddle OCR. The accuracy of our recognizer is comparable with Paddle OCR on MIDV-500 and is better on MIDV-2019, including it being about 2 times more accurate for machine-readable zones images.
Бесплатно
Enhancing forest cover analysis through super-resolution of Sentinel-2 multispectral images
Статья научная
Machine learning (ML) algorithms, combined with satellite observations, offer significant advantages in environmental studies, particularly in vegetation cover analysis. The varying spectral resolution and number of spectral bands of remote sensing imagery allow for different tasks to be addressed with different levels of detail and accuracy. A current limitation in advanced Geographic Information System (GIS) development is the availability and accessibility of data. High-resolution data with a wide spectral range are often expensive, while open-access data typically force researchers to choose between high spatial and temporal resolution or large number of spectral bands. In this study, we investigate this issue through a case study of forest type classification. We employed and trained a single-image super-resolution model based on the Residual Channel Attention Network (RCAN) to upscale Sentinel-2 multispectral images from 10 to 5 meters. We then compared image segmentation results from the original Sentinel-2 data, the upscaled data, and WorldView-3 images. In addition to experiments with spatial resolution, we explored the effect of number of spectral bands on segmentation quality. The results confirm our hypothesis that artificially upscaled data provide more information than low-resolution data, both for narrow and wider spectral ranges, with the increase in spatial resolution proving more significant than the increase in number of spectral bands.
Бесплатно
Erratum: dynamic analysis of optical cell trapping in the ray optics regime
Статья научная
In this additional part of the original paper [1], revised calculations and corrected equations are presented. Also some conclusions from the original paper are revised and discussed briefly.
Бесплатно
Статья
В настоящем дополнении к оригинальной статье [1] исправляется ошибка, допущенная при расчетах спектров отражения и пропускания изогнутого волноводного резонатора Фабри–Перо. Ошибка возникла вследствие пренебрежения оболочечными модами в прямых волноводных участках перед и после исследуемого резонатора (рис. 2а в оригинальной статье). Хотя данные моды не вносят непосредственного вклада в вычисляемую прошедшую и отраженную мощность, их учет необходим для корректного расчета спектров отражения и пропускания резонатора, что было обнаружено после опубликования статьи. В данном дополнении приводятся исправленные результаты, а также некоторые корректировки выводов оригинальной статьи.
Бесплатно
Статья научная
Change detection from synthetic aperture radar images becomes a key technique to detect change area related to some phenomenon as flood and deformation of the earth surface. This paper proposes a transfer learning and Residual Network with 18 layers (ResNet-18) architecture-based method for change detection from two synthetic aperture radar images. Before the application of the proposed technique, batch denoising using convolutional neural network is applied to the two input synthetic aperture radar image for speckle noise reduction. To validate the performance of the proposed method, three known synthetic aperture radar datasets (Ottawa; Mexican and for Taiwan Shimen datasets) are exploited in this paper. The use of these datasets is important because the ground truth is known, and this can be considered as the use of numerical simulation. The detected change image obtained by the proposed method is compared using two image metrics. The first metric is image quality index that measures the similarity ratio between the obtained image and the image of the ground truth, the second metrics is edge preservation index, it measures the performance of the method to preserve edges. Finally, the method is applied to determine the changed area using two Sentinel 1 B synthetic aperture radar images of Eddahbi dam situated in Morocco.
Бесплатно
Статья научная
This paper considers an experimental study of the layout of an active-pulse television measuring system in the problem of assessing the accuracy of measuring the distance to objects using the depth maps. The main technical characteristics and structure of the active-pulse television measuring system layout are described, the description of the multi-zone ranging method used in the experiment is given. The field tests were carried out using a system for terrain orthophotomaps construction by an unmanned aerial vehicle and a geodetic measuring instrument, which is a reference for building a terrain plan and fixing distances between objects on the ground. The technique of carrying out aerial work is described to obtain the necessary data array, on which a digital model and an orthophotomap of the area were subsequently built. Conclusions are drawn about the accuracy of digital terrain models built based on the results of aerial photography from an unmanned aerial vehicle with a geodetic receiver on board and the applicability of these data as reference data for testing a prototype of an active-pulse television measuring system.
Бесплатно
Experimental investigation of multimode dispersionless beams
Статья научная
Laser light modes are beams in whose cross-section the complex amplitude is described by eigenfunctions of the operator of light propagation in the waveguide medium. The fundamental properties of modes are their orthogonality and their ability to retain their structure during propagation for example in a lenslike medium or in free space. Developed diffractive optical elements (DOEs) of MODAN-type open up new promising potentialities of solving the tasks of generation, transformation, superposition of different laser modes and their combinations. Now we present new results obtained by synthesis and investigation of beams consisting of more than one two-dimensional Gaussian laser modes with the same value of propagation constant - multimode dispersionless beams.
Бесплатно
Extraction method and denoising performance analysis of diffuse spots and silhouettes in STORM
Статья научная
In super-resolution microscopy based on STORM (Stochastic Optical Reconstruction Microscopy), due to the diffraction phenomenon, photons emitted by fluorescent molecules form into diffuse spots in a raw image. The regions without diffuse spots in the raw image are referred to as silhouettes. The diffuse spot regions are crucial for assessing the quality of a raw image and achieving super-resolution imaging as conventional holistic evaluation methods, which fail to distinguish between diffuse spots and silhouettes, cannot reflect the quality of the diffuse spot regions. A mask-based image segmentation algorithm is proposed here to extract and separate the diffuse spots and silhouette regions. Through simulation experiments, the denoising characteristics of three-dimensional block matching filtering (BM3D) and wide spectrum denoising (WSD) in different regions under various noise levels are compared and analyzed, and important criteria for selecting denoising methods for raw images are provided. Experiments show that better denoising is achieved with WSD than BM3D in the diffuse spot regions, while BM3D performs better in the silhouette regions in low noise level.
Бесплатно
Face anti-spoofing with joint spoofing medium detection and eye blinking analysis
Статья научная
Modern biometric systems based on face recognition demonstrate high recognition quality, but they are vulnerable to face presentation attacks, such as photo or replay attack. Existing face anti-spoofing methods are mostly based on texture analysis and due to lack of training data either use hand-crafted features or fine-tuned pretrained deep models. In this paper we present a novel CNN-based approach for face anti-spoofing, based on joint analysis of the presence of a spoofing medium and eye blinking. For training our classifiers we propose the procedure of synthetic data generation which allows us to train powerful deep models from scratch. Experimental analysis on the challenging datasets (CASIA-FASD, NUUA Imposter) shows that our method can obtain state-of-the-art results.
Бесплатно
Face photo retrieval based on sketches
Статья научная
The paper deals with the problem of the automatic retrieval of face photos using sketch drawings based on the witness description. We propose new methods for the generation of a sketch population from the initial one to improve the performance of sketch-based photo image retrieval systems. The method based on the computation of an average sketch from the generated population has been applied to increase the index of similarity in sketch-photo pairs. It is shown that such sketches are more similar to the original photographic images and their use leads to good results. Results of the experiments on CUHK Face Sketch and CUHK Face Sketch FERET databases and open access databases of photo-sketches pairs are discussed.
Бесплатно
Face recognition based on the proximity measure clustering
Статья научная
In this paper problems of featureless face recognition are considered. The recognition is based on clustering the proximity measures between the distributions of brightness clusters cardinality for segmented images. As a proximity measure three types of distances are used in this work: the Euclidean, cosine and Kullback-Leibler distances. Image segmentation and proximity measure clustering are carried out by means of a software model of the recurrent neural network. Results of the experimental studies of the proposed approach are presented.
Бесплатно
Facedetectnet: face detection via fully-convolutional network
Статья научная
Ace detection is one of the most popular computer vision tasks. There are a lot of face detection approaches proposed including different CNN-based techniques, but the problem of optimal balancing between detection quality and computational speed is still relevant. In this paper we propose new CNN-based solution for face detection called FaceDetectNet. Our CNN architecture is based on ideas of YOLO/DetectNet and GoogleNet architecture supported with some new tools and implementation details created especially for our face detection application. We propose: original iterative proposal clustering (IPC) algorithm for aggregation of output face proposals formed by CNN and the 2-level “weak pyramid” providing better detection quality on the testing sets containing both small and huge images. Our face detection approach is close to previously proposed SSD-based face detection, but the principal difference is that we use the deep features of top hidden CNN layer for forming the face proposals of any size...
Бесплатно
Fast localization and rectification of documents folded into thirds
Статья научная
The ubiquitous usage of smartphones makes camera-captured document images as widely used as scanned ones as the input of a modern document recognition system. A document captured by a smartphone camera may appear mechanically distorted in the image creating the need for an image rectification step. The present paper considers a particular case of document image distortions. Specifically, if a business document is sent via postal service, it may need to be folded to fit the envelope. Once the document is taken out of the envelope and unfolded, its geometric shape is distorted in a very particular pattern. Since the most popular envelope formats in Europe and America require the document to be folded into thirds, this case is considered in this paper. We propose a novel content-independent model-based algorithm for the localization and geometrical rectification of documents folded into thirds. Our algorithm outperforms current SOTA rectification methods on the recently published dataset FDI by key rectification accuracy metrics (AD and CER) and is able to rectify documents held in hand. Moreover, it can be executed on a mobile CPU and has a reasonable execution time: it takes only about 17 ms to localize a document and about 110 ms to projectively rectify it. So it makes it possible to embed the proposed algorithm into document recognition systems designed for on-device acquisition.
Бесплатно
