scholarly journals Software tool for recognition of Ukrainian-language scientific articles

2021 ◽  
pp. 117-122
Author(s):  
Oksana Andriivna Tatarinova ◽  
Vladislav Valerievich Ovsyanikov
Keyword(s):  
Neural Network ◽  
Software Tool ◽  
Input Image ◽  
Document Structure ◽  
Mathematical Symbols ◽  
Different Types ◽  
Mathematical Formulas ◽  
Computer Recognition ◽  
Processing Mechanism

The problem of computer recognition, both separately printed characters and whole texts, which may contain mathematical formulas, and further saving the resulting document in the "Latex" format, is considered. The developed software implements the ability to recognize printable Latin, Cyrillic, Greek letters and special mathematical symbols. For this, a multilayer convolutional neural network built using the Keras machine learning library and additional validation heuristics are used. To improve the quality of neural network recognition, a sophisticated image processing mechanism has been developed that helps to remove noise from the image, eliminate errors associated with the inclination of characters, and correct character defects associated with the quality of the input image. Also implemented are mechanisms for collecting individual characters into words or mathematical formulas, reproducing the position of signs of indices and degrees, forming ordinary fractions and expressions under the root sign. The results of the recognized text are saved in a file with the simultaneous construction of the "latex" document structure. To demonstrate the capabilities of the developed software, a graphical user interface has been added, with which you can select and inspect the input image even before the start of recognition. During testing of the software, the recognition of images of different types was carried out: completely textual, mathematical formulas without text, mathematical formulas that are between blocks of text.

scholarly journals Convolutional neural-network-based classification of retinal images with different combinations of filtering techniques

2021 ◽  
Vol 11 (1) ◽  
pp. 480-490
Author(s):  
Asha Gnana Priya Henry ◽  
Anitha Jude
Keyword(s):  
Neural Network ◽  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Performance Metrics ◽  
Input Image ◽  
Application Techniques ◽  
Enhancement Method ◽  
Neural Network Input

Abstract Retinal image analysis is one of the important diagnosis methods in modern ophthalmology because eye information is present in the retina. The image acquisition process may have some effects and can affect the quality of the image. This can be improved by better image enhancement techniques combined with the computer-aided diagnosis system. Deep learning is one of the important computational application techniques used for a medical imaging application. The main aim of this article is to find the best enhancement techniques for the identification of diabetic retinopathy (DR) and are tested with the commonly used deep learning techniques, and the performances are measured. In this article, the input image is taken from the Indian-based database named as Indian Diabetic Retinopathy Image Dataset, and 13 filters are used including smoothing and sharpening filters for enhancing the images. Then, the quality of the enhancement techniques is compared using performance metrics and better results are obtained for Median, Gaussian, Bilateral, Wiener, and partial differential equation filters and are combined for improving the enhancement of images. The output images from all the enhanced filters are given as the convolutional neural network input and the results are compared to find the better enhancement method.

scholarly journals Robust deep convolutional neural network against image distortions

2021 ◽  
Vol 10 ◽  
Author(s):  
Liang-Yao Wang ◽  
Sau-Gee Chen ◽  
Feng-Tsun Chien
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
High Frequency ◽  
Input Image ◽  
Processing Unit ◽  
Different Types ◽  
Hybrid Module ◽  
Frequency Components ◽  
Discrete Wavelets ◽  
Value Decomposition

Many approaches have been proposed in the literature to enhance the robustness of Convolutional Neural Network (CNN)-based architectures against image distortions. Attempts to combat various types of distortions can be made by combining multiple expert networks, each trained by a certain type of distorted images, which however lead to a large model with high complexity. In this paper, we propose a CNN-based architecture with a pre-processing unit in which only undistorted data are used for training. The pre-processing unit employs discrete cosine transform (DCT) and discrete wavelets transform (DWT) to remove high-frequency components while capturing prominent high-frequency features in the undistorted data by means of random selection. We further utilize the singular value decomposition (SVD) to extract features before feeding the preprocessed data into the CNN for training. During testing, distorted images directly enter the CNN for classification without having to go through the hybrid module. Five different types of distortions are produced in the SVHN dataset and the CIFAR-10/100 datasets. Experimental results show that the proposed DCT-DWT-SVD module built upon the CNN architecture provides a classifier robust to input image distortions, outperforming the state-of-the-art approaches in terms of accuracy under different types of distortions.

A NEURAL-NETWORK-BASED IMAGE RESOLUTION ENHANCEMENT SCHEME FOR IMAGE RESIZING

2002 ◽  
Vol 02 (04) ◽  
pp. 503-517 ◽  
Author(s):  
HER-CHANG PU ◽  
CHIN-TENG LIN
Keyword(s):  
Neural Network ◽  
Resolution Enhancement ◽  
Input Image ◽  
Image Resolution ◽  
Natural Image ◽  
Image Resizing ◽  
Adaptive Interpolation ◽  
Supervised Learning Algorithms ◽  
Enhancement Algorithm

In this paper, a novel edge-oriented neural-network-based adaptive interpolation scheme for natural image is proposed. An image analysis module is used to classify pixels of the input image into non-oriented class and oriented class. The bilinear interpolation is used to interpolate the non-oriented regions and a neural network is proposed to interpolate the oriented regions. High-resolution digital images along with supervised learning algorithms can be used to automatically train the proposed neural network. Simulation results demonstrate that the proposed new resolution enhancement algorithm can produce higher visual quality of the interpolated image than the conventional interpolation methods.

scholarly journals Full-Reference Quality Metric Based on Neural Network to Assess the Visual Quality of Remote Sensing Images

2020 ◽  
Vol 12 (15) ◽  
pp. 2349 ◽  
Author(s):  
Oleg Ieremeiev ◽  
Vladimir Lukin ◽  
Krzysztof Okarma ◽  
Karen Egiazarian
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Visual Quality ◽  
Quality Metrics ◽  
Remote Sensing Images ◽  
Opinion Score ◽  
Different Types ◽  
Reference Quality ◽  
Improved Performance

Remote sensing images are subject to different types of degradations. The visual quality of such images is important because their visual inspection and analysis are still widely used in practice. To characterize the visual quality of remote sensing images, the use of specialized visual quality metrics is desired. Although the attempts to create such metrics are limited, there is a great number of visual quality metrics designed for other applications. Our idea is that some of these metrics can be employed in remote sensing under the condition that those metrics have been designed for the same distortion types. Thus, image databases that contain images with types of distortions that are of interest should be looked for. It has been checked what known visual quality metrics perform well for images with such degradations and an opportunity to design neural network-based combined metrics with improved performance has been studied. It is shown that for such combined metrics, their Spearman correlation coefficient with mean opinion score exceeds 0.97 for subsets of images in the Tampere Image Database (TID2013). Since different types of elementary metric pre-processing and neural network design have been considered, it has been demonstrated that it is enough to have two hidden layers and about twenty inputs. Examples of using known and designed visual quality metrics in remote sensing are presented.

Squeak and rattle noise classification using radial basis function neural networks

2020 ◽  
Vol 68 (4) ◽  
pp. 283-293
Author(s):  
Oleksandr Pogorilyi ◽  
Mohammad Fard ◽  
John Davy ◽  
Mechanical and Automotive Engineering, School ◽  
Mechanical and Automotive Engineering, School ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Accuracy ◽  
Training Method ◽  
Vehicle Interior ◽  
Trained Classifier ◽  
Different Types ◽  
Noise Classification ◽  
Automatic Tool ◽  
Multi Class Classification

In this article, an artificial neural network is proposed to classify short audio sequences of squeak and rattle (S&R) noises. The aim of the classification is to see how accurately the trained classifier can recognize different types of S&R sounds. Having a high accuracy model that can recognize audible S&R noises could help to build an automatic tool able to identify unpleasant vehicle interior sounds in a matter of seconds from a short audio recording of the sounds. In this article, the training method of the classifier is proposed, and the results show that the trained model can identify various classes of S&R noises: simple (binary clas- sification) and complex ones (multi class classification).

Convolutional Neural Network for Customer’s Opinion on Amazon Products

2019 ◽  
Vol 8 (3) ◽  
pp. 6634-6643 ◽  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Sentiment Analysis ◽  
Latent Dirichlet Allocation ◽  
Opinion Mining ◽  
Text Documents ◽  
Customer Churn ◽  
Learning Classifier ◽  
Review Spam

Opinion mining and sentiment analysis are valuable to extract the useful subjective information out of text documents. Predicting the customer’s opinion on amazon products has several benefits like reducing customer churn, agent monitoring, handling multiple customers, tracking overall customer satisfaction, quick escalations, and upselling opportunities. However, performing sentiment analysis is a challenging task for the researchers in order to find the users sentiments from the large datasets, because of its unstructured nature, slangs, misspells and abbreviations. To address this problem, a new proposed system is developed in this research study. Here, the proposed system comprises of four major phases; data collection, pre-processing, key word extraction, and classification. Initially, the input data were collected from the dataset: amazon customer review. After collecting the data, preprocessing was carried-out for enhancing the quality of collected data. The pre-processing phase comprises of three systems; lemmatization, review spam detection, and removal of stop-words and URLs. Then, an effective topic modelling approach Latent Dirichlet Allocation (LDA) along with modified Possibilistic Fuzzy C-Means (PFCM) was applied to extract the keywords and also helps in identifying the concerned topics. The extracted keywords were classified into three forms (positive, negative and neutral) by applying an effective machine learning classifier: Convolutional Neural Network (CNN). The experimental outcome showed that the proposed system enhanced the accuracy in sentiment analysis up to 6-20% related to the existing systems.

Enumeration of Cryptosporidium oocysts from surface water concentrates by laser-scanning cytometry

2000 ◽  
Vol 41 (7) ◽  
pp. 197-202 ◽  
Author(s):  
F. Zanelli ◽  
B. Compagnon ◽  
J. C. Joret ◽  
M. R. de Roubin
Keyword(s):  
Surface Water ◽  
Water Samples ◽  
Laser Scanning ◽  
Immunomagnetic Separation ◽  
Entire Surface ◽  
Cryptosporidium Oocysts ◽  
Different Types ◽  
Laser Scanning Cytometry ◽  
Direct Microscopic Observation

The utilization of the ChemScan® RDI was tested for different types of water concentrates. Concentrates were prepared by cartridge filtration or flocculation, and analysed either without purification, or after Immunomagnetic separation (IMS) or flotation on percoll-sucrose gradients. Theenumeration of the oocysts was subsequently performed using the ChemScan® RDI Cryptosporidium application. Enumeration by direct microscopic observation of the entire surface of the membrane was carried out as a control, and recoveries were calculated as a ratio between the ChemScan® RDI result and the result obtained with direct microscopic enumeration. The Chemscan enumeration technique proved reliable, with recoveries yielding close to 100% in most cases (average 125%, range from 86 to 467%) for all the concentration/purification techniques tested. The quality of the antibodies was shown to be critical, with antibodies from some suppliers yielding recoveries a low as 10% in some cases. This difficulty could, however, be overcome by the utilization of the antibody provided by Chemunex. These data conclusively prove that laser scanning cytometry, which greatly facilitates the microscopic enumeration of Cryptosporidium oocysts from water samples and decreases the time of observation by four to six times, can be successfully applied to water concentrates prepared from a variety of concentration/purification techniques.

Sign in / Sign up

Export Citation Format

Share Document