检索结果-内蒙古大学图书馆

Digital Signal Processing and its Applications (DSPA), International Conference on

作者： Y.S. Bekhtin P.E. Zhgutov Department of automatics and information technologies in control Ryazan State Radio Engineering University named after V.F. Utkin Ryazan Russia

ISBN: (数字)9798331518752

ISBN: (纸本)9798331518769

The paper is devoted to solving the problem of restoring noised images by convolutional autoencoders. It is provided a comparative research of three types of convolutional autoencoder architectures: the standard architecture based on convolution and deconvolution operations; the architecture based on Residual-blocks; the architecture based on Residual-blocks using a discriminator network. The effectiveness of the autoencoder architectures have been evaluated on synthetically noisy color images. Subjective and objective metrics as MSE, RMSE, PSNR, SSIM were used to evaluate the quality of the restored images. In the course of a comparative study, some recommendations were drawn on which of the explored autoencoders to choose providing the best effectiveness restoring the quality of distorted images.

关键词： Deconvolution Convolution Autoencoders Computer architecture Digital signal processing Image restoration Computational efficiency Noise measurement Convolutional neural networks Standards

来源：评论

学校读者我要写书评

暂无评论

Wavelet-based Filtering of Noisy Images by Amplification of Low-Frequency Components in High-Frequency Subbands

Wavelet-based Filtering of Noisy Images by Amplification of ...

引用

Digital Signal Processing and its Applications (DSPA), International Conference on

作者： Y. S. Bekhtin V. T. Trinh Department of Automatics and Information Technologies in Control Ryazan State Radio Engineering University named after V.F. Utkin Ryazan Russian Federation

ISBN: (数字)9798331518752

ISBN: (纸本)9798331518769

The paper describes a new method of noisy image restoration based on amplification of low-frequency components in high-frequency subbands, or details of fast wavelet transform (FWT). It makes a difference with respect to well-known wavelet filtering methods which are typically based on soft thresholding of wavelet coefficients belonging to high-frequency subbands of a noisy image. At the same time, the low-frequency component, or approximation can be used to extract the low-frequency components corresponding the details. It allows modifying the details of the FWT by adding the extracted low-frequency components that leads to increasing the signal-to-noise ratios in subbands. The paper contains the experimental results of modeling proving the effectiveness of the suggested method comparing to some widely used filtering methods, too. The results of modeling have shown that the proposed method allows improving quality of restored image by increasing both the signal-to-noise ratio and significantly reducing the number of ringing artifacts.

关键词： Wiener filters Filtering Image edge detection Digital signal processing Image restoration Noise measurement Signal to noise ratio Wavelet coefficients

来源：评论

学校读者我要写书评

暂无评论

Combined Speckle Removal Based on the Wiener Filter and Wavelet Transform using Texture Analysis

Combined Speckle Removal Based on the Wiener Filter and Wave...

引用

International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE)

作者： Y. S. Bekhtin V. T. Trinh Department of Automatics and Information Technologies in Control Ryazan State Radio Engineering University named after V.F. Utkin Ryazan Russian Federation

ISBN: (数字)9798331531836

ISBN: (纸本)9798331531843

The existing despeckling methods typically encounter difficulties in achieving an optimal equilibrium between the suppression of noise and the preservation of critical image features, particularly in scenarios involving images that encompass both homogeneous (smooth) areas and heterogeneous (textured or edge-dense) regions. This paper proposes a hybrid approach combining wavelet filtering and Wiener filtering, leveraging their complementary strengths. The results of computer modeling have shown that the wavelet filters are effective in homogeneous regions by exploiting multi-scale sparsity, while the Wiener filter adaptively preserves textures in heterogeneous areas. By segmenting the image based on regional homogeneity, we apply the corresponding filter, achieving superior noise reduction in the sense both objective and subjective criteria.

关键词： Wavelet transforms Power engineering Image segmentation Wiener filters Filters Image edge detection Noise Speckle Wavelet analysis Image texture analysis

来源：评论

学校读者我要写书评

暂无评论

Combined textural-dependent despeckling in SAR images 3

Combined textural-dependent despeckling in SAR images

引用

3rd Mediterranean Conference on Embedded Computing, MECO 2014

作者： Bekhtin, Yury S. Malebo, Damião P. Department of Automatics and Information Technologies in Control Ryazan State Radio Engineering University Ryazan Russia

ISBN: (纸本)9781479948260

The suggested method is aimed to be realized in different on-board embedded systems for images obtained by synthetic aperture radar (SAR) and featured with the problem of speckle. The conducted analysis of real SAR images has shown that the statistical properties of speckle strongly depend on the texture of the irradiated surface. The main idea of the method is to select the optimum despeckling algorithms from the recommended database of the algorithms using texture analysis and apply the selected algorithms to various segments of SAR images having different variances and probability density functions of speckle. The results of modeling have shown the advantage of the combined filtering in comparing with some famous despeckling procedures under criteria such as PSNR, SSIM, etc.

关键词： Speckle

来源：评论

学校读者我要写书评

暂无评论

Formation of attribute spaces using wavelets in automatic classification of explosives 08

Formation of attribute spaces using wavelets in automatic cl...

引用

9th International Conference on Computer Systems and technologies and Workshop for PhD Students in Computing, CompSysTech'08

作者： Shopov, Nikolai Ilarionov, Rajcho Simeonov, Ivan Kilifarev, Hristo Department of Automatics Information and Control Technique University of Food Technologies-Plovdiv Bulgaria Department of Computer Systems and Technologies Technical University of Gabrovo Bulgaria Department of Automation Information and Control Systems Technical University of Gabrovo Bulgaria

ISBN: (纸本)9789549641523

The non-contact automatic on-line classification of explosives is a multi-aspect task. It involves choosing the method of information gathering, planning and conduction of experiments, choosing a classifier, formation of training and control samples, synthesis and reduction of recognition attributes, etc. This paper presents the results of conducted experiments for non-contact ultrasonic information gathering, formation of attribute spaces by means of wavelet transformations and an automatic classification of explosives.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Adaptive Neuro-Fuzzy Inference System for Beverage Identification Based on VIS/NIR Spectral Analysis

Adaptive Neuro-Fuzzy Inference System for Beverage Identific...

引用

2024 International Conference automatics and Informatics, ICAI 2024

作者： Sestrimska, Mariyana Nachev, Veselin Titova, Tanya Nikovski, Plamen University of Food Technologies Department of Automatics Information and Control Systems Plovdiv Bulgaria University of Food Technologies Department of Electronics and Electrical Engineering Plovdiv Bulgaria

ISBN: (纸本)9798350353907

In the present paper, a model of a hybrid neural-fuzzy system adapted to identify drinks with certain quality indicators, more specifically - tea blends with different ingredients, has been synthesized. To illustrate the work of the classifier, different types of tea were used, for which spectral characteristics of diffuse reflectance in the VIS/NIR range of the electromagnetic spectrum were taken. PCA is used to reduce the feature space of experimental databases. The first three components obtained as a result of the PCA-analysis are selected as the input vectors of the neural fuzzy classifier. The pattern recognition results are as follows: 98.3% in training and 81.3% in testing. The obtained relatively high percentage of accuracy for the work of the hybrid artificial neural network is proof of the successful implementation of the set classification task. © 2024 IEEE.

关键词： Tea

来源：评论

学校读者我要写书评

暂无评论

Non-contact ultrasound method for identification of yogurt according to its butter content 09

Non-contact ultrasound method for identification of yogurt a...

引用

International Conference on Computer Systems and technologies and Workshop for PhD Students in Computing, CompSysTech'09

作者： Shopov, Nikolay Ilarionov, Raycho Simeonov, Ivan Kilifarev, Hristo Department of Automatics Information and Control Technique University of Food Technologies Plovdiv Bulgaria Department of Computer Systems and Technologies Technical University of Gabrovo Bulgaria Department of Automation Information and Control Systems Technical University of Gabrovo Bulgaria

ISBN: (纸本)9781605589862

In the current paper is proposed an approach for identification of yogurt according to its butter content, based on the methods for recognition of images with receiving of initial information by ultrasound. There are results presented from the made research regarding the ability for synthesis of symptoms for classification by means of discrete wavelet transformation. Classifiers are synthesized with the method "K-nearest-neighbors" (KNN) and are tested with independent control sample. It is realized a classification of yogurt with butter content 1, 2, 3, 3.6 and 5% with accuracy above 94%. © 2009 ACM.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Properties of crude laccase from Trametes versicolor produced by solid-substrate fermentation

引用

Advances in Bioscience and Biotechnology 2010年第3期1卷 208-215页

作者： Ivanka Stoilova Albert Krastanov Veselin Stanchev Department of Biotechnology University of Food Technologies Department of Automatics Information and Control Systems University of Food Technologies

A low-cost process for the production of laccases is necessary for a sustainable enzymatic wastewater treatment. Therefore, it is necessary to establish an easy and low-cost procedure for the production of laccase. In the present study the properties of crude laccase from Trametes versicolor produced by solid-substrate fermentation is investigated. The application of the enzyme for dye decolorization is also studied. Crude laccase from the studied culture established maximal activity at 45ºC. The enzyme retained over 90% of its activity in the temperature range 40- 47ºC and pH 4.5. The kinetic constants of the crude enzyme was also determined. In the presence of KCl, NaCl, CaCl2, MnSO4 and MgSO4, laccase demonstra- ted high stability—over 50% of its initial activity was still retained after 4-month incubation. Complete loss of enzymatic activity was observed in the presence of CuCl2, FeCl2, FeCl3 and NaN3 after 30 min of incubation. 100% decolorization by investigated crude laccase was completed in the case of Indigo Carmine for 4 h, Remazol Brilliant Blue R—for 6 h, Orange II— for 48 h and Congo Red—for 13 d.

关键词： Laccase Solid-Substrate Fermentation Trametes versicolor Dye Decolorization

来源：评论

学校读者我要写书评

暂无评论

Instrumental Data Fusion for Food Analysis Application

引用

IFAC-PapersOnLine 2019年第25期52卷 58-63页

作者： Veselin G. Nachev Tanya P. Titova Rosen D. Kosturkov Department of Automatics Information and Control Systems University of Food Technologies Plovdiv 4002 26 Maritza Blvd

The present paper discusses instrumental tools for analysis, control and automatic classification of foods. As accents in research is the task of increasing instrumental information in defining the quality of food, data fusion from different sensor systems and fusion classifier based on training samples. We demonstrate proposed solutions in the classification for two tasks - commercial citrus drinks and chicken meat.

关键词： multi-sensor system data fusion classification food analysis e-nose

来源：评论

学校读者我要写书评

暂无评论

Combined textural-dependent despeckling in SAR images

Combined textural-dependent despeckling in SAR images

引用

Mediterranean Conference on Embedded Computing (MECO)

作者： Yury S. Bekhtin Damião P. Malebo Department of automatics and information technologies in control Ryazan State Radio Engineering University Rvazan Russia

关键词： Speckle Synthetic aperture radar Wiener filters Filtering Wavelet transforms Image segmentation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：