检索结果-内蒙古大学图书馆

wavelet Based Random Noise Removal from Color images Using Python 4

Wavelet Based Random Noise Removal from Color Images Using P...

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Bhonsle, Devanand Saxena, K.K. Uzma Sheikh, Ruhi Sahu, Anil Kumar Singh, Pushpendra Rizvi, Tanu Shri Shankaracharya Technical Campus Department of Electrical Engg. Bhilai India Govt. Engineering College Department of Electrical Engg. Bilaspur India Anjuman College of Engg. and Technology Department of Electrical Engineering Nagpur India Siddhartha Institute of Technology and Sciences Department of Electronics and Communication Engg. India Bhilai Institute of Technology Department of Electronics and Telecommunication Engineering Durg India

ISBN: (纸本)9798350343670

image de-noising is an essential field in image processing, encompassing a wide range of applications. This is pre-processing task in which unwanted noise signals are removed using different techniques. Noise are unwanted signals which deteriorate the useful information from the image. These information may be edges, ridges, contours are other fine structures. For different applications these details are important. Noise signals may contaminate the image partially or completely. It depends upon the type of noise and its level. Noise may be categories according to its characteristics. The most frequent types of noise signals encountered in image processing include Additive White Gaussian Noise, Speckle noise, salt and pepper noise, Rician noise, random noise, and more. Noise signals introduced in the images during data acquisition, transmission or due to faulty location. Additive white Gaussian noise is one of the most common noise signal which affect almost all the images in a certain extent. In this chapter we apply de-noising technique which is based on wavelet thresholding. wavelet transform is widely recognized as one of the most popular transforms in signal and image processing. It is used in various image processing applications. Thresholding is an essential component in wavelet transform, and it is commonly classified into two types: hard thresholding and soft thresholding. In the chapter we apply soft thresholding technique which outperforms hard thresholding technique. © 2024 IEEE.

关键词： image De-noising image processing images MSE PSNR SNR Thresholding wavelet Transform

来源：评论

学校读者我要写书评

暂无评论

Approximate subtractors designed for image processing applications

引用

INTEGRATION-THE vLSI JOURNAL 2025年 103卷

作者： Parameswari, P. Divya Ananthalakshmi, A. v. Puducherry Technol Univ Elect & Commun Engn Pondicherry India

Approximate circuits play a vital role in enhancing efficiency and optimizing resource use in modern computing systems. Their benefits are particularly notable in fields that tolerate minor inaccuracies, such as image processing, signal processing, and data mining, where a slight reduction in precision can lead to substantial savings in power and space requirements. This study explores an innovative design for an approximate full subtractor based on the principle of pruning, meticulously implemented using universal two-input NOR gates, valued for their cost efficiency, low power consumption, and compact design. Existing approximate subtractors have been designed using non-universal basic gates such as XOR, XNOR, NOT, and AND gates. In contrast, the proposed approach utilizes only the universal NOR gate, leading to improved circuit efficiency in terms of area, delay, and power consumption. Additionally, this work evaluates performance metrics of approximate circuits, demonstrating their effectiveness in various image processing applications involving full subtractors.

关键词： Approximate circuits Subtractor Pruning image processing

来源：评论

学校读者我要写书评

暂无评论

Secure visual communication with advanced cryptographic and image processing techniques

引用

MULTIMEDIA TOOLS AND applications 2023年第15期83卷 45367页

作者： Sathananthavathi, v. Kumar, K. Ganesh Kumar, M. Sathish Mepco Schlenk Engn Coll Sivakasi India

Securing data during transmission is critical to prevent unauthorized access, interception, or modification of the data. Data can be communicated securely while maintaining its confidentiality, integrity, and availability by using cryptographic algorithms and measures. In the proposed work, a hybrid data compression algorithm is proposed to increase the amount of input data that is encrypted using the Advanced Encryption Standard (AES) cryptography method to boost security level, and it can be utilized to carry out the lossy compacting Steganography method. By reducing the quantity of data transmitted, this technique can enable speedy transmission over a sluggish internet connection or use less space on different storage devices. The cover image is compressed using Discrete wavelet Transform (DWT), which reduces the cover image's dimensions by lossyly compressing the image. The ordinary text is converted to hexadecimal format from text. The encrypted data will then be inserted into the compressed cover picture using the least significant bit (LSB) with image vector array (IvA). Bits per pixel (BPP), Mean Squared Error (MSE), Peak signal to Noise Ratio (PSNR), and Structural Similarity Index (SSIM) were some of the metrics we used to evaluate the proposed technique.

关键词： Cryptography Steganography AES DWT LSB SSIM PSNR MSE and BPP

来源：评论

学校读者我要写书评

暂无评论

Time frequency images as predictors for depressed patients' respondent status to SSRI antidepressant

引用

BIOMEDICAL signal processing AND CONTROL 2025年 104卷

作者： Korani, Wael Domakonda, Shyam Sundar Univ North Texas Dept Informat Sci Denton TX 76207 USA

Depression is a mental disorder that might cause self-harm and suicidal thoughts if the level of depression reaches the refractory or recurrent depressive disorder stage. Depression can be categorized into four different levels that are defined based on a psychometric called Beck Depression Inventory (BDI): minimal, mild, moderate, and severe. Depression level is important to narrow down the selection of depression therapy. There are several ways to treat depression and among them medications, Electroconvulsive therapy (ECT), repetitive Transcranial Magnetic Stimulation (rTMS), a combination of medication and rTMS. In the minimal depression level, an antidepressant medication is the best option such as, tricyclic antidepressants (TCAs), monoamineoxidase inhibitor (MAOI), and Selective serotonin reuptake inhibitors (SSRIs). This study introduces a deep learning (DL) architecture trained on time frequency images derived from EEG signals to predict the patient's respondent status to SSRI antidepressant. We introduce an efficient framework that integrate image technique with stat-of-the-art DL models. various time-frequency methods, including wavelet synchrosqueezed transform (WSST), Continuous wavelet transform (CWT), and Discrete wavelet transform (DWT), are explored to convert EEG signals into time-frequency images. Among these methods, WSST demonstrates superior performance in extracting relevant information encoded within EEG signals, outperforming CWT and DWT. Time-frequency images generated using WSST contribute to the achievement of an accuracy level of 98.89% when fed into a proposed lightweight custom CNN architecture. The results show that WSST is powerful in capturing crucial signal features in detecting the outcome of depression therapy. Our proposed architecture is simple and computationally efficient, despite its simple design, outperforms more complex architectures such as, EfficientNetv2L, ResNet152v2, Xception, DenseNet201, and MobileNetv2. The propose

关键词： Major Depressive Disorder (MDD) Electroencephalogram (EEG) Selective serotonin reuptake inhibitors (SSRI) wavelet synchrosqueezed transform (WSST)

来源：评论

学校读者我要写书评

暂无评论

image data protection in IoT applications using significant block selection based image watermarking

引用

MULTIMEDIA TOOLS AND applications 2023年第4期82卷 5073-5090页

作者： verma, vivek Singh Gupta, Sandesh Gupta, Phalguni Govt Polytech Shahbad Rampur 244901 India CSJM Univ Univ Inst Engn & Technol Kanpur 208024 Uttar Pradesh India GLA Univ Mathura 281406 India

Recent developments in IoT (Internet of Things) and its importance are significantly accepted in different applications of medical research, automobile sector, robotics, national security, and real-life usage. Securing the interface between IoT and the real-world is one of the challenging tasks for every researcher. This paper presents a watermarking scheme to protect the image database used in the presentation layer of IoT applications. The host image is decomposed using the Lifting wavelet transform (LWT) and fixed-size blocks of low-frequency components are obtained. Procedurally selected blocks of frequency components called a significant set of blocks (SSB) are used to quantize the watermark bits into it. Considering each block similar to the node of wireless networks an algorithm for block selection is proposed. Watermark extraction from an attacked watermarked image is performed using an adaptive thresholding approach. Key-based randomization at various levels provides the security feature to the proposed scheme. The LWT is used to make the algorithm more robust and computationally fast. However, randomly selected root based SSB generation leads the scheme more secure from an external intruder. The scheme performs significantly well under various signal processing operations;and outperforms in comparison with other existing schemes.

关键词： Lifting wavelet transform Block selection Significant set of blocks image protection

来源：评论

学校读者我要写书评

暂无评论

REAL-TIME IMPLEMENTATION OF LWT BASED NOvEL IR AND vI FUSION ALGORITHM USING RASPBERRY PI PLATFORM

引用

Telecommunications and Radio Engineering (English translation of Elektrosvyaz and Radiotekhnika) 2024年第4期83卷 57-85页

作者： Srinivasu, Lingamallu Naga Panguluri, Sumanth Kumar Kandula, Srinivasa Rao vasanthi, Ponduri Department of Electronics and Communication Engineering Bapatla Engineering College Andhra Pradesh Bapatla522102 India Department of Electronics and Communication Engineering Eswar College of Engineering Guntur Andhra Pradesh Narasaraopet522601 India Department of Electronics and Communication Engineering Dhanekula Institute of Engineering and Technology Ganguru Andhra Pradesh Vijayawada521139 India

One of the most important and active areas of image processing research is visible and thermal-light image fusion. Moreover, real-time visible and thermal-light image fusion has been utilized in multiple kinds of applications such as surveillance devices, military applications, medical diagnosis, remote sensing, etc. Hence, this paper suggests a real-time application of visible and infrared (v-I) image fusion using lift wavelet transform (LWT) and implemented on the Raspberry Pi. The proposed morphological operations-based unsharp masking enhancement technique overcomes the low contrast issue of the fused image. Next, the LWT provides the good feature (smooth and detail) layers of visible image (vI) and infrared image (IRI) when compared to other transformations. Due to this, we have overcome the problem of spatial distortions in the fused image. Moreover, the proposed novel fusion techniques such as, mean-weighted fusion rule based on filters and max-weighted fusion rule based on filters generate the fused image with improved texture information and overcome the problem of edge information loss. The real-time application of the v-I image fusion is implemented through the portable hardware device Raspberry Pi. Finally, the experimental results show that the suggested framework has produced a fused image with improved visual quality, rich edge information, high contrast, low spatial distortions, and more texture information, when compared to the results of existing methodologies. © 2024 Begell House Inc.. All rights reserved.

关键词： wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Identity Recognition Using wavelet-Based Neural Networks: Review and Comparative Study

Identity Recognition Using Wavelet-Based Neural Networks: Re...

引用

2024 International Conference on Decision Aid Sciences and applications, DASA 2024

作者： Ramalakshmi, Eliganti Sreya, Dama Pranati Poojitha, Tanguturi Chaitanya Bharathi Institute of Technology Department of Information Technology Hyderabad India

ISBN: (纸本)9798350369106

wavelet neural networks are a unique combination of wavelet analysis and neural network architectures, thus providing the benefits of advanced signal processing. Unlike traditional methods, WNNs offer a multi-resolution approach that outshines for nonstationary signals;therefore, these are very useful in applications related to areas such as biomedical signal analysis, image processing, and time-series forecasting. Architecture of WNNs enables the replacement of activation functions with wavelet functions for the extraction of localized features, making both processing and interpretation of data much more efficient. Some of the recent improvements in designing WNNs improve its computational efficiency to suit the requirements of real-time applications and also to incorporate it into deep learning frameworks, but still, one of the main challenges faced in WNNs such as computational complexity and scalability need to be addressed. As the historical development, core contributions, and evolving architecture of WNNs is done, this paper represents those along with filling up certain existing research gaps. This research paper addresses future directions regarding hybrid models that combine synergies of CNNs with RNNs as well as WNNs and therefore posits opening its way for enhanced performance across various domains. Researching such an area ensures and guarantees further expansion of applications in WNNs besides strengthening their importance in signal processing in the modern arena. © 2024 IEEE.

关键词： wavelet analysis

来源：评论

学校读者我要写书评

暂无评论

The Octonionic Moritoh Transform on Octonionic Function Spaces

引用

RUSSIAN MATHEMATICS 2025年第2期69卷 83-94页

作者： Kumar, A. Singh, S. K. Singh, Sh. K. Babasaheb Bhimrao Ambedkar Univ Lucknow 226025 India Mahatma Gandhi Cent Univ Motihari 845401 Bihar India

This article explores the challenges and applications of the octonion Fourier transform, with a focus on wavelet analysis. We extend the Moritoh wavelet transform to the octonionic Besov spaces, the weighted octonionic Besov spaces, the octonionic BMO spaces, and the octonionic weighted BMO spaces. The derived bounds for the octonionic Moritoh wavelet transform in these spaces contribute to a deeper understanding of its behavior. Our findings pave the way for future research in signal processing, image analysis, and the intersection of octonion wavelet analysis with other mathematical theories.

关键词： octonion Fourier transform wavelet transform Besov space BMO space

来源：评论

学校读者我要写书评

暂无评论

Morlet wavelet transformation based deep similarity structured neural learning for image quality assessment

引用

Multimedia Tools and applications 2024年第16期84卷 1-19页

作者： Balakrishnan, N. Robinson, Y. Harold Department of MCA Sona College of Technology Salem India Department of Computer Science and Engineering Francis Xavier Engineering College Tirunelveli India

Quality assessment is a key problem to be resolved in image processing. Few research works have been designed to analyze the quality of images using different techniques. However, the accuracy involved during the process of image quality assessment was not sufficient. A novel method Morlet wavelet Transformation Based Deep Similarity Structured Neural Learning (MWT-DSSNL) is proposed to enhance the performance of image quality assessment with minimal peak signal-to-noise ratio. The MWT-DSSNL Method is based on artificial neural networks with representation learning. The MWT-DSSNL Method initially gets the number of images from a given dataset as input. The MWT-DSSNL Method uses multiple layers to extract higher-level features from the input images. The MWT-DSSNL Method is a Feed-Forward network where each layer employs the output from the previous layer as input. The MWT-DSSNL Method is designed based on a biological neural network of the human brain. Contrary to the existing method, the MWT-DSSNL Method uses multiple hidden layers and Morlet wavelet transformation to deeply analyze input images and thereby extract features such as luminance, contrast, and structure with a minimal amount of time consumption. By considering the discovered features, finally MWT-DSSNL Method determines structural similarity and thereby exactly identifies the quality of input images with a lower time. From that, the MWT-DSSNL Method achieves enhanced image quality assessment performance when compared to existing works. The simulation of the MWT-DSSNL Method is conducted on factors such as PSNR, average processing time, quality detection accuracy, and false positive rate with different numbers of input images. The simulation result depicts that the MWT-DSSNL method increases the accuracy and also minimizes the time of image quality assessment when compared to conventional works. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Optimized recursive approximate multipliers for edge detection and image smoothing applications

引用

MICROSYSTEM TECHNOLOGIES-MICRO-AND NANOSYSTEMS-INFORMATION STORAGE AND processing SYSTEMS 2024年 1-12页

作者： Tammineni, vishnu Beura, Srikant Kumar Murthy, M. v. H. Bhaskara Majumdar, Shubhankar Saha, Prabir Natl Inst Technol ECE Dept Shillong 793003 Meghalaya India Lendi Inst Engn & Technol ECE Dept Vizianagram 535005 Andhra Prades India Aditya Inst Technol & Management ECE Dept Srikakulam 532201 Andhra Prades India

This paper presents a novel approach to recursive approximate multipliers (RRAM) tailored for digital image processing tasks in vLSI circuits focusing on enhancing power efficiency and error control. Two multipliers i.e., RRAM-I and RRAM-II have been reported here and also been applied in image processing applications like smoothing and edge detection. These multipliers offer a significant improvements in image quality, as evidenced by enhanced peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). RRAM-I demonstrates a remarkable 62.60% reduction in energy usage compared to traditional models, while RRAM-II further improves, achieving a 63.78% reduction in energy consumption. Additionally, for 16-bit multipliers, RRAM-I and RRAM-II offer a substantial performance gains over existing models. By focusing on power efficiency and accuracy, our designs are positioned as the best choices for practical use in IoT devices, mobile devices, and embedded systems, offering superior performance and adaptability in various image processing applications.

关键词： RRAM

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：