检索结果-内蒙古大学图书馆

Hybrid deep learning Approach for Enhanced Animal Breed Classification and Prediction

TRAITEMENT DU SIGNAL 2023年第5期40卷 2087-2099页

作者： Khan, Safdar Sardar Doohan, Nitika Vats Gupta, Manish Jaffari, Sakina Chourasia, Ankita Joshi, Kriti Panchal, Bhupendra RKDF Univ Dept Comp Sci & Engn Bhopal 462033 India Medi Caps Univ Dept Comp Sci & Engn Indore 453331 India GLA Univ Dept Elect & Commun Engn Mathura 281406 India VIT Bhopal Univ Sch Comp Sci & Engn Sehore 466114 India

The precise classification of animal breeds from image data is instrumental in real-time animal monitoring within forest ecosystems. Traditional computer vision methods have increasingly fallen short in accuracy due to the rapid progression of technology. To address these limitations, more advanced methodologies have emerged, significantly improving the accuracy of image classification, recognition, and segmentation tasks. The advent of "deep learning" has revolutionized various fields, particularly in object identification and recognition. Animal breed categorization is an important job in the field of image processing, and this research attempts to create a unique deep learning-based model for this purpose. The aim of this research is to devise efficient methodologies for image-based animal breed categorization to achieve superior accuracy levels. A hybrid deep learning model is proposed for animal breed prediction. The animal-10 dataset, obtained from Kaggle, serves as the empirical foundation for this study. The dataset underwent preprocessing, including edge deletion, normalization, and image scaling. Additionally, the animal images were converted into grayscale. Following this preprocessing phase, feature extraction was performed using two deep learning methods, namely VGG-19 and DenseNet121. The performance metrics, including accuracy, F1 score, recall, precision, and loss, were computed for the developed model using the Python simulation tool. Experimental results indicate that the proposed model outperforms existing current models in terms of these metrics. This research outcomes hold promising implications for the advancement of animal breed classification and prediction techniques.

关键词： animal breed prediction image processing classification deep learning VGG-19, densenet-121

来源：评论

学校读者我要写书评

暂无评论

A comprehensive study on enhanced QR extraction techniques with deep learning-based verification

引用

APPLIED INTELLIGENCE 2025年第7期55卷 1-22页

作者： Alam, Nur Sagar, A. S. M. Sharifuzzaman Zhang, Wenqi Jin, Taicheng Dosset, Arailym Dang, L. Minh Moon, Hyeonjoon Sejong Univ Dept Comp Sci & Engn Seoul 05006 South Korea Sejong Univ Dept Intelligent Mechatron Engn Seoul 05006 South Korea Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Duy Tan Univ Fac Informat Technol Da Nang 550000 Vietnam

In the digital age, Quick Response (QR) codes have become essential in sectors such as digital payments and ticketing, propelled by advancements in Internet of Things (IoT) and deep learning. Despite their growing use, there are significant challenges in the accurate extraction and verification of QR codes, particularly in dynamic environments. Traditional methods struggle with issues like variable lighting, complex backgrounds, and counterfeits, which degrade the performance of QR code extraction and verification processes. This paper introduces a comprehensive approach that refines QR code extraction using enhanced adaptive thresholding techniques and incorporates a deep learning framework specifically tailored for robust QR code verification. Our methodology integrates dynamic window size adjustment, statistical weighting, and post-thresholding refinement to ensure precise QR code extraction under varying conditions. The verification process employs the ShuffleNetV2 network to ensure high performance with significantly low processing times suitable for real-time applications. Additionally, our deep learning model is trained on a comprehensive dataset comprising 28,523 images across 24 distinct QR code pattern classes, including variations in lighting, noise, and backgrounds to simulate real-world conditions. Experimental results demonstrate that our proposed methodology outperforms competing techniques in both processing speed and recognition accuracy, achieving a processing time of 0.08 seconds and a validation accuracy of 99.99% in constrained scenarios. Our approach shows an exceptional ability to distinguish real QR codes from counterfeits and highlights the significance and efficacy of our method in addressing contemporary challenges.

关键词： QR code extraction deep learning Feature extraction Verification

来源：评论

学校读者我要写书评

暂无评论

A novel deep learning technique for medical image analysis using improved optimizer

引用

HEALTH INFORMATICS JOURNAL 2024年第2期30卷

作者： Agarwal, Vertika Lohani, Mc Bist, Ankur Singh Graph Era Hill Univ Bhimtal India

Application of Convolutional neural network in spectrum of Medical image analysis are providing benchmark outputs which converges the interest of many researchers to explore it in depth. Latest preprocessing technique real ESRGAN (Enhanced super resolution generative adversarial network) and GFPGAN (Generative facial prior GAN) are proving their efficacy in providing high resolution dataset. Objective: Optimizer plays a vital role in upgrading the functioning of CNN model. Different optimizers like Gradient descent, Stochastic Gradient descent, Adagrad, Adadelta and Adam etc. are used for classification and segmentation of Medical image but they suffer from slow processing due to their large memory requirement. Stochastic Gradient descent suffers from high variance and is computationally expensive. Dead neuron problem also proves to detrimental to the performance of most of the optimizers. A new optimization technique Gradient Centralization is providing the unparalleled result in terms of generalization and execution time. Method: Our paper explores the next factor which is the employment of new optimization technique, Gradient centralization (GC) to our integrated framework (Model with advanced preprocessing technique). Result and conclusion: Integrated Framework of real ESRGAN and GFPGAN with Gradient centralization provides an optimal solution for deep learning models in terms of Execution time and Loss factor improvement.

关键词： gradient centralization medical image analysis real enhanced super resolution generative adversarial network generative facial prior GAN

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Classification of Photovoltaic Panels Based on Convolutional Neural Network

引用

Computers, Materials & Continua 2023年第1期74卷 1437-1455页

作者： S.Prabhakaran R.Annie Uthra J.Preetharoselyn Department of Computational Intelligence SRM Institute of Science and TechnologyChengalpattu603203India Department of Electrical Engineering SRM Institute of Science and TechnologyChengalpattu603203India

Photovoltaic(PV)boards are a perfect way to create eco-friendly power from *** defects in the PV panels are caused by various conditions;such defective PV panels need continuous *** recent development of PV panel monitoring systems provides a modest and viable approach to monitoring and managing the condition of the PV *** general,conventional procedures are used to identify the faulty modules earlier and to avoid declines in power *** existing deep learning architectures provide the required output to predict the faulty PV panels with less accuracy and a more time-consuming *** increase the accuracy and to reduce the processing time,a new Convolutional Neural Network(CNN)architecture is ***,in the present work,a new real-time Multi Variant deep learning Model(RMVDM)architecture is proposed,and it extracts the image features and classifies the defects in PV panels quickly with high *** defects that arise in the PV panels are identified by the CNN based RMVDM using RGB *** biggest difference between CNN and its predecessors is that CNN automatically extracts the image features without any help from a *** technique is quantitatively assessed and compared with existing faulty PV board identification approaches on the large real-time *** results show that 98%of the accuracy and recall values in the fault detection and classification process.

关键词： Photovoltaic panels deep learning defect feature extraction RMVDM

来源：评论

学校读者我要写书评

暂无评论

An effective framework based on hybrid learning and kernel principal component analysis for face manipulation detection

引用

SIGNAL image AND VIDEO processing 2024年第5期18卷 4811-4820页

作者： Thakur, Rahul Rohilla, Rajesh Delhi Technol Univ Elect & Commun Engn Delhi 110042 India

Face manipulation is the process of modifying facial features in videos or images to produce a variety of artistic or deceptive effects. Face manipulation detection looks for altered or falsified visual media in order to differentiate between real and fake facial photographs or videos. The intricacy of the techniques used makes it difficult to detect face manipulation, particularly in the context of technologies like deepFake. This paper presents an efficient framework based on Hybrid learning and Kernel Principal Component Analysis (KPCA) to extract more extensive and refined face-manipulating attributes. The proposed method utilizes the EfficientNetV2-L model for feature extraction, topped up with KPCA for feature dimensionality reduction, to distinguish between real and fake facial images. The proposed method is robust to various facial manipulations techniques such as identity swap, expression swap, attribute-based manipulation, and entirely synthesized faces. In this work, data augmentation is used to solve the problem of class imbalance present in the dataset. The proposed method has less execution time while achieving an accuracy of 99.3% and an F1 Score of 0.98 on the Diverse Fake Face Dataset (DFFD).

关键词： deepFake Face manipulation detection deep learning Hybrid learning EfficientNetV2

来源：评论

学校读者我要写书评

暂无评论

Self-FuseNet: Data Free Unsupervised Remote Sensing image Super-Resolution

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2023年 16卷 1710-1727页

作者： Mishra, Divya Hadar, Ofer Ben Gur Univ Negev Sch Elect & Comp Engn Beer Sheva Israel

real-world degradations deviate from ideal degradations, as most deep learning-based scenarios involve the ideal synthesis of low-resolution (LR) counterpart images by popularly used bicubic interpolation. Moreover, supervised learning approaches rely on many high-resolution (HR) and LR image pairings to reconstruct missing information based on their association, developed by complex long hours of deep neural network training. Additionally, the trained model's generalizability on various image datasets with various distributions is not guaranteed. To overcome this challenge, we proposed our novel Self-FuseNet, particularly for extremely poor-resolution satellite images. Also, the network exhibits strong generalization performance on additional datasets (both "ideal " and "nonideal " scenarios). The network is especially for those image datasets suffering from the following two significant limitations: 1) nonavailability of ground truth HR images;2) limitation of a large count of the unpaired dataset for deep neural network training. The benefit of the proposed model is threefold: 1) it does not require any significant extensive training data, either paired or unpaired but only a single LR image without prior knowledge of its distribution;2) it is a simple and effective model for super-resolving very poor-resolution images, saving computational resources and time;3) using UNet, the processing of data are accelerated by the network's wide skip connections, allowing image reconstruction with fewer parameters. Rather than using an inverse approach, as common in most deep learning scenarios, we introduced a forward approach to super-resolve exceptionally LR remote sensing images. This demonstrates its supremacy over recently proposed state-of-the-art methods for unsupervised single real-world image blind super-resolution.

关键词： Feature extraction Superresolution Satellites Training image reconstruction Spatial resolution deep learning Blind image super-resolution (SR) data fusion deep learning self-fusion unsupervised image super-resolution (SR)

来源：评论

学校读者我要写书评

暂无评论

deep learning Approach for a Machine-Human interface based on optical real-time Gesture Recognition for Automated Guided Vehicles

Deep Learning Approach for a Machine-Human interface based o...

引用

Conference on real-time processing of image, Depth, and Video Information

作者： Krishnakumar, Kiran Raj Gersmeier, Laura Harders, Leif Ole Hussmann, Stephan West Coast Univ Appl Sci Fritz Thiedemann Ring 20 D-25746 Heide Germany REINHOLZ Technol GmbH Kirchhoffstr 1A D-25524 Itzehoe Germany

ISBN: (纸本)9781510673199;9781510673182

The intersection of deep learning and programmable logic controllers (PLCs) can lead to innovative applications in automation. One of the exciting application areas are gesture-based control systems for Automated Guided Vehicles (AGVs). AGVs are used in various industries for material handling, logistics, warehouse automation, etc. Traditionally, these vehicles are controlled using predefined routes or remote controls, but with gesture-based control, operators can communicate more naturally and efficiently. The incorporation of YOLO-Pose in YOLO versions 7 and 8 has elevated the YOLO algorithm to a leading tool for creating gesture recognition models. The YOLO algorithm employs convolutional neural networks (CNN) to detect objects in real-time. These latest YOLO models offer significantly improved accuracy, speed, and reduced training times. This paper presents the comparative results of 2D gesture recognition transfer learning models created using the YOLO v5, v7, and v8 models, along with the steps taken to implement the model in a PLC-controlled AGV. Over 14,000 images were collected to build the models. A semi-automated approach was used to annotate them. Five models were created: two Keypoint models and three object detection models using transfer learning techniques with the same hyperparameters.

关键词： real-time image processing machine-human interface gesture recognition convolutional neural networks (CNN) automated guided vehicles machine learning deep-learning networks

来源：评论

学校读者我要写书评

暂无评论

Multimodal Engagement Recognition From image Traits Using deep learning Techniques

引用

IEEE ACCESS 2024年 12卷 25228-25244页

作者： Sukumaran, Ajitha Manoharan, Arun Vellore Inst Technol Sch Elect Engn Vellore 632014 India Vellore Inst Technol Sch Elect Engn Embedded Technol Vellore 632014 India

Learner engagement is a significant factor determining the success of implementing an intelligent educational network. Currently the use of Massive Open Online Courses has increased because of the flexibility offered by such online learning systems. The COVID period has encouraged practitioners to continue to engage in new ways of online and hybrid teaching. However, monitoring student engagement and keeping the right level of interaction in an online classroom is challenging for teachers. In this paper we propose an engagement recognition model by combining the image traits obtained from a camera, such as facial emotions, gaze tracking with head pose estimation and eye blinking rate. In the first step, a face recognition model was implemented. The next stage involved training the facial emotion recognition model using deep learning convolutional neural network with the datasets FER 2013. The classified emotions were assigned weights corresponding to the academic affective states. Subsequently, by using the Dlib's face detector and shape predicting algorithm, the gaze direction with head pose estimation, eyes blinking rate and status of the eye (closed or open) were identified. Combining all these modalities obtained from the image traits, we propose an engagement recognition system. The experimental results of the proposed system were validated by the quiz score obtained at the end of each session. This model can be used for real time video processing of the student's affective state. The teacher can obtain a detailed analytics of engagement statics on a spreadsheet at the end of the session thus facilitating the necessary follow-up actions.

关键词： deep learning engagement recognition facial expression gaze direction head-pose estimation

来源：评论

学校读者我要写书评

暂无评论

Efficient Remote Health Monitoring Using deep learning and Parallel Systems

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2024年第10期15卷 174-186页

作者： El Khadiri, Zakaria Latif, Rachid Saddik, Amine Ibn Zohr Univ Agadir Natl Sch Appl Sci Lab Syst Engn & Informat Technol LISTI Agadir Morocco Ibn Zohr Univ Fac Appl Sci Ait Melloul Morocco

This study presents a novel approach for non- contact extraction of physiological parameters, such as heart rate and respiratory rate, from facial images captured using RGB cameras, leveraging recent advancements in deep learning and signal processing techniques. The proposed system integrates Artifacts intelligent-driven algorithms for accurately estimating vital signs, addressing key challenges such as variations in lighting conditions, facial orientation, and noise. The system is implemented on both a naive homogeneous architecture and an optimized heterogeneous CPU-GPU system to enhance real-time performance and computational efficiency. A comparative analysis is performed to evaluate processing speed, accuracy, and resource utilization across both architectures. Results demonstrate that the optimized heterogeneous system significantly outperforms the homogeneous counterpart, achieving faster processing times while maintaining high accuracy levels. This performance boost is achieved through parallel computing frameworks such as OpenMP and OpenCL, which allow for efficient resource allocation and scalability. The research highlights the potential of heterogeneous architectures for real-time healthcare applications, including remote patient monitoring and telemedicine, providing a robust solution for future developments in non-invasive health technology.

关键词： real-time healthcare embedded systems heterogeneous computing deep learning CPU-GPU architecture

来源：评论

学校读者我要写书评

暂无评论

HCMPE-Net: An unsupervised network for underwater image restoration with multi-parameter estimation based on homology constraint

引用

OPTICS AND LASER TECHNOLOGY 2025年 186卷

作者： Xiang, Dan He, Dengyu Sun, Hao Gao, Pan Zhang, Jinwen Ling, Jing Guangzhou Maritime Univ Sch Comp Sci Guangzhou 510725 Peoples R China Guangdong Polytech Normal Univ Sch Elect & Informat Guangzhou 510665 Peoples R China Guangdong Polytech Normal Univ Sch Automat Guangzhou 510665 Peoples R China Guangdong Polytech Normal Univ Guangdong Ind Training Ctr Guangzhou 510665 Peoples R China Guangdong Prov Key Lab Green Construct & Intellige Guangzhou 510725 Peoples R China Guangzhou Maritime Univ Sch Low Altitude Equipment & Intelligent Control Guangzhou 510725 Peoples R China

Underwater images suffer from severe degradation due to light absorption and scattering. Although deep learning-based methods have demonstrated impressive performance in underwater image restoration, their dependence on paired datasets limits their applicability. Therefore, an unsupervised network for underwater image restoration with multi-parameter estimation based on homology constraint is proposed to address this challenge. This method eliminates the dependency on real labels, thereby broadening its applicability across various scenarios. Meanwhile, compared with traditional unsupervised networks, this paper designed the optimized parameter estimation modules that not only improve restoration accuracy but also ensure real-time processing performance. Specifically, a contextual attention-based residual network is employed to estimate scene radiance. This module integrates global and local features to achieve accurate estimation using a contextual attention mechanism. Additionally, an adaptive cross-channel interaction network and a quadtreebased Gaussian blur module are established for precise estimation of the transmission map and background light. The adaptive cross-channel interaction network dynamically adjusts the interaction between RGB channels to enhance detail fidelity and local transmission estimation accuracy. The background light estimation module integrates quad-tree and Gaussian blur strategies to effectively mitigate background light bias in complex lighting environments. During the training phase, a color loss function based on three color spaces is defined. This function imposes joint constraints on the image in different color spaces, accurately capturing color deviations and optimizing the overall color restoration performance. Extensive experimental results demonstrate that our method achieves superior restoration accuracy and real-time performance across multiple real-world underwater image datasets, significantly outperforming existing state

关键词： deep learning Homology constraint Underwater image restoration Unsupervised network

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：