检索结果-内蒙古大学图书馆

Multimodal Engagement Recognition From image Traits Using deep learning Techniques

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

Effective deep learning approach for segmentation of pulmonary cancer in thoracic CT image

引用

BIOMEDICAL SIGNAL processing AND CONTROL 2024年 89卷

作者： Thangavel, Chitra Palanichamy, Jaganathan Christian Coll Engn & Technol Dept Elect & Commun Engn Oddanchatram Tamil Nadu India PSNA Coll Engn & Technol PG Dept Comp Applicat Dindigul 624622 Tamil Nadu India

One of the most severe kinds of tumors in people is lung cancer. Identifying lung cancer and its types requires costly and time-consuming procedure research. Furthermore, lung nodules are difficult to identify because of their diversity and visual similarity to neighboring locations. Conventional machine learning methods either treat these components separately or rely on human integration, which can be time-consuming and could fail to fully capture the intricate relationships between these features. deep learning methods' layered structures enable them to automatically incorporate many features and learn meaningful descriptions. Thus, this framework proposes an efficient deep learning technique for classifying pulmonary nodules using Computerized Tomography (CT) images. Initially, several pre-processing methods are taken into account to prepare the data. Then, TNet based deep learning algorithm segments the lung nodule, and the CenterNet-based method extracts the texture and intensity attributes from the segmented image. Following that, the proposed NASNet-based classifier categorizes the nodules as cancerous or not, using the attributes that have been collected. Finally, the presented method will be assessed by the metrics like Dice similarity coefficient (DSC), Sensitivity, Positive predictive Value (PPV), f1-score, precision, recall, and accuracy on the LUNA-16 and Lung image Database Consortium (LIDC-IDRI) datasets, and the outcomes are contrasted with other existing approaches.

关键词： deep learning Lung cancer Lung nodule NASNet CenterNet

来源：评论

学校读者我要写书评

暂无评论

Complementary spatial transformer network for real-time 3D object recognition

引用

JOURNAL OF real-time image processing 2023年第5期20卷 88页

作者： Krishna Kumar, K. P. Paul, Varghese APJ Abdul Kalam Technol Univ CET Campus Thiruvananthapuram 695016 Kerala India Rajagiri Sch Engn & Technol Dept Comp Sci & Engn Kochi 682039 Kerala India

Tiny deep learning Models offer many advantages in various applications. From the perspective of statistical machine learning theory the contributions of this paper is to complement the research advances and results obtained so far in real-time 3D object recognition. We propose a Tiny deep learning Model named Complementary Spatial Transformer Network (CSTN) for real-time 3D object recognition. It turns out that CSTN's working, and analysis are much simplified in a target space setting. We make algorithmic enhancements to perform CSTN computations faster and keep the learning part of CSTN in minimal size. Finally, we provide the experimental verifications of the results obtained in publicly available point cloud data sets ModelNet40 and ShapeNetCore with our model performing 1.65-2 times better in DPS (Detections/s) rate on GPU hardware for 3D object recognition, when compared to state-of-the-art networks. Complementary Spatial Transformer Network architecture requires only 10-35% of trainable parameters, when compared to state-of-the-art networks, making the network easier to deploy in edge AI devices.

关键词： 3D object recognition Spatial transformer network Spatial entropy Target space real-time tiny deep learning models

来源：评论

学校读者我要写书评

暂无评论

deep learning for Sensing Matrix Prediction in Computational Microwave Imaging With Coded-Apertures

引用

IEEE ACCESS 2024年 12卷 16844-16855页

作者： Zhang, Jiaming Sharma, Rahul Garcia-Fernandez, Maria Alvarez-Narciandi, Guillermo Abbasi, Muhammad Ali Babar Yurduseven, Okan Queens Univ Belfast Ctr Wireless Innovat CWI Sch Elect Elect Engn & Comp Sci EEECS Belfast BT3 9DT North Ireland

This work aims to simplify the characterization process of coded-apertures for computational imaging (CI) at microwave frequencies. A major benefit of the presented technique is the minimization of the processing time needed to calculate the system sensing matrix for microwave CI-based compressive sensing applications. To achieve this, a deep learning-based approach which is capable of generating the sensing matrix using features learned directly from the coded-aperture distribution is proposed. To avoid the vanishing gradient problem, the proposed deep learning network contains skip connections. Using a dataset of 1,000 testing samples, the average normalized mean-squared-error (NMSE) calculated between the sensing matrix generated by the conventional method and that predicted by the proposed network is 0.0036. Moreover, the average mean-squared-error (MSE) calculated between the images reconstructed using the conventional and the predicted sensing matrix is 0.00297. In addition to providing high-fidelity estimations with minimized error, we demonstrate that using the trained network, the prediction of the sensing matrix can be achieved in 0.212 s, corresponding to a 65% reduction in the computation time needed to calculate the sensing matrix. This has significant outcomes in achieving real-time operation of CI-based microwave imaging systems.

关键词： Computational imaging deep learning image reconstruction microwave imaging sensing matrix

来源：评论

学校读者我要写书评

暂无评论

High-resolution image processing and entity recognition algorithm based on artificial intelligence

引用

JOURNAL OF INTELLIGENT SYSTEMS 2024年第1期33卷

作者： Sun, Yutong Jilin Technol Coll Elect Informat Sch Software Engn Jilin 132000 Jilin Peoples R China

Objective With the popularity of high-resolution devices such as high-definition, ultra-high-definition televisions, and smartphones, the demand for high-resolution images is also increasing, which puts forward higher requirements for high-resolution image processing and entity recognition *** This article introduced the research progress and application of high-resolution image processing and entity recognition algorithms from the perspective of artificial intelligence (AI). First, the important role of AI in high-resolution image processing and entity recognition was introduced, and then the applications of deep learning-based algorithms in high-resolution image grayscale equalization, denoising, and deblurring were introduced. Subsequently, the application of AI-based object detection and image segmentation algorithms in entity recognition was explored, and the superiority of AI-based high-resolution image processing and entity recognition algorithms was verified through training and testing. The accuracy of the model was verified through testing experiments. Finally, a summary and outlook were made on high-resolution image processing and entity recognition algorithms based on *** After experimental testing, it was found that high-resolution image processing and entity recognition based on AI had higher efficiency, and the overall image recognition ability was improved by 29.6% compared to traditional image recognition models. The recognition speed and accuracy were also *** High-resolution image processing and element recognition algorithms based on AI enabled observers to see the detailed information in the image more clearly, thus improving the efficiency and accuracy of image analysis. Through continuous improvement of algorithm performance, real-time application, and expansion of cross-disciplinary applications, people can look forward to the development of more advanced and powerful image processing and entity recognition

关键词： artificial intelligence deep learning convolutional neural network image processing entity recognition algorithms

来源：评论

学校读者我要写书评

暂无评论

A lightweight image inpainting model for removing unwanted objects from residential real estate's indoor scenes

引用

MULtimeDIA TOOLS AND APPLICATIONS 2024年第34期83卷 80389页

作者： Sompoppokasest, Srun Siriborvornratanakul, Thitirat Natl Inst Dev Adm Grad Sch Appl Stat 148 SeriThai Rd Bangkok 10240 Thailand

To enhance the appeal of residential real estate listings and captivate online customers, clean and visually convincing indoor scenes are highly desirable. In this research, we introduce an innovative image inpainting model designed to seamlessly replace undesirable elements within images of indoor residential spaces with realistic and coherent alternatives. While Generative Adversarial Networks (GANs) have demonstrated remarkable potential for removing unwanted objects, they can be resource-intensive and face difficulties in consistently producing high-quality outcomes, particularly when unwanted objects are scattered throughout the images. To empower small- and medium-sized businesses with a competitive edge, we present a novel GAN model that is resource-efficient and requires minimal training time using arbitrary mask generation and a novel half-perceptual loss function. Our GAN model achieves compelling results in removing unwanted elements from indoor scenes, demonstrating the capability to train within a single day using a single GPU, all while minimizing the need for extensive post-processing.

关键词： deep learning image inpainting image completion Generative Adversarial Network

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

Attention-based color consistency underwater image enhancement network

引用

SIGNAL image AND VIDEO processing 2024年第5期18卷 4385-4394页

作者： Chang, Baocai Li, Jinjiang Wang, Haiyang Li, Mengjun Shandong Technol & Business Univ Sch Informat & Elect Engn Yantai 264005 Peoples R China Inst Network Technol Yantai 264000 Peoples R China

Underwater images often exhibit color deviation, reduced contrast, distortion, and other issues due to light refraction, scattering, and absorption. Therefore, restoring detailed information in underwater images and obtaining high-quality results are primary objectives in underwater image enhancement tasks. Recently, deep learning-based methods have shown promising results, but handling details in low-light underwater image processing remains challenging. In this paper, we propose an attention-based color consistency underwater image enhancement network. The method consists of three components: illumination detail network, balance stretch module, and prediction learning module. The illumination detail network is responsible for generating the texture structure and detail information of the image. We introduce a novel color restoration module to better match color and content feature information, maintaining color consistency. The balance stretch module compensates using pixel mean and maximum values, adaptively adjusting color distribution. Finally, the prediction learning module facilitates context feature interaction to obtain a reliable and effective underwater enhancement model. Experiments conducted on three real underwater datasets demonstrate that our approach produces more natural enhanced images, performing well compared to state-of-the-art methods.

关键词： Underwater image enhancement deep learning Attention mechanisms Gamma correction Color histograms

来源：评论

学校读者我要写书评

暂无评论

Motion training recognition based on thermal radiation imaging system and object detection: Human motion thermal image monitoring

引用

THERMAL SCIENCE AND ENGINEERING PROGRESS 2025年 60卷

作者： Zhao, Jie Liu, Chang Hou, Huisheng Minzu Univ China Sch Phys Educ Beijing 100081 Peoples R China

A human motion monitoring method based on thermal radiation image system and target detection technology is developed. The heat distribution of human body in motion is captured by thermal image, and the real-time recognition and analysis of human motion is realized by combining image processing and target detection algorithm. A complete set of thermal radiation optical image monitoring system is designed in this study. A highsensitivity thermal imaging camera is used to capture the thermal radiation images of the human body in the process of motion, and these images are then transmitted to the data acquisition unit for preliminary data collation and storage. The image processing module preprocesses the acquired thermal images, and the preprocessed images are fed into the object detection algorithm, which is based on the deep learning framework and can recognize and classify different movements of the human body. The thermal radiation image monitoring system can accurately capture the thermal image of the human body in different motion states, and identify the movement type of the athlete in real time through the target detection algorithm. The system has a strong ability to capture the details of actions, and can identify the beginning, progress and end stages of actions. Compared with traditional monitoring methods, the thermal radiation light image monitoring system has obvious advantages in terms of data accuracy and real-time performance. This method can not only provide high precision movement recognition, but also has the advantages of non-contact and real-time monitoring, which greatly improves the efficiency and accuracy of sports training monitoring.

关键词： Thermal radiation Optical image system Target detection Recognition of sports training Human movement Thermal image monitoring

来源：评论

学校读者我要写书评

暂无评论

HARNESSING deep learning FOR DISEASED AND FRESH ORANGE DETECTION: A COMPARATIVE ANALYSIS OF YOLO V8 AND RT-DETR 13

HARNESSING DEEP LEARNING FOR DISEASED AND FRESH ORANGE DETEC...

引用

13th International Conference on image processing Theory Tools and Applications

作者： Roy, Kyamelia Osmani, Mohammad Hatif Pal, Tapan Kumar Chaudhuri, Sheli Sinha Djemal, Khalifa Feiz, Amir Ali Siliguri Govt Polytech Dept ETCE Siliguri India Jadavpur Univ Dept ETCE Kolkata India Kanyapur Polytech Dept CST Asansol W Bengal India Univ Paris Saclay Univ Evry Val dEssonne Gif Sur Yvette France

ISBN: (纸本)9798331541859;9798331541842

Automation in horticulture with computer vision and deep learning revolutionizes the industry by enabling precise and efficient harvesting and disease detection. This technology enhances productivity and quality control, benefiting farmers and food manufacturers alike. The present work offers a comparative analysis of advanced deep learning detection models-YOLO V8, RT-DETR with ResNet and with EfficientNet backbones-focused on identifying diseased (canker) and healthy (fresh) oranges. A comprehensive evaluation of these three models was conducted to assess their performance. YOLO V8 emerged with superior results, showcasing its robustness and effectiveness for real-time detection. Amongst the 3models YOLO V8 attained the best accuracy value of 99.6%. The other performance metrics underscore the model's high accuracy and efficiency in identifying and classifying objects with minimal errors, affirming its suitability for real-time horticultural diagnostics. The comparative analysis highlights YOLO V8's superiority over RT-DETR models with ResNet and EfficientNet backbones, positioning it as a highly reliable choice for detecting healthy and diseased oranges. This work advances the field by proving the superior performance of YOLO V8 for this specific application and validating the performance with the other sophisticated deep learning architectures.

关键词： YOLO V8 RT-DETR (real time Detection Transformer) ResNet EfficientNet mAP (Mean Average Precision) Detection

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：