检索结果-内蒙古大学图书馆

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Ling, Jun Xue, Han Song, Li Xie, Rong Gu, Xiao Shanghai Jiao Tong Univ Inst Image Commun & Network Engn Shanghai Peoples R China Shanghai Jiao Tong Univ AI Inst MOE Key Lab Artificial Intelligence Shanghai Peoples R China

ISBN: (纸本)9781665445092

image composition plays a common but important role in photo editing. To acquire photo-realistic composite images, one must adjust the appearance and visual style of the foreground to be compatible with the background. Existing deep learning methods for harmonizing composite images directly learn an image mapping network from the composite to real one, without explicit exploration on visual style consistency between the background and the foreground images. To ensure the visual style consistency between the foreground and the background, in this paper, we treat image harmonization as a style transfer problem. In particular, we propose a simple yet effective Region-aware Adaptive Instance Normalization (RAIN) module, which explicitly formulates the visual style from the background and adaptively applies them to the foreground. With our settings, our RAIN module can be used as a drop-in module for existing image harmonization networks and is able to bring significant improvements. Extensive experiments on the existing image harmonization benchmark datasets shows the superior capability of the proposed method. Code is available at https://***/junleen/RainNet.

关键词： deep learning Visualization Computer vision Adaptation models Rain Codes Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Intraoperative Adverse Event Detection in Laparoscopic Surgery: Stabilized Multi-Stage Temporal Convolutional Network with Focal-Uncertainty Loss 6

Intraoperative Adverse Event Detection in Laparoscopic Surge...

引用

Machine learning for Healthcare Conference

作者： Wei, Haiqi Rudzicz, Frank Fleet, David Grantcharov, Teodor Taati, Babak Univ Toronto Surg Safety Technol Int Ctr Surg Safety Toronto ON Canada Univ Toronto Vector Inst Toronto ON Canada Univ Hlth Network Toronto ON Canada Univ Toronto Toronto Rehabil Inst Toronto ON Canada

Intraoperative adverse events (iAEs) increase rates of postoperative mortality and morbidity. Identifying iAEs is important to quality assurance and postoperative care, but requires expertise, is time consuming, and expensive. Automated or partially-automated techniques are, therefore, desirable. Previous work showed that conventional image processing has not worked well with real-world laparoscopic videos. We present a novel modular deep learning system that can partially automate the process of iAE screening using videos of laparoscopic procedures. The system consists of a stabilizer to reduce camera motion, a spatiotemporal feature extractor, and a multi-stage temporal convolutional neural network to detect adverse events. We apply a novel focal-uncertainty smoothing loss to handle class imbalance and to address multi-task uncertainty. The system is evaluated using 5-fold cross-validation on a large (228 hours) dataset of laparoscopic videos, and we perform ablation studies to investigate the effects of stabilization and focal-uncertainty loss. Our system achieves an AUROC of 0.952, an average precision (AP) of 0.626 in thermal injury detection, and an AUROC of 0.823 and an AP of 0.336 in bleeding detection. Our novel modular deep learning system outperforms conventional deep learning baselines. The model can be used as a screening tool to search for high risk events and to provide feedback for operation quality improvements and postoperative care. Source code available on GitHub: https://***/ICSSresearch/IAE-video.

关键词： learning systems

来源：评论

学校读者我要写书评

暂无评论

Rosette Plant Centre Detection and Tracking Using YOLO: An Efficient deep learning Approach

Rosette Plant Centre Detection and Tracking Using YOLO: An E...

引用

Computing and Machine Intelligence (ICMI), International Conference on

作者： Amila Akagić Rijad Sarić Emir Buza Stefani Kecman Mathew G. Lewsey Edhem Čustović James Whelan Faculty of Electrical Engineering University of Sarajevo (UNSA) Sarajevo Bosnia and Herzegovina Dept. of Animal Plant and Soil Sciences La Trobe Institute for Sustainable Agriculture & Food (LISAF) Melbourne VIC Australia Australian Research Council Research Hub for Medicinal Agriculture La Trobe University Melbourne VIC Australia Scientific Instruments Australia (SIA) Melbourne VIC Australia State Key Laboratory of Plant Environmental Resilience College of Life Sciences Zhejiang University Hangzhou China Provincial International Science and Technology Cooperation Base on Engineering Biology Zhejiang University Haining China

ISBN: (数字)9798350372977

ISBN: (纸本)9798350372984

The precise detection of plant centres is important for growth monitoring, enabling the continuous tracking of plant development to discern the influence of diverse factors. It holds significance for automated systems like robotic harvesting, facilitating machines in locating and engaging with plants. In this paper, we explore the YOLOv4 (You Only Look Once) real-time neural network detector for plant centre detection. Our dataset, comprising over 12,000 images from 151 Arabidopsis thaliana accessions, is used to fine-tune the model. Evaluation of the dataset reveals the model's proficiency in centre detection across various accessions, boasting an mAP of 99.79% at a 50 % IoU threshold. The model demonstrates real-time processing capabilities, achieving a frame rate of approximately 50 FPS. This outcome underscores its rapid and efficient analysis of video or image data, showcasing practical utility in time-sensitive applications.

关键词： YOLO Measurement Visualization Neural networks Streaming media real-time systems Robots

来源：评论

学校读者我要写书评

暂无评论

Metric learning for dynamic text classification 2

Metric learning for dynamic text classification

引用

2nd Workshop on deep learning Approaches for Low-Resource Natural Language processing, deepLo@EMNLP-IJCNLP 2019

作者： Wohlwend, Jeremy Elenberg, Ethan R. Altschul, Samuel Henry, Shawn Lei, Tao ASAPP Inc

ISBN: (纸本)9781950737789

Traditional text classifiers are limited to predicting over a fixed set of labels. However, in many real-world applications the label set is frequently changing. For example, in intent classification, new intents may be added over time while others are removed. We propose to address the problem of dynamic text classification by replacing the traditional, fixed-size output layer with a learned, semantically meaningful metric space. Here the distances between textual inputs are optimized to perform nearest-neighbor classification across overlapping label sets. Changing the label set does not involve removing parameters, but rather simply adding or removing support points in the metric space. Then the learned metric can be fine-tuned with only a few additional training examples. We demonstrate that this simple strategy is robust to changes in the label space. Furthermore, our results show that learning a non-Euclidean metric can improve performance in the low data regime, suggesting that further work on metric spaces may benefit low-resource research. © 2019 Association for Computational Linguistics

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

deep learning Based Face Mask Detection System for COVID-19 Control 6

Deep Learning Based Face Mask Detection System for COVID-19 ...

引用

6th International Conference on image Information processing, ICIIP 2021

作者： Sarma, Madhusmita Talukdar, Anjan Kumar Sarma, Kandarpa Kumar Gauhati University Depertment of Electronics and Communication Engineering Guwahati India

ISBN: (纸本)9781665433617

COVID-19 pandemic is spreading continuously causing serious health problems. Wearing face mask is one of the prominent precautions people can easily follow. In this paper, we have built a model for face-mask detection system using deep learning technique that uses Histogram of Oriented Gradients (HOG) based features for face detection and Convolutional Neural Network (CNN) for detecting whether the person is wearing face mask or not. The model has also the capability of detecting whether the wearer is wearing the face mask properly or not. This model has been trained with 3650 images using python script in Google Colab environment applying Keras and TensorFlow. After a number of trials we have found that our model gives best result with 50 epochs. We have found training and validation accuracy 94.59% and 98.51% respectively. The model has been tested with real time inputs. From the experimental results it has been found that the proposed model is capable of detection faces with-mask and without-mask with 97% accuracy. © 2021 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Employing texture features of chest x-ray images and machine learning in covid-19 detection and classification

Mendel

引用

Mendel 2021年第1期27卷 9-17页

作者： Alquran, Hiam Alsleti, Mohammad Alsharif, Roaa Qasmieh, Isam Abu Alqudah, Ali Mohammad Harun, Nor Hazlyna Binti Department of Biomedical Systems and Informatics Engineering Yarmouk University Irbid21163 Jordan The Institute of Biomedical Technology King Hussein Medical Center Royal Jordanian Medical Service Amman11855 Jordan College of applied medical Sciences Radiological Science Program King Saud University Jeddah21435 Saudi Arabia Data Science Research Lab School of Computing Universiti Utara Malaysia Sintok Kedah06010 Malaysia

The novel coronavirus (nCoV-19) was first detected in December 2019. It had spread worldwide and was declared coronavirus disease (COVID-19) pandemic by March 2020. Patients presented with a wide range of symptoms affecting multiple organ systems predominantly the lungs. Severe cases required intensive care unit (ICU) admissions while there were asymptomatic cases as well. Although early detection of the COVID-19 virus by real-time reverse transcription-polymerase chain reaction (RT-PCR) is effective, it is not efficient;as there can be false negatives, it is time consuming and expensive. To increase the accuracy of in-vivo detection, radiological image-based methods like a simple chest X-ray (CXR) can be utilized. This reduces the false negatives as compared to solely using the RT-PCR technique. This paper employs various image processing techniques besides extracted texture features from the radiological images and feeds them to different artificial intelligence (AI) scenarios to distinguish between normal, pneumonia, and COVID-19 cases. The best scenario is then adopted to build an automated system that can segment the chest region from the acquired image, enhance the segmented region then extract the texture features, and finally, classify it into one of the three classes. The best overall accuracy achieved is 93.1% by exploiting Ensemble classifier. Utilizing radiological data to conform to a machine learning format reduces the detection time and increase the chances of survival. © 2021, Brno University of Technology. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

image Analytics to Detect Cigarette in an image Using deep learning

Image Analytics to Detect Cigarette in an Image Using Deep L...

引用

International Conference on Signal and Data processing, ICSDP 2019

作者： Kharade, Abhijeet Abhishek, Kumar Dwibedi, Debaraj Mehta, Siddharth Meruga, Hemanth Gangula, Pratap Narayana, D. Borse, Rushikesh Great Lakes Institute of Management Manamai Tamil Nadu India E&TC Engineering MIT Academy of Engineering Pune Alandi India

ISBN: (纸本)9789811583902

Significant number of modern films depict some form of tobacco use, but rarely depict its real-life consequences such as addiction, illness and death. As per [1], anti-tobacco health warnings are mandatory for scenes depicting smoking scenes. In this paper, an automated recognition system is proposed to identify images with smoking activities and tag them accordingly. The proposed approach implements the technique of object detection based on deep learning. Convolutional neural network is used to generate feature maps from the images. These machine-learnt features are used to classify the images. The system can detect the smoking events of uncertain actions with various cigarette sizes, colors and shapes. We have experimented our work by applying the proposed approach to two real-world datasets and that have demonstrated the effectiveness of our solution with a decent model accuracy. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Tobacco

来源：评论

学校读者我要写书评

暂无评论

Partial discharge based recognition of water droplets location in high voltage insulator using convolutional neural network - Bacterial foraging algorithm based optimized machine learning classifier

引用

MEASUREMENT 2023年第1期221卷

作者： Kalaivani, L. Maheswari, R. V. Vigneshwaran, B. Karthick, Alagar Kathirvelu, Murugan Marquez, Fausto Pedro Garcia Natl Engn Coll Dept Elect & Elect Engn Kovilpatti 628503 Tamil Nadu India KPR Inst Engn & Technol Dept Elect & Elect Engn Renewable Energy Lab Coimbatore 641407 Tamil Nadu India KPR Inst Engn & Technol Dept Elect & Commun Engn Coimbatore 641407 Tamil Nadu India Univ Castilla La Mancha Ingneium Res Grp Ciudad Real 13071 Spain Univ Cordoba Dept Quim Organ Cordoba Spain

Measurement and analysis of Partial Discharge (PD) patterns have appeared as an emerging field in assessing insulation failure in High Voltage apparatus. This paper uses a PD signal combined with the deep convolution -optimized learning machine classifier (DC-OLMC) to predict the location of water droplets in 11 kV polymer insulators subjected to alternating currents. There are two major confront when applying the proposed algorithm: i) Contamination is a significant issue in PD signal measurement, which causes a reduction in recognition rate (RR), and ii) with minimal computing time, high-level feature extraction and recognition. Traditional condition monitoring methods of insulators concentrated on extracting fewer priority features from the input patterns. In the current work, to address this problem, an Alexnet with Bacterial Foraging Algorithm (BFO) based optimized kernel parameter classifier and Translation Invariant Wavelet Transform (TIWT) is employed to remove interference from PD signals. The analysis demonstrates that the suggested technique, with an identification rate of 99.17%, is considered a valuable tool for locating water droplets in high-voltage insulators.

关键词： High voltage insulators image processing techniques deep neural network Bacterial Foraging Optimization Kernel function

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Disease in Rice Paddy: A deep learning based Convolution Neural Networks Approach 12

Early Detection of Disease in Rice Paddy: A Deep Learning ba...

引用

12th International Conference on Computing Communication and Networking Technologies, ICCCNT 2021

作者： Chakraborty, Anghsuman Layek, Soumik Sankar, Ravi Saha, Sangit Ghosh, Alokesh Ray, Hena Centre for Development of Advanced Computing Kolkata India

ISBN: (纸本)9781728185958

The agriculture industry faces huge economic losses due to bacterial, viral or fungal infections in the crops due to which farmers lose 15 to 20% of their total profit every year. India is the second largest producer of rice and a leading exporter of the same in the global market. Thus, early detection of diseases in essential crops is a significant area of research in order to prevent further damage to them. The widespread development of deep learning makes it possible to achieve the goal of disease detection in crops. The novelty of this work is early detection of Brown spot disease in rice paddy using Convolution Neural Networks. The area of the disease affected was also found to optimize the usage of fertilizers. This work makes use of image recognition and pre-processing algorithm based on real time data. Data pre-processing and feature extraction has been done using a self-designed image-processing tool. Tensor flow and Keras framework has been implemented on both training and testing data which was collected manually from rice fields. The proposed model achieved an accuracy of 97.32%. © 2021 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Integrated image processing Device For Visually Impaired

Integrated Image Processing Device For Visually Impaired

引用

International Conference on Communication, Computing and Internet of Things (IC3IoT)

作者： J. Raja N Kaviya B V Koushika R Sushma Department of Electronics and Communication Engineering Sri Sairam Engineering College Chennai Tamil Nadu

ISBN: (数字)9798350352689

ISBN: (纸本)9798350352696

In a world where technology is developing more quickly than ever before, many of these advances have been aimed at making people's lives easier. To aid with these efforts, we are creating an integrated picture processor for visually impaired people. The main forms of human communication nowadays are speech and text. A person must have the vision to view text-based information. Nonetheless, persons without the ability to see can still learn things by listening. The integrated image processor is an assistive text-reading tool that uses a camera to help the blind read text on labels, printed notes, and merchandise. It entails text extraction from an image using optical character recognition (OCR) and text-to-speech (TTS) conversion to turn it into speech. This method aids the blind in reading the text and serves as the foundation for the creation of a prototype that will enable the blind to identify objects in the real world. Using Jetson Nano, the text from product descriptions is retrieved and rendered as speech, with mobility as the primary consideration. It entails text extraction from an image using optical character recognition (OCR) and text-to-speech (TTS) conversion to turn it into speech. This method aids the blind in reading the text and serves as the foundation for the creation of a prototype that will enable the blind to identify objects in the real world. Using Raspberry Pi, the text from product descriptions is retrieved and rendered as speech, with mobility as the primary consideration. By including a battery backup, portability is made possible and could be used in future technology. The user can use the device at any time and any place because of its portability. The project also has a feature that uses OpenCV and TensorFlow to recognize cash notes. Additionally, this system incorporates deep learning-based object identification, which uses MobileNets and SSD methods for object detection, to recognize various items for recognizing barriers in front of

关键词： image processing IEEE merchandise Optical character recognition Prototypes Speech recognition Object detection Cameras

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：