检索结果-内蒙古大学图书馆

Combine deep learning and artificial intelligence to optimize the application path of digital image processing technology 24

Combine deep learning and artificial intelligence to optimiz...

引用

2024 Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence, DEAI 2024

作者： Pan, Linying Xu, Jingyu Sun, Wenjian Wan, Weixiang Zeng, Qiang Information Studies Trine university PhoenixAZ85258 United States Computer Information Technology Northern Arizona University FlagstaffAZ86011 United States Electronic and information engineering Yantai University Shandong Province Yantai264005 China Electronics & Communication Engineering University of Electronic Science and Technology of China ChengDu611731 China Computer Technology Zhejiang University Zhejiang Hangzhou310058 China

ISBN: (纸本)9798400717147

Artificial intelligence provides a new research concept for digital image processing. However, at present, artificial intelligence is rarely introduced into the teaching of digital image processing in colleges and universities, and there are problems such as obsolete teaching content, single teaching method and simple course experiment, which affect the teaching effect and are not conducive to the cultivation of comprehensive and innovative talents. Digital image processing technology brings more possibilities to communication engineering and makes people's communication more convenient. For example, video calls and photo transmission make people's communication methods in daily life more and more diversified. The limitation of time and space allows people to meet online, creating more communication possibilities. However, there are still many problems and methods worthy of in-depth exploration. Therefore, this paper has a comprehensive understanding and mastery of the traditional methods and deep learning methods of digital image processing, so as to improve the relevant project practice and scientific research exploration ability, and make reference for similar research conclusions. © 2024 ACM.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

deep learning Computer Vision Algorithms for real-time UAVs On-board Camera image processing

arXiv

引用

arXiv 2022年

作者： Palmas, Alessandro Andronico, Pietro Nurjana Technologies srl Italy

This paper describes how advanced deep learning based computer vision algorithms are applied to enable real-time on-board sensor processing for small UAVs. Four use cases are considered: target detection, classification and localization, road segmentation for autonomous navigation in GNSS-denied zones, human body segmentation, and human action recognition. All algorithms have been developed using state-of-the-art image processing methods based on deep neural networks. Acquisition campaigns have been carried out to collect custom datasets reflecting typical operational scenarios, where the peculiar point of view of a multi-rotor UAV is replicated. Algorithms architectures and trained models performances are reported, showing high levels of both accuracy and inference speed. Output examples and on-field videos are presented, demonstrating models operation when deployed on a GPU-powered commercial embedded device (NVIDIA Jetson Xavier) mounted on board of a custom quad-rotor, paving the way to enabling high level autonomy. Copyright © 2022, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Efficient tomato harvesting robot based on image processing and deep learning

引用

PRECISION AGRICULTURE 2023年第1期24卷 254-287页

作者： Miao, Zhonghua Yu, Xiaoyou Li, Nan Zhang, Zhe He, Chuangxin Li, Zhao Deng, Chunyu Sun, Teng Shanghai Univ Sch Mechatron Engn & Automat Dept Automat Intelligent Equipment & Robot Lab Shangda St 99 Shanghai Peoples R China

Agricultural robots are rapidly becoming more advanced with the development of relevant technologies and in great demand to guarantee food supply. As such, they are slated to play an important role in precision agriculture. For tomato production, harvesting employs over 40% of the total workforce. Therefore, it is meaningful to develop a robot harvester to assist workers. The objective of this work is to understand the factors restricting the recognition accuracy using image processing and deep learning methods, and improve the performance of crop detection in agricultural complex environment. With the accurate recognition of the growing status and location of crops, temporal management of the crop and selective harvesting can be available, and issues caused by the growing shortage of agricultural labour can be alleviated. In this respect, this work integrates the classic image processing methods with the YOLOv5 (You only look once version 5) network to increase the accuracy and robustness of tomato and stem perception. As a consequence, an algorithm to estimate the degree of maturity of truss tomatoes (clusters of individual tomatoes) and an integrated method to locate stems based on the resultant experiments error of each individual method were proposed. Both indoor and real-filed tests were carried out using a robot harvester. The results proved the high accuracy of the proposed algorithms under varied illumination conditions, with an average deviation of 2 mm from the ground-truth. The robot can be guided to harvest truss tomatoes efficiently, with an average operating time of 9 s/cluster.

关键词： image processing YOLOv5 network Agriculture robot Tomato harvesting

来源：评论

学校读者我要写书评

暂无评论

Automatic Chart Decoding System Based on deep learning and image processing 4

Automatic Chart Decoding System Based on Deep Learning and I...

引用

4th International Symposium on Artificial Intelligence and Intelligent Manufacturing, AIIM 2024

作者： Liang, Chaofan Xue, Fenghao Li, Zhangwei College of Software Engineering Chengdu University of Information Technology Chengdu610000 China

ISBN: (纸本)9798331541729

Statistical Charts contain a wealth of information. As an important way to visualize data presentation, statistical charts allow viewers to obtain a complete and intuitive understanding of the content shown in a very short time. At present, the research on automatic extraction and understanding of a large amount of text information has been relatively mature. However, even the latest big artificial intelligence models cannot accurately extract statistical graphs, which are personalized and contain a large amount of information. We propose an automatic bar chart data extraction process by combining deep learning and image processing technology, and construct an intelligent bar chart decoding system. The system is divided into three parts: the classification of statistical chart types, the text detection in the image, the classification of text roles and the image extraction. The original data used to create the chart in the pan-bar graph image is extracted for downstream applications. We evaluate and compare our system on public datasets. The results show that our system has better accuracy. © 2024 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Detection of Employee Fatigue Based on image processing Using deep learning Model 4

Detection of Employee Fatigue Based on Image Processing Usin...

引用

4th International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024

作者： Ethan, Michael Kusuma, I. Gede Putra Bina Nusantara University Computer Science Department Binus Graduate Program Jakarta11480 Indonesia

ISBN: (纸本)9798331506490

Fatigue in workplace is a common thing shared by all employees. Continuous exposure of fatigue could lead to negative productivity for companies. Current research on fatigue detection mostly focused to detect fatigues from a single 2D image data, meanwhile research on fatigue detection using each frames from video data is needed for better detection for fatigue process. The main advantage of using each timesteps of frames from video data which makes the model is able to predict long term dependency of fatigue person. To solve this problem, a deep learning model is proposed that could detect employee fatigue based on image processing using video data. Three models are used to train data using Convolutional Neural Network (CNN), which are time Distributed CNN LSTM, 3D CNN, and 3D CNN LSTM. Out of those three models, the best model to detect fatigue person from video data is time Distributed CNN Model with F-1 Score value of 0.77 and Accuracy Score of 0.76 for testing data. The model that gives best inference time is also time Distributed CNN Model with the average value of 382 miliseconds to detect fatigues from 58 testing data with each of the data has duration of 3 seconds and 12 frames. © 2024 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Temporal signals to images: Monitoring the condition of industrial assets with deep learning image processing algorithms

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART O-JOURNAL OF RISK AND RELIABILITY 2022年第4期236卷 617-627页

作者： Garcia, Gabriel Rodriguez Michau, Gabriel Ducoffe, Melanie Gupta, Jayant Sen Fink, Olga Swiss Fed Inst Technol Swiss Fed Inst Technol Zurich Switzerland Airbus AI Res Toulouse Midi Pyrenees France

The ability to detect anomalies in time series is considered highly valuable in numerous application domains. The sequential nature of time series objects is responsible for an additional feature complexity, ultimately requiring specialized approaches in order to solve the task. Essential characteristics of time series, situated outside the time domain, are often difficult to capture with state-of-the-art anomaly detection methods when no transformations have been applied to the time series. Inspired by the success of deep learning methods in computer vision, several studies have proposed transforming time series into image-like representations, used as inputs for deep learning models, and have led to very promising results in classification tasks. In this paper, we first review the signal to image encoding approaches found in the literature. Second, we propose modifications to some of their original formulations to make them more robust to the variability in large datasets. Third, we compare them on the basis of a common unsupervised task to demonstrate how the choice of the encoding can impact the results when used in the same deep learning architecture. We thus provide a comparison between six encoding algorithms with and without the proposed modifications. The selected encoding methods are Gramian Angular Field, Markov Transition Field, recurrence plot, grey scale encoding, spectrogram, and scalogram. We also compare the results achieved with the raw signal used as input for another deep learning model. We demonstrate that some encodings have a competitive advantage and might be worth considering within a deep learning framework. The comparison is performed on a dataset collected and released by Airbus SAS, containing highly complex vibration measurements from real helicopter flight tests. The different encodings provide competitive results for anomaly detection.

关键词： Unsupervised fault detection time series encoding helicopters vibrations CNN

来源：评论

学校读者我要写书评

暂无评论

A Novel Human Face Expression Recognition Based on image processing Assisted Convoluted deep learning Methodology

A Novel Human Face Expression Recognition Based on Image Pro...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Tamilselvi, M. Venkata Siva Prasad, Ch. Kumari, M. Varuna Lavanya, R. Sai Nandurkar, Y. Al-Mousa, Mohammad Rasmi Dept of Ece Chennai India Jeppiaar Engineering College Department of Ece Rajiv Gandhi salai Chennai119 India Qis College of Engineering and Technology Department of S&h Pondur Road Vengamukkapalem Ongole Prakasam Andhra Pradesh Prakasam District523272 India Qis College of Engineering and Technology Department of Mca Pondur Road Vengamukkapalem Ongole Prakasam Andhra Pradesh Prakasam District523272 India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India College of Information Technology Zarqa University Department of Cyber Security zarqa Jordan University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

Facial expression recognition has become a critical component in applications involving human-computer interaction, security systems, and behavioral analysis. This paper presents a novel approach to human face expression recognition using a convoluted deep learning methodology supported by image processing techniques. The system is designed to accurately classify seven fundamental emotions - Anger, Disgust, Fear, Happy, Sadness, Surprise, and Neutral - using the FER2013 dataset. The methodology includes preprocessing steps such as noise reduction, grayscale conversion, and face registration. Feature extraction is performed using Gabor filters and Local Binary Patterns (LBP), while Convolutional Neural Networks (CNNs) are employed to learn deep hierarchical features. The system was optimized through hyperparameter tuning, achieving an overall accuracy of 96.29% on the test set. Precision, recall, and F1-scores for each emotion also exceeded 95%, with 'Happy' and 'Surprise' emotions showing the best performance. The results indicate that the model is effective for real-time applications requiring reliable emotion detection. The paper concludes with discussions on model performance, challenges in classifying similar emotions, and recommendations for future improvements. © 2024 IEEE.

关键词： Gabor filters

来源：评论

学校读者我要写书评

暂无评论

Cotton Plant Disease Detection and Prevention Using deep learning and image processing 11

Cotton Plant Disease Detection and Prevention Using Deep Lea...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Kesani, Ruthvija Sunkavalli, Jaya Prakash Shaik, Mahamamad Rafi Yadala, Kusuma Velagapudi Ramakrishna Siddhartha Engineering College Dept. of Information Technology Vijayawada India

ISBN: (纸本)9798350350357

One of the most important aspects of the agricultural economy is the production of cotton, which is threatened by diseases that lower crop quality and yield. Conventional techniques for diagnosing diseases are frequently subjective and labor-intensive. This paper presents a novel method for the automatic detection and prevention of cotton plant diseases that makes use of deep learning techniques. A convolutional neural network (CNN) model is trained using a dataset that includes various photos of both healthy and sick cotton plants. The suggested model offers a dependable and time-efficient solution by exhibiting high accuracy in differentiating between different diseases. Moreover, proactive disease detection is made possible by the integration of real-time monitoring systems, such as drones fitted with high-resolution cameras. Early detection lessens the need for broadspectrum antibiotics by enabling the prompt application of preventive measures, such as targeted therapies. Finally, we conduct a comprehensive computational analysis of eight cutting-edge object detection algorithms on the cotton plant dataset to identify diseases on the leaves and seven cutting-edge classification algorithms on the cotton plant datasets to determine if a leaf has a disease or not. computed results indicate that it has a high degree of object detection accuracy. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Integrating image processing Techniques with deep learning Network Models to Detect and Identify Defects on the Surface of Tomato

Integrating Image Processing Techniques with Deep Learning N...

引用

2023 IEEE International Conference on Electrical, Computer and Energy Technologies, ICECET 2023

作者： Do Van, Dinh Sao Do University Hai Duong03500 Viet Nam

ISBN: (纸本)9798350327816

Before export, fruit should be classified to improve quality, meet customer requirements and increase product value. This article proposes a method to identify defects on the surface of tomato skin using image processing techniques combined with deep learning models. The identification method includes the following main steps: (i) data collection (image of tomato: green, ripe, diseased, scratched), (ii) image labeling, (iii) data file division, (iv) model training, (v) selection and using models. The results of using Faster R-CNN model combining Resnet-10l and testing on YOLOv5 to identify and classify tomatoes that met and failed export for high accuracy (95.3 %) and met get real time. © 2023 IEEE.

关键词： deep convolutional neural network deep learning Faster R-CNN tomato export classification YOLO YOLOv5

来源：评论

学校读者我要写书评

暂无评论

deep learning in image processing and Pattern Recognition

引用

ELECTRONICS 2025年第10期14卷 1942-1942页

作者： Wang, Aili Wu, Haibin Iwahori, Yuji Harbin Univ Sci & Technol Heilongjiang Prov Key Lab Laser Spect Technol & Ap Harbin 150080 Peoples R China Chubu Univ Dept Comp Sci 1200 Matsumoto Cho Kasugai 4878501 Japan

The current field shows a trend of multi-dimensional fusion [1], the use of lightweight convolutional self-encoder and generative adversarial network in denoising, super-resolution tasks beyond the traditional methods, and multimodal fusion technology through the integration of visible/infrared/depth map data to enhance feature extraction. In future, it is necessary to build a quantum entanglement parallel denoising system, develop neural radiation field three-dimensional dynamic reconstruction technology, and integrate optoelectronic hardware design to guarantee data security [2].A self-supervised and comparative learning framework significantly reduces the dependence on labeled data [3], and the attention mechanism is combined with reinforcement learning to optimize dynamic sampling. In future, it is necessary to build a self-supervised contrast collaboration framework, develop Transformer–dynamic convolution hybrid architecture [4], and strengthen cross-scale modeling and *** Transformer dominates image classification and segmentation through the self-attention mechanism, and dynamic sparse attention improves real-time analysis capabilities [5]. In future, we need to design a multimodal synergy framework, develop a physical embedding model to integrate a priori knowledge such as light field equations, and combine it with dynamic pruning to balance performance [6].In the field of intelligent transportation, multi-sensor fusion is used to build high-precision 3D environment models [7], event cameras help to break through the traditional frame rate limitations, and federated learning is employed to optimize global traffic prediction. In future, we need to develop an impulse neural network to drive heterogeneous data alignment, construct a meta-learning cross-domain adaptive framework, and establish a privacy security sharing mechanism [8].End-to-end models are employed to realize the accurate classification of agricultural pests and diseases, whe

关键词：

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：