检索结果-内蒙古大学图书馆

An optimized deep learning approach to detect and classify defective tiles in production line for efficient industrial quality control

引用

NEURAL COMPUTING & APPLICATIONS 2023年第15期35卷 11089-11108页

作者： Kovilpillai, J. Judeson Antony Jayanthy, S. Sri Ramakrishna Engn Coll Dept Elect & Commun Coimbatore Tamil Nadu India

In this paper, a deep learning-based machine vision approach is proposed to automatically detect and classify defective tiles in the production assembly line of a tile manufacturing industry. The deep learning model used in this methodology is trained with 30,000 real-time images of cement/ceramic tiles, and the features of the image samples are extracted using the convolutional layers in the model. The defective tiles are identified and classified using an optimized activation function that acts as the decision-making layer or output layer of the deep learning model. The performance of this deep learning technique is evaluated using various metrics like accuracy, precision, recall and f1-score which is further compared with state-of-the-art activation functions like Relu, sigmoid, tanh and softmax. To further enhance the performance metrics, the feature extraction is done using various pre-trained models like VGG-16, Resnet50 and InceptionV3 and was further evaluated using metrics like K (Kappa statistic), OA (overall accuracy) and AA (average accuracy). The obtained experimental results with an accuracy of 99.96% under a favorable learning rate prove the robustness and efficiency of the proposed methodology to enhance industrial quality control in any tile manufacturing industry.

关键词： deep learning Machine vision image processing Industry 4.0 Industry quality control Vision computing

来源：评论

学校读者我要写书评

暂无评论

deep full-color optically-sectioned microscopy with multi-reference colorization

引用

OPTICS AND LASER TECHNOLOGY 2025年 180卷

作者： Bai, Chen Dang, Shipei Qian, Jia Tian, Xuan Li, Runze Peng, Tong Li, Xing Yang, Yanlong Dan, Dan Yao, Baoli Chinese Acad Sci State Key Lab Transient Opt & Photon Xian Inst Opt & Precis Mech Xian 710119 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Shanxi Univ Collaborat Innovat Ctr Extreme Opt Taiyuan 030006 Peoples R China

As the wide-field microscopy, structured illumination microscopy (SIM) enables optical sectioning (OS) and super-resolution imaging, having the advantages of high spatial resolution, short image recording time, and less photobleaching and phototoxicity. With white light illumination, full-color SIM technology based on the huesaturation-value (HSV) color space, namely HSV-SIM, can restore the color information of the sample surface, which is an important physical quantity describing the characteristics of living creatures and their optical properties. Nevertheless, fringes are inevitably left in the processing channel, especially in the hue (H) and saturation (S) channels, leading to color distortion as well as oversaturation and excessive redness. Besides, HSVSIM requires the OS algorithm to run three times in each channel and requires two transformations between the red-green-blue (RGB) and HSV color spaces, thereby extending the data processing time for large-scale samples. In this paper, a natural color SIM method is proposed through deep learning with multi-reference-based colorization, called deep-MRC-SIM, which can effectively reconstruct high-quality full-color OS images with improved color authenticity and richness. In addition to taking the corresponding WF image with same scanning depth as a reference, deep-MRC-SIM also introduces other WF data at two random depths as references. This makes deepMRC-SIM more robust and precise for natural color SIM with such three multi-WF references. Case studies of different specimens with a specific digital micro-mirror device (DMD)-based SIM system are used to validate this method. Regarding the color rendition, the image histogram cosine similarity and structural similarity of deepMRC-SIM were on average 7.67 and 2.10 times better than those of HSV-SIM, respectively;Meanwhile, the reconstruction time was reduced by 69.24%. This cost-effective and convenient deep-MRC-SIM method offers a promising tool to observe the 3-D

关键词： Optical microscopy Optical imaging processing Optically-sectioning Full-color microscopy deep learning

来源：评论

学校读者我要写书评

暂无评论

Pothole Detection and Dimension Estimation System using deep learning (YOLO) and image processing 35

Pothole Detection and Dimension Estimation System using Deep...

引用

35th International Conference on image and Vision Computing New Zealand (IVCNZ)

作者： Chitale, Pranjal A. Kekre, Kaustubh Y. Shenai, Hrishikesh R. Karani, Ruhina Gala, Jay P. DJSCE Mumbai Maharashtra India

ISBN: (纸本)9781728185798

The world is advancing towards an autonomous environment at a great pace and it has become a need of an hour, especially during the current pandemic situation. The pandemic has hindered the functioning of many sectors, one of them being Road development and maintenance. Creating a safe working environment for workers is a major concern of road maintenance during such difficult times. This can be achieved to some extent with the help of an autonomous system that will aim at reducing human dependency. In this paper, one of such systems, a pothole detection and dimension estimation, is proposed. The proposed system uses a deep learning based algorithm YOLO (You Only Look Once) for pothole detection. Further, an image processing based triangular similarity measure is used for pothole dimension estimation. The proposed system provides reasonably accurate results of both pothole detection and dimension estimation. The proposed system also helps in reducing the time required for road maintenance. The system uses a custom made dataset consisting of images of water-logged and dry potholes of various shapes and sizes.

关键词： YOLO deep learning Triangular Similarity image processing Pothole Detection Dimension Estimation

来源：评论

学校读者我要写书评

暂无评论

QARV: Quantization-Aware ResNet VAE for Lossy image Compression

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第1期46卷 436-450页

作者： Duan, Zhihao Lu, Ming Ma, Jack Huang, Yuning Ma, Zhan Zhu, Fengqing Purdue Univ Elmore Family Sch Elect & Comp Engn W Lafayette IN 47907 USA Nanjing Univ Sch Elect Sci & Engn Nanjing 210093 Jiangsu Peoples R China

This paper addresses the problem of lossy image compression, a fundamental problem in image processing and information theory that is involved in many real-world applications. We start by reviewing the framework of variational autoencoders (VAEs), a powerful class of generative probabilistic models that has a deep connection to lossy compression. Based on VAEs, we develop a new scheme for lossy image compression, which we name quantization-aware ResNet VAE (QARV). Our method incorporates a hierarchical VAE architecture integrated with test-time quantization and quantization-aware training, without which efficient entropy coding would not be possible. In addition, we design the neural network architecture of QARV specifically for fast decoding and propose an adaptive normalization operation for variable-rate compression. Extensive experiments are conducted, and results show that QARV achieves variable-rate compression, high-speed decoding, and better rate-distortion performance than existing baseline methods.

关键词： Lossy image compression learned image compression variational autoencoder deep learning

来源：评论

学校读者我要写书评

暂无评论

Convergence of deep learning and Edge Computing using Model Optimization 13

Convergence of Deep Learning and Edge Computing using Model ...

引用

13th Iranian/3rd International Machine Vision and image processing Conference (MVIP)

作者： Babaei, Peyman Islamic Azad Univ Comp Dept West Tehran Branch Tehran Iran

ISBN: (纸本)9798350350494;9798350350500

Edge systems are undergoing a groundbreaking computing evolution to support artificial intelligence, deep learning, and complex computational algorithms. Using cloud servers to perform deep learning model inference poses challenges such as response delays, increased communication costs, and data privacy concerns. Therefore, significant efforts have been made to push the processing of deep learning models to edge systems, which has led to the creation of edge intelligence as the intersection of learning and edge computing. learning models, especially deep convolutional neural networks, have made significant achievements in machine vision, which provide high accuracy and predictability by spending computing power and memory. If these models are optimized and deployed on edge systems, there will be a revolution in the applications of edge systems in real time. In this paper, by using optimization techniques such as quantization, weight pruning, and weight clustering, the possibility of deploying a typical convolutional neural network model on edge systems that have limited computing resources and memory is investigated. The results show that by using a collaborative algorithm, despite the slight decrease in the accuracy of the model, it is possible to achieve a small-sized model that can even be deployed on microcontrollers.

关键词： Model optimization Quantization Weight pruning Weight clustering Edge computing deep learning

来源：评论

学校读者我要写书评

暂无评论

Speed and accuracy in Tandem: deep learning-Powered Millisecond-Level pulmonary embolism detection in CTA

引用

BIOMEDICAL SIGNAL processing AND CONTROL 2025年 106卷

作者： Wu, Houde Chen, Ting Wang, Longshuang Guo, Li Tianjin Med Univ Sch Med Imaging Tianjin 300203 Peoples R China Dalian Med Univ Affiliated Hosp 1 Dalian 116011 Liaoning Peoples R China

Background and Objectives: Pulmonary embolism (PE) is a critical medical condition that requires a rapid and accurate diagnosis. Traditional methods, although highly precise, have focused primarily on accuracy, neglecting the urgency of speed required in emergency settings. This study aims to develop a deep learning model that not only maintains high accuracy but also achieves millisecond-level PE detection speed. Materials and Methods: This study employed an internal dataset comprising 160 patients from Tianjin Medical University General Hospital, and an external RSNA dataset for validation. Our model, built upon the YOLOv5 framework, was enhanced with Partial Convolution, a C2f module, and decoupled head structure. Results: The internal test set achieved a recall of 82.5 %, precision of 84.2 %, and mean average precision (mAP) of 87.2 %, significantly outperforming the other leading models. Notably, our model provided an inference time of just 1.6 ms per image, setting a new benchmark for real-time PE detection, which was faster than YOLOv5 (2.9 ms), YOLOv6 (4.0 ms), and YOLOv8 (3.2 ms). Furthermore, our model demonstrated faster convergence and consistently lower loss values during training, achieving perfect precision at a significantly lower confidence threshold than other YOLO variants, highlighting its superior optimization and generalization capabilities. Conclusion: This study successfully developed a deep learning model capable of millisecond-level PE detection without compromising the accuracy. Its performance underscores its potential to revolutionize PE diagnosis in emergency clinical settings, enabling timely and reliable intervention.

关键词： Artificial Intelligence deep learning Pulmonary Embolism Target Detection YOLO

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor flow state identification and schlieren image generation for supersonic inlet

引用

AEROSPACE SCIENCE AND TECHNOLOGY 2025年 158卷

作者： Wang, Yu-Jie Zhao, Yong-Ping Jin, Yi Hou, Kuan-Xin Nanjing Univ Aeronaut & Astronaut Coll Energy & Power Engn Nanjing 210016 Peoples R China Civil Aviat Flight Univ China Coll Aeronaut Engn Guanghan 618703 Peoples R China

The detection of flow state inside the supersonic inlet, including internal flow patterns and schlieren images, is crucial for advancing supersonic flight technology. However, obtaining precise information from inlets with varying internal contraction ratios (ICR) is challenging due to limitations in the operating environment and equipment, particularly in capturing schlieren images. In this paper, deep learning approaches are applied to flow state identification and schlieren image generation for supersonic inlet. For one thing, a time-frequency deep convolutional neural network model aggregates pressure signals from multiple sensors to predict the current flow pattern. For another, an enhanced pix2pix schlieren generation network (EPSGN) generates flow patterns on a blank inlet schlieren by incorporating recognition results and semantic labels. The experimental results demonstrate that the joint system achieves an accuracy of 99.23% in identifying the flow state of the supersonic inlet. Furthermore, the system is capable of generating schlieren images that depict various flow states under different experimental conditions, including those transient phenomena that are unobservable by high-speed cameras. The entire process requires only approximately 46 ms, underscoring its suitability for realtime applications in detecting the internal flow state of supersonic inlets. The rapid processing time facilitates immediate feedback, which is essential for real-time monitoring and control systems.

关键词： Supersonic inlet deep learning Multi-sensor flow state identification Enhanced pix2pix schlieren generation network

来源：评论

学校读者我要写书评

暂无评论

real-time hand gesture recognition using multiple deep learning architectures

引用

SIGNAL image AND VIDEO processing 2023年第8期17卷 3963-3971页

作者： Aggarwal, Apeksha Bhutani, Nikhil Kapur, Ritvik Dhand, Geetika Sheoran, Kavita Indian Inst Technol Roorkee Dept CSE Roorkee 247667 Uttar Pradesh India Maharaja Surajmal Inst Technol Delhi 110058 Delhi India

Human gesture recognition is one of the most challenging problems in computer vision, striving to analyze human gestures by machine. However, most of the literature on gesture recognition utilizes isolated data with only one gesture in one image or a video for classifying gestures. This work targets the identification of human gestures from the continuous stream of data input taken from a live camera feed, with no pre-defined boundaries. This task becomes even more complex given the diverse lighting conditions, varying backgrounds and different gesture positions in the same input stream of data. This work presents an effective deep learning architecture to classify gestures taken from multiple viewpoints and varying object sizes. To perform the classification, in this work, we have synthesized a real-world dataset consisting of 4500 images collected from different persons of varying age groups ranging from 10 to 50. The dataset is accumulated considering a wide variety of characteristics to address the complexities in the gesture recognition process. A real-time system is developed that captures, analyzes and classifies live gesture videos frame by frame. To prove the validity of our approach, we have compared our results with multiple deep learning architectures and other benchmark datasets. The results depict that our approach outperforms the existing works and is able to detect gestures with deteriorating lighting conditions and murky gesture positions, achieving an accuracy of 99.63%.

关键词： Convolution neural network Artificial neural network Gesture recognition Transfer learning

来源：评论

学校读者我要写书评

暂无评论

real-time Human Activity Recognition using Wi-Fi CSI: A deep CNN Architecture Approach 13

Real-Time Human Activity Recognition using Wi-Fi CSI: A Deep...

引用

13th International Conference on image processing Theory Tools and Applications

作者： Karim, Meridja Imene, Sekkiou Aymen, Gammoudi Univ Paris Saclay Campus Evry Evry France Caplogy Velizy Villacoublay France

ISBN: (纸本)9798331541859;9798331541842

Human activity recognition (HAR) using Wi-Fi signals has gained significant attention due to its non-invasive nature, ubiquity, and respect for privacy, in contrast to camera-based systems. This study aims to develop a robust deep learning model for real-time HAR using Channel State Information (CSI) from Wi-Fi signals. We propose a deep Convolutional Neural Network (CNN) architecture incorporating an attention mechanism to process CSI data and classify various human activities. Our model was trained and tested using a comprehensive dataset of Wi-Fi CSI, employing advanced data augmentation techniques to enhance model generalization. The proposed model achieved an impressive accuracy of 99.69%, significantly outperforming existing approaches in terms of precision, recall, and F1 score. These findings demonstrate the potential of using Wi-Fi CSI with deep CNNs and attention mechanisms for accurate and real-time HAR, paving the way for applications in smart homes, healthcare monitoring, and other domains requiring efficient and privacy-preserving activity recognition. Future work will explore adapting this methodology to a variety of datasets and integrating an emotion recognition system to further expand its capabilities.

关键词： human activity recognition (HAR) Wi-Fi sensing deep learning attention mechanism channel state information(CSI) Convolutional neural network (CNN) Data augmentation

来源：评论

学校读者我要写书评

暂无评论

A Patient-Specific Registration of Coronary Angiogram-Fluoroscopy by Similarity- Based Transfer learning

引用

IEEE ACCESS 2024年 12卷 133509-133520页

作者： Kim, Changhyeon Jeong, Daehyeon Kim, Dongkue Ryu, Jeha Cho, Kyunghoon Gwangju Inst Sci & Technol Sch Integrated Technol Gwangju 61005 South Korea VIBE Anseong 17546 Gyeonggi Do South Korea KRRI Uiwang Si 16105 Gyeonggi Do South Korea Gwangju Inst Sci & Technol Artificial Intelligence Grad Sch Gwangju 61005 South Korea Chonnam Natl Univ Hosp Dept Cardiol Gwangju 61469 South Korea

Percutaneous coronary intervention (PCI) is an effective treatment for normalizing blood flow in coronary arteries narrowed by stent implantation. Guidewire insertion during PCI requires considerable precision and expertise, and two X-ray videos, a cine loop of angiography and a real-time video of live fluoroscopy, are used to aid guidewire navigation to the target location without entering the wrong blood vessel branches. However, simultaneously watching and interpreting two radiographic videos warrants increased mental effort and intervention time. Additionally, more contrast agents may have to be injected to verify the insertion. Although deep-learning-based dynamic coronary roadmapping (DCR) has been suggested to provide registered images from two different X-ray sources, existing methods may not be suitable for irregular heartbeats or may vary in effectiveness depending on the patient, posing challenges in time-critical situations. To address these challenges, we propose a patient-specific approach for DCR using similarity-based patient data matching in transfer learning with a residual U-Net. The proposed method leverages the anatomical similarities between newly acquired and pre-acquired angiograms by utilizing principal component analysis and cosine similarity to facilitate efficient transfer learning. Moreover, a residual U-Net architecture that incorporates residual blocks and leaky ReLU activation functions to accelerate patient-specific transfer learning is proposed. These advanced techniques resulted in significantly fast transfer learning of less than five minutes from a pre-trained model, as well as high registration image quality with over 30 dB in peak signal-to-noise ratio, while maintaining a registration error of $1.04\pm 0.19$ mm.

关键词： Transfer learning Training Videos real-time systems Visualization Electrocardiography Arteries deep learning X-ray applications image registration Coronary arteriosclerosis Blood flow dynamic coronary roadmap image registration percutaneous coronary intervention X-ray angiography X-ray fluoroscopy

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：