检索结果-内蒙古大学图书馆

Dynamic method to optimize memory space requirement in real-time video surveillance using convolution neural network

引用

IMAGING SCIENCE JOURNAL 2024年第5期72卷 576-590页

作者： Biswas, Tamal Bhattacharya, Diptendu Mandal, Gouranga Natl Inst Technol Agartala Dept Comp Sci & Engn Agartala Tripura India VIT AP Univ Sch Comp Sci & Engn Amaravati India

Real-time video surveillance is one of the most effective ways to observe crime, mischief, and violence. But, most of the recent surveillance system consumes huge memory space to store the video. This article proposed an advanced dynamic video surveillance strategy to utilize minimum memory space with the finest detection of suspicious moving objects. In the proposed system, a convolution neural network (CNN) classifier and frame resolution switching is used to detect the movement of objects with appropriate frame resolution. A high-definition (HD) frame can be recorded dynamically when any movement of a suspicious object is detected. The system records low-quality frames, which are less important. Finally, the improved gradient-based histogram equalization technique is applied to all frames to obtain enhanced suspicious frames. Several real-time imperial tests are conducted and it is observed that the proposed system detects suspicious objects with 98.25% accuracy. Besides, the system consumes 80% less memory storage.

关键词： Video surveillance minimum memory space convolution neural network image enhancement dynamic patching suspicious object resolution switching histogram equalization

来源：评论

学校读者我要写书评

暂无评论

Detection of a casting defect tracked by deep convolution neural network

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2018年第1-4期97卷 573-581页

作者： Lin, Jinhua Yao, Yu Ma, Lin Wang, Yanjie Changchun Univ Technol Mechatron Engn Changchun 130000 Jilin Peoples R China FAW Foundry Co Ltd Changchun 130000 Jilin Peoples R China Chinese Acad Sci Univ Mechatron Engn Changchun 130033 Jilin Peoples R China

In order to relieve the problem of a false and missed detection of casting defects in X-ray detection, a robust detection method based on vision attention mechanism and deep learning of feature map is proposed. The ray images are used as input sequence, the false detection is eliminated by the intra-frame attention strategy, and the missed detection is excluded by the inter-frame deep convolution neural network (DCNN) strategy. In the intra-frame detection stage, the center-peripheral difference method is proposed to simulate the difference operation of biological vision;the suspicious defect area is directly detected according to the gradient threshold in this stage. In the inter-frame learning stage, the convolution neural network is established based on deep learning strategy to extract defect feature from a suspicious defect area;a deep learning feature vector is obtained in this stage. The similarity degree of the suspicious defect area is computed by a feature vector;a casting defect is tracked by the similarity matching of the suspicious defect in continuous frames;then, the false defects (such as noise) is excluded after defect tracking. The experimental results show that the false rate and missed rate for detection of casting defects are less than 4%, and the accuracy of the defect detection is more than 96%, which proves the robustness of the proposed method.

关键词： Casting defect Deep learning Ray image convolution neural network

来源：评论

学校读者我要写书评

暂无评论

Salient Target Detection Method of Video Images Based on convolution neural network

引用

TRAITEMENT DU SIGNAL 2022年第6期39卷 2157-2163页

作者： Yao, Zhuo Guo, Li Beihua Univ Sch Math & Stat Jilin 132013 Jilin Peoples R China

Traditional target detection of video images is often used to distinguish the relevant classification of large categories of targets, in the case of complex and diverse image content, it cannot capture enough visual cues, which makes it difficult to distinguish small differences between categories. Therefore, this article studies the salient target detection method of video images based on convolution neural network. Based on dictionary learning, the dynamic features of videos are extracted, and then the coefficient matrix is generated based on the dictionary to complete the learning, so as to realize the complete description of the underlying dynamics of videos. DMD algorithm is used to extract the dynamic mode of videos, and finally the foreground and background of video image frames are separated. Based on YOLOv4 network model, the salient target detection model of video images is constructed. Aiming at the defects of YOLOv4 network model, such as redundant parameters, many convolution modules and complex architecture, a series of model optimization are carried out. Experimental results verify the effectiveness of the model.

关键词： convolution neural network video images salient target detection

来源：评论

学校读者我要写书评

暂无评论

A face recognition system based on convolution neural network using multiple distance face

引用

SOFT COMPUTING 2017年第17期21卷 4995-5002页

作者： Moon, Hae-Min Seo, Chang Ho Pan, Sung Bum Kongju Natl Univ Dept Convergence Sci Kong Ju South Korea Chosun Univ Dept Elect Engn Gwangju South Korea

The recognition technology that recognizes or discriminates certain individuals is very important for the security that provides intelligence services. Face recognition rate can vary depending on variability of the face itself as well as other external factors such as illumination, background, angle and distance of a camera position. The paper suggests a proper method for long-distance face recognition by resolving the change in recognition rate resulting from distance change in long-distance face recognition. For the long-distance face recognition test, face images by actual distance from 1 to 9 m away were obtained directly. Actual face images taken by distance were applied to resolve the issue rising from distance change and CNN was applied to extract overall features of face. The test showed that proposed face recognition algorithm that used CNN as feature extraction and face images by actual distance for training was found to show the best performance.

关键词： Long-distance face recognition Multiple distance face Intelligent robot service convolution neural network

来源：评论

学校读者我要写书评

暂无评论

Early fault diagnosis of ball screws based on 1-D convolution neural network and orthogonal design

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART O-JOURNAL OF RISK AND RELIABILITY 2021年第5期235卷 783-797页

作者： Yin, Chen Wang, Yulin He, Yan Liu, Lu Wang, Yan Yue, Guannan Nanjing Univ Sci & Technol Sch Mech Engn 200 Xiaolinwei Nanjing 210094 Jiangsu Peoples R China Chongqing Univ State Key Lab Mech Transmiss Chongqing Peoples R China Univ Brighton Dept Comp Math & Engn Brighton E Sussex England DFH Satellite Co Ltd Beijing Peoples R China

Ball screws, the most frequently used mechanical components to transform rotary motion into linear motion, can directly affect the precision and service life of engineering machines. Once the efficiency and accuracy of ball screws degrades, the performance and safety of machines are hard to guarantee. Conventional fault diagnosis researches of ball screws are mainly focused on ordinary faults such as preload loss and wear, and lack of the researches on early faults such as lubrication degradation which may progress into the ordinary faults. Additionally, the fault diagnosis models proposed in previous studies divide the fault diagnosis into two separated stages: feature extraction and fault classification, which prevents the usage for real-time applications. The specifically designed algorithm in features extraction stage may be also not workable on other objects. To tackle these drawbacks, this paper proposes a highly accurate early fault diagnosis model of ball screws based on a state-of-the-art deep learning technique, called One-Dimensional convolutional neural network (1-D CNN). Experiments simulating the lubrication degradation of ball screws are specially designed for the early fault diagnosis of the ball screws. Moreover, a concise and efficient approach based on orthogonal design is exploited to scientifically obtain the optimal parameters of the 1-D CNN. The results of a case study verify the superiority of the proposed method in establishing a highly accurate 1-D CNN based fault diagnosis model.

关键词： Early fault diagnosis convolution neural network orthogonal design ball screw deep learning

来源：评论

学校读者我要写书评

暂无评论

Cervical cancer diagnosis using convolution neural network: feature learning and transfer learning approaches

引用

SOFT COMPUTING 2023年 1-11页

作者： Kalbhor, Madhura M. Shinde, Swati V. Pimpri Chinchwad Coll Engn Dept Comp Engn Pune India

Cervical Cancer most often affects women and is a feared disease worldwide. It occurs due to the abnormal growth of cells in the cervix and slowly spreads to other organs in the body. Cervical cancer can be cured completely if detected at an early stage. Various cervical screening methods are available, but early screening with low-cost Pap smear tests is the key to curing. Knowing about this cancer, if we contribute to detecting it at an early stage, may help to save a life. For accurate disease diagnosis and prompt care at an early stage of cell development, automated Pap smear cell recognition and classification are critical. Various computer-aided systems are available that use hand-crafted features of Pap smear images to categorize them into normal and abnormal cells. Deep learning classification methods have been the top choice as their approaches have attained state-of-the-art in tumor identification. In this article, deep learning is used in two different ways. In this approach, pre-trained models as feature extractors and different machine learning algorithms are utilized for classification;the second approach used is transfer learning using pre-trained models to classify Cervical Cancer images. Using the first method with a pre-trained model as a feature extractor, ResNet-50 achieves the highest classification accuracy of 92.03%. Using the second approach of fine-tuning pre-trained models, Google Net has given the highest classification accuracy of 96.01%.

关键词： Cervical cancer classification Machine learning convolution neural network Deep learning Medical image Pap smear Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Hand Sign Recognition for Thai Finger Spelling: an Application of convolution neural network

引用

JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY 2019年第2期91卷 131-146页

作者： Nakjai, Pisit Katanyukul, Tatpong Khon Kaen Univ Dept Comp Engn Khon Kaen Thailand

The finger spelling is a necessary part of Sign Languagean important means of communication among people with hearing disability. The finger spelling is used to spell out names, places or signs that have not yet been defined. A sign recognition system attempts to allow better communication between hearing majority and hearing disability people. Our study investigates Thai Finger Spelling(TFS), its unique characteristics, a design of automatic TFS recognition, and approaches to handle a TFS key potential issue. Our research designs automatic TFS recognition as a two-stage pipeline: (1) locating and extracting a signing hand on the image and (2) classifying the signing image into the valid TFS sign. Signing hand is located and extracted based on color scheme and contour area using Green's Theorem. Two approaches are examined for signing image classification: convolution neural network(CNN)-based and Histogram of Oriented Gradients(HOG)-based approaches. Our experimental results have shown the viability of the proposed pipeline, which achieves mean Average Precision (mAP) at 91.26. The proposed design outperforms state-of-the-arts in automatic visual TFS recognition. In a practical sign recognition system, invalid TFS signs may appear in sign transition or simply from unaware hand postures. We proposed a formulation, called confidence ratio. Confidence ratio is simple to compute and generally compatible with multi-class classifiers. The confidence ratio has been found to be a promising mechanism for identifying invalid TFS signs. Our findings reveal challenging issues related to TFS recognition, practical design for TFS sign transcription, formulation and effectiveness of confidence ratio.

关键词： Sign language transcription Thai sign recognition Thai Finger Spelling convolution neural network Open-set recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Classification of Microblogging Texts Using convolution neural network

引用

IEEE ACCESS 2019年 7卷 68678-68691页

作者： Parwez, Md Aslam Abulaish, Muhammad Jahiruddin Jamia Millia Islamia Dept Comp Sci New Delhi 110025 India South Asian Univ Dept Comp Sci New Delhi 110021 India

Microblogging sites contain a huge amount of textual data and their classification is an imperative task in many applications, such as information filtering, user profiling, topical analysis, and content tagging. Traditional machine learning approaches mainly use a bag of words or n-gram techniques to generate feature vectors as text representation to train classifiers and perform considerably well for many text information processing tasks. Since short texts, such as tweets, contain a very limited number of words, the traditional machine learning approaches suffer from data sparsity and curse of dimensionality problems due to feature representation using a bag of words or n-grams techniques. Nowadays, the use of feature vectors, such as word embeddings, as an input to neural networks for text classification and clustering has shown a remarkable performance gain. In this paper, we present the different neural network models for multi-label classification of microblogging data. The proposed models are based on convolutional neural network (CNN) architectures, which utilize pre-trained word embeddings from generic and domain-specific textual data sources. The word embeddings are used individually and in various combinations through different channels of CNN to predict class labels. We also present a comparative analysis of the proposed CNN models with traditional machine learning models and one of the existing CNN architectures. The proposed models are evaluated over a real Twitter dataset, and the experimental results establish their efficacy to classify microblogging texts with improved accuracy in comparison with the traditional machine learning approaches and the existing CNN models.

关键词： Social network analysis machine learning deep learning multi-label classification word embedding convolution neural network

来源：评论

学校读者我要写书评

暂无评论

A convolution neural network Approach to Access Knee Joint Angle Using Foot Pressure Mapping Images: A Preliminary Investigation

引用

IEEE SENSORS JOURNAL 2021年第15期21卷 16937-16944页

作者： Chhoeum, Vantha Kim, Young Min, Se Dong Soonchunhyang Univ Dept Software Convergence Asan 31538 South Korea Soonchunhyang Univ Inst Wellness Convergence Technol Asan 31538 South Korea Soonchunhyang Univ Dept Med IT Engn & Software Convergence Asan 31538 South Korea

The use of various footwear results in change in knee biomechanics, altering gait pattern. Monitoring the joint angle using machine or deep learning approaches is challenging due to input data type selection. This study introduces a convolution neural network (CNN) relied on foot pressure mapping to assess knee joint angle during use of various footwear. A pilot study was conducted with six healthy participants walking at a comfortable gait on a treadmill wearing three types of footwear. We used the F-scan system to measure foot pressure and saved the information to video as input data. Kinematic data of knee joint angle was calibrated by Kinovea software using video recording and served as reference data. We extracted 10 gait cycles from input and reference data. The CNN model was trained with 12000 images and validated with 3000 images. Results of our study suggest that the CNN image-based can accurately predict the knee joint angle with mean absolute error lower than 10.0 (deg), mean relative error less than 10.0%, and the correlation coefficient between 70.0% and 90.0% for the three types of tested footwear. The CNN image-based generated a similar knee joint angle pattern for a gait cycle (GC) of all tested shoes;less information about the image pattern during the swing phase is available. Integration between CNN and foot pressure mapping image provided a strong correlation in estimating knee joint angle for a GC during use of three footwear types.

关键词： Footwear Knee Sensors Foot Software Legged locomotion neural networks convolution neural network foot pressure mapping footwear gait knee joint angle regression

来源：评论

学校读者我要写书评

暂无评论

Automatic recognition of asphalt pavement cracks using metaheuristic optimized edge detection algorithms and convolution neural network

引用

AUTOMATION IN CONSTRUCTION 2018年 94卷 203-213页

作者： Nhat-Duc Hoang Quoc-Lam Nguyen Van-Duc Tran Duy Tan Univ Inst Res & Dev Fac Civil Engn P809-03 Quang Trung Danang 550000 Vietnam Duy Tan Univ Fac Civil Engn P809-03 Quang Trung Danang 550000 Vietnam Duy Tan Univ Int Sch 254 Nguyen Van Linh Danang 550000 Vietnam

Crack detection is a crucial task in periodic pavement survey. This study establishes and compares the performance of two intelligent approaches for automatic recognition of pavement cracks. The first model relies on edge detection approaches of the Sobel and Canny algorithms. Since the implementation of the two edge detectors require the setting of threshold values, Differential Flower Pollination, as a metaheuristic, is employed to fine-tune the model parameters. The second model is constructed by the implementation of the convolution neural network (CNN) - a deep learning algorithm. CNN has the advantage of performing the feature extraction and the prediction of crack/non-crack condition in an integrated and fully automated manner. Experimental results show that the model based on CNN achieves a good prediction performance of Classification Accuracy Rate (CAR) = 92.08%. This performance is significantly better than the method based on the edge detection algorithms (CAR = 79.99%). Accordingly, the proposed CNN based crack detection model is a promising alternative to support transportation agencies in the task of periodic pavement inspection.

关键词： Pavement crack detection convolution neural network Image processing Edge detection algorithm Deep learning Metaheuristic

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：