检索结果-内蒙古大学图书馆

International Joint conference on neural networks (IJCNN)

作者： Sawahashi, Naoki Principe, Jose C. Univ Florida Elect & Comp Engn Gainesville FL 32610 USA

ISBN: (纸本)9798350359329;9798350359312

Cellular automata have ideal properties for scalable and efficient computing, but a lack of a training method limits their real-world applications. First, we propose to partition the cellular lattice into three regions: input, output, and processing. Second, we propose a novel synthesis method to train a linear hybrid cellular automaton. Third, we show image classification on the MNIST dataset using only logic operations. By mapping local states over the globally linear lattice, the proposed model achieved above 90% test accuracy in binary image classification. Our method does not require any pre or post-processors to perform computation over the lattice. Hence, the lattice maintains its massive parallelism and locality of computation, ideal for ultra-low power processing in machine learning.

关键词： cellular automata image classification parallel processing neuromorphic computing machine learning

来源：评论

学校读者我要写书评

暂无评论

Document image segmentation using a two-stage neural network

Document image segmentation using a two-stage neural network

引用

conference on applications of artificial neural networks in image processing V

作者： Ahmed, M Cooper, B Love, S Lexmark Int Inc Software Res Lexington KY USA

ISBN: (纸本)0819435805

In this paper, we present a new system to segment and label document images into text, halftone images, and background using feature extraction and unsupervised clustering. Each pixel is assigned a feature pattern consisting of a scaled family of differential geometrical invariant features and texture features extracted from the cooccurence matrix. The invariant feature pattern is then assigned to a specific region using a two-stage neural network system. The first stage is a self-organizing principal components analysis (SOPCA) network that is used to project the feature vector onto its leading principal axes found by using principal components analysis (PCA). Using the SOPCA algorithm, we can train the SOPCA network to project our feature vector orthogonally onto the subspace spanned by the eigenvectors belonging to the largest eigenvalues. By doing that we ensure that the vector is represented by a reduced number of effective features. The next step is to cluster the output of the SOPCA network into different regions. This is accomplished using a self-organizing feature-map (SOFM) network. In this paper, we demonstrate the power of the SOPCA-SOFM approach to segment document images into text, halftone, and background.

关键词： image segmentation Principal component analysis Feature extraction neural networks Halftones Neurons Moire patterns Feature selection Network security image quality

来源：评论

学校读者我要写书评

暂无评论

Estimation of Leaf Area in Bell Pepper Plant using image processing techniques and artificial neuralnetworks 7

Estimation of Leaf Area in Bell Pepper Plant using Image Pro...

引用

7th IEEE International conference on Signal and image processing applications, ICSIPA 2021

作者： Mohammadi, Vahid Minaei, Saeid Mahdavian, Ali Reza Khoshtaghaza, Mohammad Hadi Gouton, Pierre Biosystems Engineering Department Faculty of Agriculture Tarbiat Modares University No 7 Al Ahmad Street Tehran Iran ImViA Laboratory UFR Sciences et Techniques Université de Bourgogne Franche-Comté 9 Avenue Alain Savary Dijon France

ISBN: (纸本)9781665435925

Measurement and estimation of physical properties of plant leaves have always been considered as important requirements for monitoring and optimizing of plant growth. This study aimed at utilization of image processing and artificial intelligence techniques for non-invasive and nondestructive estimation of bell pepper leaves properties in the first month of growth. Physical properties of bell pepper plant leaves were extracted from RGB images. The algorithm makes use of gradient magnitude and watershed image. Leaf area as the most important index of growth was estimated as a function of other physical parameters including leaf length, width, perimeter etc. Using stereo imaging, the leaf distance from the camera was measured and applied in pixel-wise calculations. artificial neural networks (ANN) were trained based on a database of actual values of leaf properties (i.e. 311 bell-pepper plant leaves). The success rate of the developed algorithm for detection and separation of leaves was 84.32%. The Multilayer Perceptron (MLP) network could successfully estimate the leaf area values with a validation performance of 0.912. © 2021 IEEE

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

A Survey on Capsule networks: Evolution, Application, and Future Development

A Survey on Capsule Networks: Evolution, Application, and Fu...

引用

International conference on High Performance Big Data and Intelligent Systems (HPBD and IS)

作者： Li, Jiawei Zhao, Qichen Li, Nan Ma, Lin Xia, Xuan Zhang, Xiaoguang Ding, Ning Li, Nannan Xi An Jiao Tong Univ Coll Comp Sci & Technol Xian Peoples R China Chinese Univ Hong Kong Sch Data Sci Shenzhen Peoples R China Shenzhen Inst Artificial Intelligence & Robot Soc Shenzhen Peoples R China Chinese Univ Hong Kong Inst Robot & Intelligent Mfg Shenzhen Peoples R China Macau Univ Sci & Technol Int Inst Next Generat Internet Macau Peoples R China

ISBN: (纸本)9781665413275

Capsule networks have drawn increasing attention since the concept is proposed in 2011. They hold advantages over convolutional neural networks (CNNs) on modeling part-to-whole relationships between entities and learning viewpoint invariant representations. A variety of improved designs and applications related to capsule networks have been explored within the past decade. This paper presents a relatively thorough survey of literatures corresponding to the evolution of the capsule networks and their applications. Different design of capsule networks from Hinton's group as well as other researchers are reviewed. applications of capsule networks in various scenarios and tasks are elaborated, including hyperspectral image processing, medical image processing, facial image processing, text classification, object detection, image segmentation, few-shot learning, etc. The relation and comparison of capsule networks, CNNs, and transformers, and the trend of future development of capsule networks are discussed. We believe this review provides a good reference to researchers who are interested in capsule networks.

关键词： Capsule networks deep learning artificial intelligence artificial neural network

来源：评论

学校读者我要写书评

暂无评论

SMART PIXEL DESIGNS FOR image-processing 2

SMART PIXEL DESIGNS FOR IMAGE-PROCESSING

引用

conference on Photonics for Processors, neural networks, and Memories ii

作者： KIAMILEV, F KRISHNAMOORTHY, AV UNIV N CAROLINA DEPT ELECT ENGNCHARLOTTENC 28223

ISBN: (纸本)0819416215

image processing is widely regarded as a successful application of electronic technology. However, there is a wide gap between commercially successful image processing implementations and system design that have been proposed by the research community. Of particular interest are image processing architectures that use large number of densely interconnected processors to compute and transmit image date in parallel 2-D format. The interconnect density and packaging constraints of electronic packaging technology preclude efficient implementation of such architectures. In contrast, optoelectronic integrated circuits combined with surface-normal optical interconnects offer the promise of a technology platform that is inherently better suited for the implementation of interconnect intensive image processing applications.

关键词： image processing Data processing Optoelectronics Packaging image storage Computer architecture Electrical engineering image transmission Photonic integrated circuits Photonics

来源：评论

学校读者我要写书评

暂无评论

The Utilization of artificial Intelligence and Deep Learning for Identifying Vehicle Wheels 4th

The Utilization of Artificial Intelligence and Deep Learning...

引用

4th International conference on Digital Technologies and applications (ICDTA)

作者： Maaroufi, Mohammed Mouhcine Stour, Laila Agoumi, Ali Demori, Julien Hassan II Univ Casablanca Fac Sci & Technol Mohammedia Proc & Environm Engn Lab BP 146 Mohammadia Morocco Hassania Sch Publ Works Civil Engn Hydraul Environm & Climate Lab Casablanca Morocco Macq Mobil Evere Belgium

ISBN: (纸本)9783031686498;9783031686504

The technology using artificial intelligence (AI) allows, through the preprocessing of video and image data, their transformation into traffic information, the recognition in abusive conditions of elements, the specification of the different characteristics of the vehicle (type, brand, model, color), object detection and tracking, automatic calibration and positioning. Algorithms for performance evaluation can evaluate recognition quality and detect malfunctions due to external factors, reduced lighting conditions, or incorrect camera installation. This article discusses the application of AI and deep learning techniques to identify vehicle wheels. It highlights the preprocessing of image and video data to extract traffic information, detect vehicle attributes, and perform object tracking. The study focuses on understanding AI and convolutional neural networks (CNNs) for image processing, emphasizing the significance of feature extraction algorithms. The research outlines the methodology for creating a dataset of annotated wheel images, selecting the YOLO detection algorithm, and using the Darknet Github framework for training and testing CNNs. It discusses the training process, including configuration, data augmentation, and evaluation metrics like Mean Average Precision (MAP) and Intersection Over Union (IOU). Finally, the article concludes with insights into the practical applications of the developed wheel detection system, suggesting future improvements and potential integrations with other projects.

关键词： Smart mobility artificial intelligence deep learning convolutional neural networks wheel

来源：评论

学校读者我要写书评

暂无评论

image segmentation applications with unsupervised neural networks

Image segmentation applications with unsupervised neural net...

引用

IEEE 13th Signal processing and Communications applications conference, SIU 2005

作者： Şengür, Abdulkadir Türkoǧlu, Ibrahim Ince, M. Cevdet Bilgisayar ve Elektronik Eǧitimi Bölümü Firat Üniversitesi Elaziǧ Elektrik ve Elektronik Mühendisligi Bölümü Firat Üniversitesi Elaziǧ

ISBN: (纸本)0780392396

image segmentation is the most difficult task of low level computer vision applications. The performance of the segmentation algorithm affects the subsequent applications performances such as high level pattern recognition applications. In this study we examine 1-D and 2-D unsupervised artificial neural networks (Kohonen network) and we evaluate the performances of the examined structures over image segmentation applications. Experimental studies show the advantages and disadvantages of the Kohonen networks. © 2005 IEEE.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

Multidimensional polynomial powers of sigmoid (PPS) Wavelet neural networks

Multidimensional polynomial powers of sigmoid (PPS) Wavelet ...

引用

1st International conference on Bio-Inspired Systems and Signal processing

作者： Marar, Joao Fernando Coelho, Helder Sao Paulo State Univ Fac Ciencias Dept Comp Adapt Syst & Computat Intelligence Lab Sao Paulo Brazil

ISBN: (纸本)9789898111180

Wavelet functions have been used as the activation function in feedforward neural networks. An abundance of R&D has been produced on wavelet neural network area. Some successful algorithms and applications in wavelet neural network have been developed and reported in the literature. However, most of the aforementioned reports impose many restrictions in the classical backpropagation algorithm, such as low dimensionality, tensor product of wavelets, parameters initialization, and, in general, the output is one dimensional, etc. In order to remove some of these restrictions, a family of polynomial wavelets generated from powers of sigmoid functions is presented. We described how a multidimensional wavelet neural networks based on these functions can be constructed, trained and applied in pattern recognition tasks. As an example of application for the method proposed, it is studied the exclusive-or (XOR) problem.

关键词： artificial neural network function approximation polynomial powers of sigmoid (PPS) wavelets functions PPS-Wavelet neural networks activation functions feedforward networks

来源：评论

学校读者我要写书评

暂无评论

Study on Text Classification using Capsule networks 5

Study on Text Classification using Capsule Networks

引用

5th International conference on Advanced Computing and Communication Systems (ICACCS)

作者： Katarya, Rahul Arora, Yamini Delhi Technol Univ Comp Sci Engn New Delhi India Delhi Technol Univ Informat Technol New Delhi India

ISBN: (纸本)9781538695333

Deep neural networks are being used in different domains, from image Classification to Natural language processing. Research has been done on artificial neural networks and different types of neural networks such as CNN and RNN have been studied and developed. They have been applied in different applications. In 2017, a new concept has been introduced in the neural networks Architecture by Geoffrey Hinton Capsule networks. Capsule networks bring an improvement in the old neural network architecture and it has worked better than the Convolutional neural networks (CNN). There are certain disadvantages of using the convolutional neural networks, few areas where CNN lacks, Capsule networks have overcome those limitations and now it is better neural network architecture for developing models to solve the problems in different domains. Capsule networks are primarily used for image Classification. They can be applied in the areas of Natural Language processing and Recommender Systems to utilize the textual information in a more efficient manner. neural networks can be trained to learn numeric representations of various words and phrases using models such as Word2Vec and Glove and can be applied to classify the data in different categories. This paper presents a review on text classification using the newly introduced capsule networks.

关键词： neural networks Classification Capsules Capsule networks

来源：评论

学校读者我要写书评

暂无评论

Development of a multispectral imagery device devoted to weed detection

引用

JOURNAL OF ELECTRONIC IMAGING 2004年第3期13卷 547-552页

作者： Vioix, JB Douzals, JP ENESAD F-21800 Quetigny France LE21 F-71200 Le Creusot France

Multispectral imagery is a large domain with a number of practical applications: thermography and quality control in industry, food science, and agronomy. The main interest is to obtain spectral information of the objects for which a reflectance signal can be associated to physical, chemical, and/or biological properties. Agronomic applications of multispectral imagery generally involve the acquisition of several images in visible and near infrared wavelengths. We first present a different kind of multispectral devices used for agronomic applications and then introduce an original multispectral acquisition system based on a single CCD. First results in laboratory are detailed, presenting a detection method using a neural network and in-field acquisitions and their results are shown. To improve the quality of weed detection, the spatial distribution of crops is used by a second method. Finally, the first works on merging are outlined. (C) 2004 SPIE and IST.

关键词： Optical filters Multispectral imaging Charge-coupled devices Reflectivity neural networks Cameras Neurons Spatial resolution image processing Visible radiation

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：