检索结果-内蒙古大学图书馆

IEEE International conference on Smart Instrumentation, Measurement and applications (ICSIMA)

作者： Abdul Mutholib Teddy S. Gunawan Jalel Chebil Mira Kartiwi Electrical Computer Engineering Department International Islamic University Malaysia Kuala Lumpur Malaysia Information System Department International Islamic University Malaysia Kuala Lumpur Malaysia

Since the past decades, many researchers proposed their methods to recognize the vehicle number plate. One of the methods is template matching which is executed in the optical character recognition (OCR) step of the automatic number plate recognition (ANPR) system. In previous researches, many researchers are used a high end desktop PC and high resolution camera to implement the ANPR system. In this paper, the optimization of ANPR algorithm on limited hardware of Android mobile phone is presented. First, various steps to optimize ANPR and OCR block using template matching are described. Our proposed algorithm was based on Tesseract library. For comparison purpose, the template matching based OCR will be compared to artificial neural Network (ANN) based OCR. The optimization on ANPR was performed as currently there is no image processing tool available on the standard Android mobile phone. By optimization of ANPR, many advantages could be achieved, such as higher recognition accuracy, less resource consumption, and less computational complexity. Results on 30 images showed that the recognition rate was 97.46% while the processing time was 1.13.

关键词： Optimization Optical character recognition software Character recognition Smart phones Licenses artificial neural networks Accuracy

来源：评论

学校读者我要写书评

暂无评论

A Pseudoinverse Incremental Algorithm for Fast Training Deep neural networks with Application to Spectra Pattern Recognition

A Pseudoinverse Incremental Algorithm for Fast Training Deep...

引用

International Joint conference on neural networks

作者： Ke Wang Ping Guo Qian Yin A-Li Luo Xin Xin School of Computer Science and Technology Beijing Institute of Technology Image Processing and Pattern Recognition Laboratory Beijing Normal University Key Laboratory of Optical Astronomy National Astronomical Observatories Chinese Academy of Sciences

ISBN: (纸本)9781509006212

Deep learning scheme has received significant attention during these years, particularly as a way of building hierarchical representations from unlabeled data for a variety of signal and information processing tasks. However, deep neural networks suffer from slow learning speed since most used training algorithms are based on variations of the gradient descent algorithms which require iterative optimization and thus are time-consuming. In addition, a series of control parameters need to be specified empirically which lacks of the theoretical guidance, and current learning algorithms for deep networks are not very suitable to incremental learning scenario. To address these issues, we propose a fast learning scheme in this paper. The basic idea of our approach is to pre-train basic units such as auto-encoders of the deep architecture in an analytical way without any iterative optimization procedure. This scheme is also extended to an incremental learning version. The experimental result shows the superiority of our approach over the state-of-the-art gradient descent based algorithms. To demonstrate the impact of our algorithm on complicated real world applications, we give an example of its performance in astronomical spectra pattern recognition.

关键词： astronomical spectra Spectra Pattern recognition learning (artificial intelligence) Recognition (Psychology) neural network algorithms control parameter Optimization Procedure descent Fasting Functional training Road

来源：评论

学校读者我要写书评

暂无评论

SwiftSpike: An Efficient Software Framework for the Development of Spiking neural networks

SwiftSpike: An Efficient Software Framework for the Developm...

引用

Omni-layer Intelligent Systems (COINS), International conference on

作者： Genevieve Claire Fahey Samuel J. Ippolito Glenn I. Matthews School of Engineering RMIT University Melbourne Australia

Spiking neural networks (SNNs) are Machine Learning (ML) algorithms that use sparse, binary, event-driven spikes to propagate information through the network. Coupled with physical neuromorphic processors, SNNs are more energy efficient compared to matrix-based artificial neural Network (ANN) solutions, making them well-suited to resource-constrained Internet of Things (IoT) applications that have strict power and local processing requirements. SNN algorithms still require further research to improve their accuracy and allow them to compete with ANNs but their development is hampered by a lack of fast, modular software and simulation frameworks. In this work we present SwiftSpike, an efficient, customisable SNN development framework written in C++ that supports user-defined neuron and synapse models. We validate SwiftSpike against the widely used Brian 2 framework and demonstrate speed-ups of 17.3x on an unsupervised image recognition task trained with Spike-Timing-Dependent Plasticity (STDP).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Individual processing speed analysis for traffic sign detection and recognition

Individual processing speed analysis for traffic sign detect...

引用

IEEE International conference on Smart Instrumentation, Measurement and applications (ICSIMA)

作者： Nursabilillah Mohd Ali Nur Maisarah Mohd Sobran Syahar Azalia Ab. Shukur Mariam Md Ghazaly Ahmad Fayeez Tuani Ibrahim Department of Mechatronic Engineering University Teknikal Malaysia Melaka Malaysia Department of Mechatronic Engineering Faculty of Electrical Engineering University Teknikal Malaysia Melaka Malaysia

Of late, traffic sign detection and recognition are becoming very prevalent topic as it enhances drivers towards safety and alert them with precaution information. This study reports about processing time of the individual color detection and recognition of the partial occlusion traffic sign that have been previously implemented using HSV and RGB color ratio and ANN and PCA method respectively for detection and recognition. The data set for detection and classification process has been successfully created in various places in Malaysia that involved with degradation and out of planes rotated of the signs. There are three standard types of colored images have been used in the study namely Red, Blue and Yellow signs. In this study, we analyze the system processing speed of individual color detection and classification respectively using red, green and blue (RGB) and hue, saturation and value (HSV) color segmentation techniques, supervised feed forward artificial neural network (ANN) and principal component analysis (PCA). The experimental result shown that processing time of individual color detection during daytime and at night using HSV method is slightly faster than RGB technique. On the other hand, supervised feed forward neural network has reached almost 1s in recognizing traffic sign images rather than PCA with only 0.0238s.

关键词： image color analysis Vehicles Principal component analysis artificial neural networks Roads Accidents Hardware

来源：评论

学校读者我要写书评

暂无评论

Efficient Region Proposals Generation for Object Detection

Efficient Region Proposals Generation for Object Detection

引用

International conference on image and Signal processing and their applications (ISPA)

作者： Imene Bourafa Mokhtar Taffar Mohamed-Nadjib Zennir LaRIA Lab Computer Sc. Dpt University of Jijel Jijel Algeria

ISBN: (数字)9798350309249

ISBN: (纸本)9798350309256

Object detection models based on region proposals, whether those using classic methods or deep neural networks, have provided cutting-edge results and achieved an interesting speed/accuracy ratio. The state-of-the-art methods using local feature detectors to generate region proposals incorporate descriptor information or combine the detected interest points with other methods to generate proposals. In this work, we aim to explore the efficiency of proposals generated only according to the position of the generated SURF keypoints. We propose an object detection approach namely SURF-Fast-RCNN, based on FAST-RCNN framework, that integrates SURF local detector. Instead of using the proposals produced by the selective search method, each 2-combination of interest points is considered as a candidate box which we call keypoint anchors. Based on the intersection over union (IoU) value of each keypoint anchor with ground truth boxes, we discard the excess anchors and assign labels to the retained ones denoting their class labels. The retained anchors are fed into the detector for training, followed by NMS operation to suppress the overlapping boxes. Our SURF-Fast-RCNN model is trained and tested on different region proposals on the MS-COCO dataset examples. With 1000 region proposals, the performances of our model reached an accuracy of about 82% and a mean average precision of 84.04%, which are encouraging results.

关键词： Training Visualization image recognition Search methods Detectors Object detection artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Classification of Green Series Fischer's Lovebirds Using Fuzzy Logic Algorithm

Classification of Green Series Fischer's Lovebirds Using Fuz...

引用

IEEE International conference on artificial Intelligence in Engineering and Technology (iiCAIET)

作者： Jobert D. Apilado Aron Miguel R. Jintalan Cyrel O. Manlises School of Electrical Electronics and Computer Engineering Mapua University Manila Philippines

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

This study explores the application of fuzzy logic on the Raspberry Pi platform for classifying Green Series Fischer” s Lovebirds, specifically Green, Jade, Misty, and Olive. African Fischer's lovebirds, known for their vibrant colors and sociable nature, pose a classification challenge due to their varied color mutations. Previous techniques such as image processing, artificial neural networks, and color segmentation have been used for species identification, achieving varying degrees of success. Using a fuzzy logic algorithm combined with membership functions and fuzzy rules, the researchers achieved an accuracy of 72.5% on a testing set of 40 samples, with 10 samples per class. The system integrates a camera module and OpenCV for image capture and processing, offering an efficient alternative to traditional visual inspection methods often inadequate for untrained observers. The methodology involved capturing images using a Raspberry Pi 3 Model B and developing a fuzzy logic model for color-based feature extraction and classification. The results demonstrate the effectiveness of fuzzy logic in distinguishing subtle color differences among lovebird variations. This study underscores the potential of combining fuzzy logic and Raspberry Pi for real-time image classification, contributing to advancements in color image processing and practical applications in avian identification.

关键词： Fuzzy logic Visualization image segmentation image color analysis Observers Inspection Real-time systems Classification algorithms Testing image classification

来源：评论

学校读者我要写书评

暂无评论

image Based Quality Inspection in Smart Manufacturing Systems: A Literature Review

引用

Procedia CIRP 2021年 103卷 262-267页

作者： Milica Babic Mojtaba A. Farahani Thorsten Wuest Industrial and Management Systems Engineering West Virginia University Morgantown WV 26505 USA

Quality inspection is an important component of today’s smart manufacturing systems (SMS). Their prominence stems from the objective of manufacturing companies to i) deliver high-quality products, ii) inspire brand loyalty, iii) keep within regulations, and iv) minimize waste of resources (incl. such as employee and machine time, scrap materials) to maximize profit. There is a wide variety of quality inspection systems deployed on the shop floor utilizing different technologies, ranging from human operators to high-fidelity sensor systems to image based systems. In this work we focus on the latter, modern image-based quality inspection systems and processes. Vision based quality inspection has seen an increase in applications and academic attention over the past decade, aligned with the dawn of Industry 4.0. On the one hand, digital camera systems (including the optics, sensors, and connectivity) have become more powerful and at the same time more affordable. On the other hand, the analytics – namely artificial intelligence and machine learning algorithms – have made tremendous advancements in terms of results as well as accessibility. Most notably, deep neural networks and deep learning have elevated the potential of computer vision in quality inspection applications to the next level. In this paper, we will conduct a comprehensive literature review analysing image based quality inspection systems in SMS over the last decade. We will focus particularly on the question of how image based in-situ quality inspection of three-dimensional parts is currently conducted. The results will provide an overview of the different available image based quality inspection approaches, their benefits and challenges, as well as specific application areas and/or industries.

关键词： Machine Vision Visual Inspection Quality Inspection image processing Smart Manufacturing Production Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

An image processing Player Acquisition and Tracking System for E-sports

An Image processing Player Acquisition and Tracking System f...

引用

International conference on Cloud Technologies and applications (CloudTech)

作者： Joaquim Vieira Nicolaas Luwes Center for Sustainable Smart Cities Bloemfontein South Africa

ISBN: (数字)9781728161754

ISBN: (纸本)9781728161761

Studying one's enemy has been the key to winning a war for centuries. This can be seen in the success of the historical success of the Chinese, Greek, and Mongolian empires. Over the years, these dogmas of studying one's enemy before the battle have now made its way into our modern lives as well, not only in real battle but also on the electronic battlefield. In E-Sports, teams will often study one another to find the strengths and weaknesses that can be exploited and avoided in the next encounters. The manner in which this is done is through the observing of prior matches to determine patterns in the manner in which they operate, play and react. This process is extremely time-consuming as one match is a minimum of an hour in duration. This paper demonstrates a program able to acquire and track player positions throughout a match in order to simplify and automate this process. This tracking data can be used with machine learning and or neural networks as part of a professional E-Sport prediction model.

关键词： Cloud computing neural networks Machine learning Predictive models Real-time systems Pattern matching Sports

来源：评论

学校读者我要写书评

暂无评论

Implementation of online optical character recognition system using embedded DSP platform

Implementation of online optical character recognition syste...

引用

International conference on Advanced Electronic Systems (ICAES)

作者： Nirmal Savio Paul J Suriya Prakash Student Trainee CSIR-CEERI Chennai Centre CSIR Madras Complex Chennai India Central Electronics Engineering Research Institute CSIR Pilani Rajasthan IN

This paper describes the implementation of an Optical Character Recognition (OCR) system using embedded DSP hardware and software platforms. The system utilizes an area-scan camera and the HALCON image processing library running upon the Strampe VisionBox hardware platform programmed through the Code Composer Studio IDE. This prototype system can be modified for several potential applications such as sorting of packed food based on expiry date.

关键词： Optical character recognition software Cameras Character recognition artificial neural networks Hardware Digital signal processing Optical imaging

来源：评论

学校读者我要写书评

暂无评论

Integration of Machine Learning Algorithms and Nash Game Theory in A Similar image Retrieval System

Integration of Machine Learning Algorithms and Nash Game The...

引用

International conference on Optimization and applications (ICOA)

作者： Mohammed Touaoussa Noureddine Moussaid Anouar Ben-Loghfyry Omar Gouasnouane Hassan II University Casablanca LMCSA FST Mohammedia Morrocco Hassan II University Casablanca LMCMANFST Mohammedia Morrocco

ISBN: (数字)9798350387353

ISBN: (纸本)9798350387360

In the realm of image processing, the ability to describe an image accurately and comprehensively is paramount. images, whether captured by cameras, generated by computers, or obtained through various means, contain a wealth of information waiting to be analyzed and understood. Among the key elements defining an image, two stand out prominently: color and form. Each of these components plays a crucial role in shaping our perception and interpretation of visual data. Our team has crafted a CBIR system enhanced by a duo of machine learning algorithms and various clustering techniques alongside low-level image feature extraction methods. These components converge to formulate a Nash game, thereby presenting us with a multi-criteria optimization challenge. In tackling this challenge, we've devised a In this two-player static Nash game, each player employs a unique strategy, specifically color moments and shape moments, corresponding to their objective functions. The Nash equilibrium is represented by the membership classes assigned to the query image. Looking ahead, we intend to replace the Zernike moments with a neural network approach and thoroughly compare the two methods concerning time and efficiency

关键词： Visualization Machine learning algorithms image color analysis Shape image retrieval neural networks Machine learning Games Nash equilibrium Optimization

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：