检索结果-内蒙古大学图书馆

3rd International Conference on Optics, Computer applications, and Materials Science, CMSD 2023

作者： Dovgal, vladislav v. Gura, Dmitry A. Dyachenko, Roman A. Kuban State Technological University Moskovskaya Str Krasnodar350072 Russia Kuban State Agrarian University 13 Kalinina Str Krasnodar350044 Russia

ISBN: (纸本)9781510674486

To date, the problem of automating work with images taken using satellite systems has become relevant. This task concerns a wide range of human activities, including urban planning, transport logistics, ecology and environmental monitoring, etc. To solve these problems, there are many tools, of which solutions based on the use of machine learning algorithms are particularly effective. The complexity of this approach lies in the wide variety of computer vision models that exist today. The purpose of this research is to select the most popular neural network architectures and conduct a study that aims to identify the most effective architecture in terms of efficiency and quality of work performed. This study will help determine the machine learning model that is most suitable for further use in a software product aimed at working with satellite images, the main functions of which will be object detection and segmentation. © 2024 SPIE. All rights reserved.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Squid Game Implementation Using Advanced Open Computer vision and Music Synchronization 4th

Squid Game Implementation Using Advanced Open Computer Visio...

引用

The 4th International Conference on Data Science, machine Learning 2022

作者： Nataraj, K.R. Kumar, R. Puneeth Nayak, Rahul J. vedashree, v. Kiran, L. Taseen, Rakheeba Department of CSE Don Bosco Institute of Technology Bengaluru India

ISBN: (纸本)9789819920570

According to a recent info trends study, in 2021, mobile and camera device users will have taken more than 1.5 trillion images, a sharp increase from the data from 2016. These image data will be used in a variety of real-time applications, including visual video surveillance, object identification, object detection, and classification. Advanced computer vision algorithms that were an upgrade over traditional computer vision techniques were created to manage these enormous volumes of data automatically. One of the most crucial tasks is object detection, which can greatly enhance the functionality of a variety of computer vision-based applications, including object tracking, license plate detection, mask and social distance detection, etc. To create a comprehensive. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Efficient Hardware Architectures for Accelerating Deep Neural Networks: Survey

引用

IEEE ACCESS 2022年 10卷 131788-131828页

作者： Dhilleswararao, Pudi Boppu, Srinivas Manikandan, M. Sabarimalai Cenkeramaddi, Linga Reddy Indian Inst Technol Bhubaneswar Sch Elect Sci Bhubaneswar 752050 India Indian Inst Technol Bhubaneswar Sch Elect Sci Bhubaneswar 678557 India Univ Agder Dept ICT N-4879 Grimstad Norway

In the modern-day era of technology, a paradigm shift has been witnessed in the areas involving applications of Artificial Intelligence (AI), machine Learning (ML), and Deep Learning (DL). Specifically, Deep Neural Networks (DNNs) have emerged as a popular field of interest in most AI applications such as computer vision, image and video processing, robotics, etc. In the context of developed digital technologies and the availability of authentic data and data handling infrastructure, DNNs have been a credible choice for solving more complex real-life problems. The performance and accuracy of a DNN is a way better than human intelligence in certain situations. However, it is noteworthy that the DNN is computationally too cumbersome in terms of the resources and time to handle these computations. Furthermore, general-purpose architectures like CPUs have issues in handling such computationally intensive algorithms. Therefore, a lot of interest and efforts have been invested by the research fraternity in specialized hardware architectures such as Graphics processing Unit (GPU), Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), and Coarse Grained Reconfigurable Array (CGRA) in the context of effective implementation of computationally intensive algorithms. This paper brings forward the various research works on the development and deployment of DNNs using the aforementioned specialized hardware architectures and embedded AI accelerators. The review discusses the detailed description of the specialized hardware-based accelerators used in the training and/or inference of DNN. A comparative study based on factors like power, area, and throughput, is also made on the various accelerators discussed. Finally, future research and development directions, such as future trends in DNN implementation on specialized hardware accelerators, are discussed. This review article is intended to guide hardware architects to accelerate and improve the effe

关键词： machine learning field programmable gate array (FPGA) deep neural networks (DNN) deep learning (DL) application specific integrated circuits (ASIC) artificial intelligence (AI) central processing unit (CPU) graphics processing unit (GPU) hardware accelerators

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Using Transfer Learning with ResNet50 7th

Facial Expression Recognition Using Transfer Learning with R...

引用

7th International Conference on Inventive Systems and Control, ICISC 2023

作者： Hiremath, Shantala S. Hiremath, Jayaprada Kulkarni, vaishnavi v. Harshit, B.C. Kumar, Sujith Hiremath, Mrutyunjaya S. Image Processing Sony India Software Centre Pvt. Ltd. Karnataka Bangalore560103 India Department of Computer Science and Engineering Visvesvaraya Technological University Belgaum590018 India Department of CSE Alvas Institute of Engineering and Technology Mijar Karnataka Moodbidri574225 India Department of Image Processing eMath Technology Pvt. Ltd. Karnataka Bangalore560072 India Artificial Intelligence and Machine Learning VVDN Technologies Pvt. Ltd. Karnataka Bangalore560066 India

ISBN: (纸本)9789819916238

Facial expression recognition mimics human coding abilities and delivers non-verbal human–robot communication cues. machine learning and deep learning techniques enable real-world computer vision applications. Deep learning-based facial emotion recognition models have under-fitted or over-fitted due to inadequate training data. They are using FER2013’s 7 picture categories. Face detection using AdaBoost, scaling with OpenCv, and contrast improvement with histogram equalization preprocess these pictures. These pre-processed pictures are given to the ResNet50 pre-trained network, which obtained 77.3% accuracy. Transfer learning improves this outcome. By running pre-processed pictures through ResNet50’s FC1000 layer, features are retrieved and trained using a multiclass nonlinear support vector machine (SvM) classifier with seven classes. Training with 89.923% accuracy creates a knowledge base. Emotion recognition techniques let robots understand people, which can improve HCI. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of American Sign Language Using Wavelet Transform and CNN

Performance Analysis of American Sign Language Using Wavelet...

引用

International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2022

作者： Thalange, A.v. Shrigandhi, M.N. Konapure, R.R. Ankaskar, v.N. Walchand Institute of Technology Solapur India

ISBN: (纸本)9789819947164

Sign languages play an important role to bridge the communication gap with hearing-impaired people. A lot of research is carried out to provide efficient, portable, and economical, tools, techniques, and products to make communication smooth, fast, and correct for both static and dynamic sign language recognition. For vision-based sign language recognition, various machine learning algorithms are used. Convolutional Neural Network (CNN) is one such method popularly used. However, the accuracy and speed of recognition are still a matter of concern, especially in dynamic sign language recognition. This paper presents the analysis of the performance of two methods Wavelet Transform and CNN for static American Sign Language (ASL) recognition in terms of (i) the average time of recognition, i.e., processing time for a single sign image, and (ii) accuracy, i.e., recognition rate. This work is carried out on signer-dependent static ASL images. It is observed that using CNN, the accuracy of recognition is 97.30%, and for Wavelet Transform it is 96.20%, indicating a very small difference. However, the average time required for recognition or the processing time for a single image using CNN is 41.2 s of CPU time, and using Wavelet Transform, it is 13.5 s of CPU time, which is almost 67% less than that required using CNN. Thus, compared to CNN, Wavelet Transform can be preferred in applications where timing is a major constraint. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Recent advances on image edge detection: A comprehensive review

引用

NEUROCOMPUTING 2022年 503卷 259-271页

作者： Jing, Junfeng Liu, Shenjuan Wang, Gang Zhang, Weichuan Sun, Changming Xian Polytech Univ Coll Elect & Informat Xian 710048 Peoples R China Xian Polytech Univ Branch Shaanxi Artificial Intelligence Joint Lab Xian Peoples R China Beijing Inst Basic Med Sci Beijing 100850 Peoples R China Griffith Univ Inst Integrated & Intelligent Syst Nathan Qld Australia CSIRO Data61 POB 76 Epping NSW 1710 Australia

Edge detection is one of the most important and fundamental problems in the field of computer vision and image processing. Edge contours extracted from images are widely used as critical cues for various image understanding tasks such as image segmentation, object detection, image retrieval, and corner detection. The purpose of this paper is to review the latest developments on image edge detection. Firstly, the definition and properties of edges are introduced. Secondly, the existing edge detection methods are classified and introduced in detail. Thirdly, the existing widely used datasets and evaluation criteria for edge detection methods are summarized. Finally, future research directions for edge detection are elaborated. (C) 2022 Elsevier B.v. All rights reserved.

关键词： Edge detection Hand-crafted machine learning Evaluation criteria Evaluation database

来源：评论

学校读者我要写书评

暂无评论

Computer and Physical Modeling for the Estimation of the Possibility of Application of Convolutional Neural Networks in Close-Range Photogrammetry

Scientific Visualization

引用

Scientific visualization 2023年第1期15卷 71-82页

作者： Pinchukov, v.v. Poroykov, A.Yu. Shmatko, E.v. Sivov, N.Yu. National Research University "Moscow Power Engineering Institute Russia

Close-range photogrammetry is widely used to measure the surface shape of various objects and its deformations. The classic approach for this is to use a stereo pair of images, which are captured from different angles using two digital video cameras. The surface shape is measured by triangulating a set of corresponding two-dimensional points from these images using a predetermined location of cameras relative to each other. various algorithms are used to find these points. Several photogrammetry methods use cross-correlation for this purpose. This paper discusses the possibility of replacing the correlation algorithm with neural networks to determine displacements of small areas in the images. They allow increasing the calculation speed and the spatial resolution of the measurement results. To verify the possibility of using convolutional networks for photogrammetry tasks, computer and physical modeling were carried out. For the first test, a set of synthetically generated images representing images of the Particle image velocimetry method was used. The displacements of particles in the images are known, it allows to estimate the accuracy of processing of such images. For the second test, a series of experimental images with surfaces with different deformation was obtained. Computational experiments were performed to process synthetic and experimental images using selected neural networks and a classical cross-correlation algorithm. The limitations on the use of the compared algorithms were determined and their error in reconstructing the three-dimensional shape of the surface was evaluated. Computer and physical modeling have shown the operability and efficiency of neural networks for processing photogrammetry images. © 2023 National Research Nuclear University. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

AutoFace: How to Obtain Mobile Neural Network-Based Facial Feature Extractor in Less Than 10 Minutes?

引用

IEEE ACCESS 2024年 12卷 25106-25118页

作者： Savchenko, Andrey v. Sber AI Lab Moscow 117312 Russia HSE Univ Lab Algorithms & Technol Network Anal Nizhnii Novgorod 603155 Russia

various mobile and edge devices have significantly different processing capabilities, making it challenging to develop a single universal architecture of a neural network to extract facial embeddings. In this paper, we study the automated machine learning techniques to design a neural network with the best performance on a concrete device. The novel procedure is proposed to choose the better subnetwork of the Supernet based on a genetic algorithm with a surrogate binary classifier to compare the expected accuracy of two subnetworks. The latter uses only encoding of a candidate subnetwork and does not require directly estimating its accuracy on a validation set. As a result, the most computationally efficient and accurate model in TensorFlow Lite format is obtained in less than 10 minutes for a specific device and latency constraint. An Android demo application has been developed to demonstrate the potential of designed neural networks. It is experimentally shown that the proposed approach is universal: it can extract deep embeddings for tasks such as face verification and facial expression recognition and for various types of devices, including smartphones and Raspberry Pi single-board mini-computers. Our models process one facial image in real-time and achieve much higher accuracy when compared to the best-known lightweight networks.

关键词： Face recognition Task analysis Training Computer architecture Feature extraction Artificial neural networks Performance evaluation Mobile communication Genetic algorithms Search methods Evolutionary computation Emotion recognition Mobile applications edge devices genetic algorithms evolutionary search face verification facial expression recognition

来源：评论

学校读者我要写书评

暂无评论

Rapid detection of adulteration in pistachio based on deep learning methodologies and affordable system

引用

MULTIMEDIA TOOLS AND applications 2024年第5期83卷 14797-14820页

作者： Cinarer, Gokalp Dogan, Nurcan Kilic, Kazim Dogan, Cemhan Yozgat Bozok Univ Fac Engn & Architecture Dept Comp Engn TR-66100 Yozgat Turkiye Yozgat Bozok Univ Bogazliyan Vocat Sch Dept Food Technol TR-66400 Yozgat Turkiye Yozgat Bozok Univ Yozgat Vocat Sch Dept Comp Technol TR-66100 Yozgat Turkiye

The development of international trade has facilitated the global distribution of food. Ensuring the safety of food products is a crucial process that spans from production to sale. Mismanagement of this process can pose significant public health risks. The issue of food adulteration is increasingly prevalent, necessitating the development of fast and reliable methods for its detection. Deep learning, as an effective machine learning algorithm, has emerged as a new field in the food industry, offering rapid and accurate results in the identification of food adulteration. In this study, a digital image and deep learning-based method was developed to detect spinach adulteration in pistachios. A unique dataset with 6 classes was created in a laboratory environment for testing the method. The adulteration rates for each class were determined, and images were analyzed in various color spaces, including Red Green Blue (RGB), HSv (Hue Saturation value), Y,u and v (YUv), and L, a, and b (LAB). Subsequently, Convolutional Neural Network (CNN) architectures, namely ResNet-50, vGGNet-19, and DenseNet201, were employed for classification. The accuracy of all color spaces and architectural combinations exceeded 90%. Notably, the vGGNet-19 architecture achieved a 100% success rate in classifying the LAB color space. Moreover, the YUv/ResNet-50 and HSv/vGGNet-19 combinations demonstrated over 98% success in detecting peanut adulteration. The utilization of deep learning-based architectures enables swift and effortless analysis of complex food samples, eliminating the challenges associated with analyzing large quantities of food and effectively preventing food adulteration.

关键词： Pistachio Adulteration Deep Learning CNN (Convolutional Neural Network) Transfer Learning image processing

来源：评论

学校读者我要写书评

暂无评论

Age detection by optimizing the structure of layers and neurons in the neural network

引用

JOURNAL OF OPTICS-INDIA 2024年第2期53卷 1186-1202页

作者： Jiang, Zhenghong Zhou, Chunrong Chongqing Vocat Coll Transportat Sch Big Data Jiangjin 402247 Chongqing Peoples R China

Age detection is a fundamental task in computer vision with numerous applications, from targeted advertising to security systems. This paper proposes a robust approach for age estimation based on local binary patterns to extract features associated with face images. The goal of accurately predicting people's ages from facial images is to overcome challenges such as changes in lighting conditions, poses, and facial expressions. The proposed method uses a combination of feature extraction, feature selection, and machine learning algorithms, which we named Hybrid method. At first, facial landmarks are detected to determine the key points of the face and enable the extraction of the corresponding facial features. These features are then fed into a feature selection algorithm to identify the most distinctive ones, reducing dimensionality and increasing model efficiency. To evaluate the proposed approach, extensive experiments are conducted on benchmark datasets, including different age groups and ethnicities. The results show the effectiveness of the proposed method in achieving high accuracy and robustness in age estimation. As shown in the calculation results, the detection rate and accuracy of Hybrid method age estimation calculations are better than competing methods. For Hybrid method, the mean absolute error is 4.94 years, with a standard deviation of 4.74 years. From the point of view of average absolute error, this age estimation method is superior to other methods that have been presented to date. The proposed method for estimating the age of people has a final sensitivity of 97.2%, an accuracy of 96.8%, and a precision of 99.1%. In addition, it is stated in the specifications of the implementation system that the program can be executed in about 3.5 s, which is a suitable speed for estimating the age of people based on their face photographs.

关键词： ANN Hybrid method Age detection image processing

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：