检索结果-内蒙古大学图书馆

5th International Conference on Advances in Electrical Engineering (ICAEE)

作者： Hasan, Md Jahid Wahid, Md Ferdous Alom, Md Shahin Hajee Mohammad Danesh Sci & Technol Univ Dept Elect & Elect Engn Dinajpur 5200 Bangladesh

ISBN: (纸本)9781728149349

Nowadays, Citizen of one country is traveling to another country to settle their various needs through widespread modern transportation system. However, Passport is a worldly recognized indispensable identity document which is required for travelling internationally. Moreover, Citizen of many countries is strictly prohibited from travelling to other certain countries. So, Passport inspection is a key responsibility for immigration officers in order to confirm the identity of traveler. In addition to that it is a laborious and time-consuming task for immigration officers to check all passports meticulously. Hence, automatic country recognition from passport cover image can save a lot of time and physical labour by identifying those unauthorized travelers. Thus in this paper, we have investigated an automatic system using deep convolutional neural network (DCNN) based on transfer learning with Support Vector Machine (SVM) classifier to analyze passport cover for country identification. Here, the Inception-ResNet-v2 DCNN architecture has been retrained with 80% of image dataset which includes ten classes of passport cover of ten countries using transfer learning method for feature extraction and the extracted feature were then used to train SVM. The proposed model achieved an accuracy level around of 98.75% on the test image dataset.

关键词： passport deep convolutional neural network transfer learning support vector machine feature extraction

来源：评论

学校读者我要写书评

暂无评论

deep convolutional neural network Target Classification for Underwater Synthetic Aperture Sonar Imagery 24

Deep Convolutional Neural Network Target Classification for ...

引用

Conference on Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIV

作者： Galusha, A. Dale, J. Keller, J. M. Zare, A. Univ Missouri Elect Engn & Comp Sci Dept Columbia MO 65211 USA Univ Florida Elect & Comp Engn Dept Gainesville FL USA

ISBN: (数字)9781510626904

ISBN: (纸本)9781510626904

In underwater synthetic aperture sonar (SAS) imagery, there is a need for accurate target recognition algorithms. Automated detection of underwater objects has many applications, not the least of which being the safe extraction of dangerous explosives. In this paper, we discuss experiments on a deep learning approach to binary classification of target and non-target SAS image tiles. Using a fused anomaly detector, the pixels in each SAS image have been narrowed down into regions of interest (ROIs), from which small target-sized tiles are extracted. This tile data set is created prior to the work done in this paper. Our objective is to carry out extensive tests on the classification accuracy of deep convolutional neural networks (CNNs) using location-based cross validation. Here we discuss the results of varying network architectures, hyperparameters, loss, and activation functions;in conjunction with an analysis of training and testing set configuration. It is also in our interest to analyze these unique network setups extensively, rather than comparing merely classification accuracy. The approach is tested on a collection of SAS imagery.

关键词： Synthetic Aperture Sonar deep convolutional neural network deep Learning Choquet Fuzzy Integral Sugeno Fuzzy measure

来源：评论

学校读者我要写书评

暂无评论

deep convolutional neural network for Classifying Satellite Images with Heterogeneous Spatial Resolutions 21st

Deep Convolutional Neural Network for Classifying Satellite ...

引用

21st International Conference on Computational Science and Its Applications (ICCSA)

作者： Miranda, Mateus de Souza de Santiago Jr, Valdivino Alexandre Korting, Thales Sehn Leonardi, Rodrigo de Freitas Jr, Moises Laurence Inst Nacl Pesquisas Espaciais INPE Ave Astronautas 1758 BR-12227010 Sao Jose Dos Campos SP Brazil Agencia Espacial Brasileira BR-70610200 Brasilia DF Brazil Inst Fed Educ Ciencia & Tecnol Tocantins BR-77950000 Araguatins TO Brazil

ISBN: (纸本)9783030870072;9783030870065

deep Learning, and most notable deep neural networks, have largely driven Artificial Intelligence in the area of remote sensing, mainly image classification tasks. In this paper, we present an approach based on convolutional neural networks to classify Earth Observation satellite images as environmental preserved or non-preserved areas. One interesting feature of our approach is the fact that we used sensors with different spatial resolutions to assess the performance of a traditional network. We relied on images from the Tocantins Cerrado obtained by the Wide-Scan Multispectral and Panchromatic Camera of the CBERS-4A satellite, with a spatial resolution of 8m to create the training dataset. For testing, we set up a set of images of the Sentinel satellite, with a spatial resolution of 10m from Goias Cerrado. Results imply that convolutional neural networks are feasible and are a good alternative for classifying remote sensing areas even when dealing with images from various sensors, and also with different spatial resolutions, where the model used in this study obtained an accuracy of 0.87. This study demonstrates the flexibility of convolutional neural networks concerning the ability to generalize knowledge for classifying remote sensing images.

关键词： deep convolutional neural network Satellite image classification Remote sensing

来源：评论

学校读者我要写书评

暂无评论

deep convolutional neural network for Mammographic Density Segmentation

Deep Convolutional Neural Network for Mammographic Density S...

引用

Conference on Medical Imaging - Computer-Aided Diagnosis

作者： Wei, Jun Li, Songfeng Chan, Heang-Ping Helvie, Mark A. Roubidoux, Marilyn A. Lu, Yao Zhou, Chuan Hadjiiski, Lubomir Samala, Ravi K. Univ Michigan Dept Radiol Ann Arbor MI 48109 USA Sun Yat Sen Univ Sch Math Guangzhou Guangdong Peoples R China Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou Guangdong Peoples R China

ISBN: (数字)9781510616400

ISBN: (纸本)9781510616400

Breast density is one of the most significant factors for cancer risk. In this study, we proposed a supervised deep learning approach for automated estimation of percentage density (PD) on digital mammography (DM). The deep convolutional neural network (DCNN) was trained to estimate a probability map of breast density (PMD). PD was calculated as the ratio of the dense area to the breast area based on the probability of each pixel belonging to dense region or fatty region at a decision threshold of 0.5. The DCNN estimate was compared to a feature based statistical learning approach, in which gray level, texture and morphological features were extracted from each ROI and the least absolute shrinkage and selection operator (LASSO) was used to select and combine the useful features to generate the PMD. The reference PD of each image was provided by two experienced MQSA radiologists. With IRB approval, we retrospectively collected 347 DMs from patient files at our institution. The 10-fold cross-validation results showed a strong correlation r=0.96 between the DCNN estimation and interactive segmentation by radiologists while that of the feature-based statistical learning approach vs radiologists' segmentation had a correlation r=0.78. The difference between the segmentation by DCNN and by radiologists was significantly smaller than that between the feature-based learning approach and radiologists (p < 0.0001) by two-tailed paired t-test. This study demonstrated that the DCNN approach has the potential to replace radiologists' interactive thresholding in PD estimation on DMs.

关键词： Breast density digital Mammogram deep convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

deep convolutional neural network for Facial Expression Recognition 1

引用

9th International Conference on Image and Graphics (ICIG)

作者： Zhai, Yikui Liu, Jian Zeng, Junying Piuri, Vincenzo Scotti, Fabio Ying, Zilu Xu, Ying Gan, Junying Wuyi Univ Sch Elect & Informat Engineer Jiangmen 529020 Peoples R China Univ Milan Dept Comp Sci I-26013 Crema Italy

ISBN: (数字)9783319716077

ISBN: (纸本)9783319716077;9783319716060

In this paper, a deep convolutional neural network model and the method of transfer learning are used to solve the problems of facial expression recognition (FER). Firstly, the method of transfer learning was adopted and face recognition net was transferred into facial expression recognition net. And then, in order to enhance the classification ability of our proposed model, a modified Softmax loss function (Softmax-MSE) and a double activation layer (DAL) are proposed. We performed our experiment on enhanced SFEW2.0 dataset and FER2013 dataset. The experiments have achieved overall classification accuracy of 48.5% and 59.1% respectively, which achieved the state-of-art performance.

关键词： Facial expression recognition (FER) deep convolutional neural network Transfer learning

来源：评论

学校读者我要写书评

暂无评论

deep convolutional neural network for Recognizing the Images of Text Documents 8

Deep Convolutional Neural Network for Recognizing the Images...

引用

8th International Conference on Mathematics, Information Technologies, Education (MoMLeT and DS)

作者： Golovko, Vladimir Kroshchanka, Aliaksandr Mikhno, Egor Komar, Myroslav Sachenko, Anatoliy Bezobrazov, Sergei Shylinska, Inna Brest State Tech Univ Brest BELARUS Panstwowa Szkola Wyzsza Papieza Jana Pawla II Biala Podlaska Poland Ternopil Natl Econ Univ Temopil Ukraine Kazimierz Pulaski Univ Technol & Humanitie Radom Poland

A comparative analysis of various methods and architectures used to solve the problem of object detection is carried out. This allows so-called one-way neural networks architectures to provide high quality solutions to the problem. A neural network algorithm for labeling images in text documents is developed on the basis of image preprocessing that simplifies the localization of individual parts of a document and the subsequent recognition of localized blocks using a deep convolutional neural network. The resulting algorithm provides a high quality of localization and an acceptable level of subsequent classification.

关键词： Object Detection deep convolutional neural network Labeling Images Image Preprocessing Text Image

来源：评论

学校读者我要写书评

暂无评论

deep convolutional neural network Combined with Concatenated Spectrogram for Environmental Sound Classification 7

Deep Convolutional Neural Network Combined with Concatenated...

引用

7th IEEE International Conference on Computer Science and network Technology (ICCSNT)

作者： Chi, Zhejian Li, Ying Chen, Cheng Fuzhou Univ Coll Math & Comp Sci Fuzhou Peoples R China

ISBN: (纸本)9781728132990

Environmental sound classification (ESC) is an important but challenging issue. In this paper, we propose a new deep convolutional neural network, which uses concatenated spectrogram as input features, for ESC task. This concatenated spectrogram feature we adopt can increase the richness of features compared with single spectrogram. It is generated by concatenating two regular spectrograms, the Log-Mel spectrogram and the Log-Gammatone spectrogram. The network we propose uses convolutional blocks to extract and derive high-level feature images from concatenated spectrogram, and each block is composed of three convolutional layers and a pooling layer. In order to keep depth of the network and reduce numbers of parameters, we use filter with a small receptive field in each convolutional layer. Besides, we use the average pooling to keep more information. Our method was tested on ESC-50 and UrbanSound8K and achieved classification accuracy of 83.8% and 80.3%, respectively. The experimental results show that the proposed method is suitable for ESC task.

关键词： Concatenated spectrogram deep convolutional neural network Environmental sound classification

来源：评论

学校读者我要写书评

暂无评论

deep convolutional neural network Design Approach for 3D-Object Detection for Robotic Grasping

Deep Convolutional Neural Network Design Approach for 3D-Obj...

引用

作者： Sharma, Purvesh Texas State University – San Marcos

学位级别：硕士

Recognition technology has gained state-of-the-art performance with the dawn of deep convolutional neural network (DCNN), and with these achievements in computer vision, machine learning, and 3D-sensor, industries are near to start a new era of the automation. However, object detection for robotic grasping in varying environments, low illumination, occlusion, and partial images contributes to poor accuracy and slows the speed of detecting objects. In this thesis, an approach is presented to recognize an object in an industrial warehouse through a robotic vision to advance warehouse automation using a robot arm. A multimodal architecture is designed to be used as a base network/backbone network of Single Shot Detector (SSD) to address the warehouse’s challenge, such as partial images and low illumination. This architecture uses Red-Green-Blue (RGB) and Depth images as an input and provides a single output. Most of the researchers used Visual Geometry Group (VGG), Residual network (ResNet), and MobileNet for detection purposes, but in this thesis, a new DCNN architecture is designed to perform a specific task of grasping. Here, four different Red-Green-Blue-Depth (RGB-D) deep neural network architectures are designed and compared in their training, testing, and other statistical metrics for evaluation. The deep convolutional neural network (DCNN) development motive is to recognize the input object image obtained from the depth sensor cameras in warehouses. Four objects are mainly focused on this research: ‘Bowl,’ ‘School glue,’ ‘Dove bar,’ ‘Soda can.’ Furthermore, details of the designed model, its performance, and the results are discussed in this thesis.

关键词： deep convolutional neural network 3D object detection

来源：评论

学校读者我要写书评

暂无评论

Aquila coyote-tuned deep convolutional neural network for the classification of bare skinned images in websites

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2022年第10期13卷 3239-3254页

作者： Gupta, Jaya Pathak, Sunil Kumar, Gireesh Amity Univ Rajasthan Jaipur Rajasthan India JK Lakshmipat Univ Jaipur Rajasthan India

Pornographic websites become increasingly obdurate via disguising and misleading the under-aged people, which obstruct the development of a healthy and safe network environment. The conventional strategies of bare skin classification perform the detection process through a single feature of these sites, which would be unsuccessful to solve the more complicated and tedious situations. Hence, this research focuses on proposing a well-adapted port image classification model using an optimized deep convolutional neural network (deep CNN). The significance of this research relies on the proposed Aquila Coyote (AqCO) optimization algorithm, developed with the integration of Aquila hunters and the coyote hunters, which engages in tuning the hyper-parameters of the deep CNN classifier. Moreover, the significant features of the image are utilized by the classifier, which further boosts the classification accuracy of the proposed model. The analysis is done based on performance parameters, such as accuracy, sensitivity, and specificity in such a way to evaluate the efficiency of the proposed porn image classification model. The maximal accuracy of the proposed model is 95.91% for the B-Praneeth dataset, which is high as compared to the existing methods of porn image classification methods.

关键词： Pornographic websites Porn image deep convolutional neural network Hyper-parameters And optimization

来源：评论

学校读者我要写书评

暂无评论

Design an image-based sentiment analysis system using a deep convolutional neural network and hyperparameter optimization

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第25期83卷 66479-66498页

作者： Anilkumar, B. Devi, N. Lakshmi Kotagiri, Srividya Sowjanya, A. Mary GMR Inst Technol Dept Elect & Commun Engn Razam Andhra Pradesh India GMR Inst Technol Dept Comp Sci & Engn Razam Andhra Pradesh India Andhra Univ Coll Engn A Dept CS&SE Visakhapatnam Andhra Pradesh India

These days, sentiment analysis is a hot issue. The growth of sentiment analysis methods results from the exponential growth in data made possible by the emergence of social media networks. However, big data sentiment analysis with images is a challenging task. The most frequent obstacles with image-based sentiment analysis are noise, data scarcity, disappearing gradients, classification issues, and sentiment prediction. The system's performance is harmed, and sentiment prediction could produce poor outcomes due to distorted visuals and visual perception issues. This approach proposes the deep convolutional neural network with Hyper Parameter Optimization (DCNN-HPO) for correctly predicting sentiment analysis by optimizing the DCNN parameters. Moreover, image datasets are collected from the net source and trained in the system. All the images are pre-processed, and features are extracted using the VGG-16 network. Then, the extracted features are updated to the DCNN, and the weight parameters of the DCNN are optimized using the Krill Herd Optimization (KHO). Finally, perform sentiment analysis to classify positive, negative, and neutral sentiments from the input images. Thus, the designed model attained 98% accuracy, 99.12% sensitivity, and 0.2 s of execution time, which shows the efficiency of the developed model. Finally, the designed model accurately classifies the sentiment using input images.

关键词： deep convolutional neural network Hyper Parameter Optimization Image Based Sentiment Analysis Prediction and Krill Herd Optimization Social Media Data

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：