检索结果-内蒙古大学图书馆

9th International Conference on Intelligent Systems (IS)

作者： Ioannakis, George Arnaoutoglou, Fotis Koutsoudis, Anestis Pavlidis, George Chamzas, Christodoulos Democritus Univ Thrace Univ Campus Kimmeria GR-67100 Xanthi Greece Athena Res Ctr Univ Campus Kimmeria GR-67100 Xanthi Greece

ISBN: (纸本)9781538670972

Exploiting 2d-manifold slicing and parameterisation techniques in order to manage a 31) model as a 21) representation is an active research field, that enables the application of a wide range of image processing and analysis techniques. In this work, we propose a method to represent a 3d model's surface on a 2d regular grid and encode its kl curvature, thus producing a new 3d geometry feature, the CurvMaps, that may be used for 3d model classification. The feature creating transformation relies on the identification of a 3d model's geometrical "extrema", the computation of id principal curvature and its encoding into a 2d regular grid. The applicability of CurvMaps in 3d model classification is being discussed through the experimentation with a number of classical methods.

关键词： 3d model feature 3d image feature 3d parametrisation slicing 3d model classification machine learning CNN

来源：评论

学校读者我要写书评

暂无评论

3d model classification via Principal Thickness Images

引用

COMPUTER-AIdEd dESIGN 2016年 78卷 199-208页

作者： Shu, Zhenyu Xin, Shiqing Xu, Huixia Kavan, Ladislav Wang, Pengfei Liu, Ligang Zhejiang Univ Ningbo Inst Technol Sch Informat Sci & Engn Ningbo 315100 Zhejiang Peoples R China Ningbo Univ Sch Informat Sci & Engn Ningbo 315211 Zhejiang Peoples R China Zhejiang Wanli Univ Inst Math Ningbo 315100 Zhejiang Peoples R China Univ Utah Sch Comp Salt Lake City UT 84112 USA Univ Sci & Technol China Sch Math Sci Graph & Geometr Comp Lab Hefei 230026 Anhui Peoples R China

With the innovation in 3d modeling software, more and more 3d models are becoming available in recent decades. To facilitate efficient retrieval and search of large 3d model databases, an effective shape classification algorithm is badly in need. In this paper, we propose a new feature descriptor named Principal Thickness Images (PTI) that encodes the boundary surface and the voxelized constituents of a 3d shape into three gray-scale images. With the support of PTI, we extend the kernel sparse representation based classification from 2d case to non-rigid 3d models. Our classification algorithm inherits the robustness of kernel sparse representation and is able to achieve a high success rate and strong reliability on non-rigid models from the SHREC'11 non-rigid 3d models dataset. Numerous tests demonstrate superior performance of the proposed method over previous 3d shape classification approaches. (C) 2016 Published by Elsevier Ltd.

关键词： Non-rigid 3d model 3d model classification Principal Thickness Images Kernel sparse representation

来源：评论

学校读者我要写书评

暂无评论

3d model classification and Recognition Method Based on Tensor Principal Component Analysis 8

3D Model Classification and Recognition Method Based on Tens...

引用

8th International Symposium on Computational Intelligence and design (ISCId)

作者： Wang, Xinying Yue, Yuanyang Changchun Univ Technol Coll Comp Sci & Engn Changchun Peoples R China

ISBN: (纸本)9781467395878

This paper propose a 3d model classification and recognition method based on tensor principal component analysis. Firstly, the 3d model is transformed into 2d view and expressed in tensor, and then feature vector from multiple angles of tensor is extracted. On the basis of multi-linear principal component analysis and linear discriminate analysis, we present a method for merged weighted multi-linear principal component analysis with weighted linear discriminate analysis (WMPCA + WLdA). This method is not only can save spatial correlation of the projected view, but also can improve feature recognition of the 3d model through using class label information and features weight. Experiments on Princeton Shape Benchmark has shown that the method is superior to the conventional MPCA, MPCA + LdA, WMPCA + LdA and other methods on classification results of 3d model.

关键词： tensor multi-linear principal component analysis linear discriminate analysis 3d model classification

来源：评论

学校读者我要写书评

暂无评论

A powerful 3d model classification mechanism based on fusing multi-graph

引用

NEUROCOMPUTING 2015年 168卷 761-769页

作者： Leng, Biao du, Changchun Guo, Shuang Zhang, Xiangyang Xiong, Zhang Beihang Univ Sch Comp Sci & Engn Beijing 100191 Peoples R China

Recently, integrating several feature descriptors to be a powerful one has become a hot issue in the field of 3d object understanding. The fusing mechanism is so crucial that can significantly affect the performance of 3d model classification. In this paper, a powerful model for 3d model classification, which can novelly integrate several graphs, is proposed. This mechanism is based on graph fusion and modifies each graph's weight in a boost manner. Each graph's weight in the fusion graph can be dynamically calculated according to its performance. Finally, a fusion graph is acquired to 3d model classification. We conduct the experiments on the publicly available 3d model databases: Princeton shape benchmark (PSB) and SHREC'09, and the experimental results demonstrate the powerful performance of the proposed method. (C) 2015 Elsevier B.V. All rights reserved.

关键词： 3d model classification Graph fusion Boost modified

来源：评论

学校读者我要写书评

暂无评论

3d model classification based on nonparametric discriminant analysis with kernels

引用

NEURAL COMPUTING & APPLICATIONS 2013年第3-4期22卷 771-781页

作者： Li, Jun-Bao Sun, Wen-He Wang, Yun-Heng Tang, Lin-Lin Harbin Inst Technol Dept Automat Test & Control Harbin 150006 Peoples R China Harbin Univ Commerce Sch Comp & Informat Engn Harbin Peoples R China Heilongjiang Inst Sci & Technol Coll Elect & Informat Engn Harbin 150027 Heilongjiang Peoples R China Shenzhen Grad Sch Sch Comp Sci & Technol Harbin Inst Technol Shenzhen Peoples R China

3d model classification has many applications in CAd, 3d object retrieval, and so on. The description of 3d model is crucial but difficult, which leads to the difficulty of classification. The traditional classifier has its limitation in classification of 3d model description. In this paper, we present 3d model classification-based nonparametric discriminant analysis with kernels combined with geometry projection-based histogram model for invariable feature extraction. Firstly, we present nonparametric discriminant analysis with kernels, and secondly, we proposed the invariable feature extraction method with geometry projection-based histogram model. Thirdly, we present the framework of 3d model classification using the proposed nonparametric discriminant analysis with kernels and geometry projection-based histogram model. Finally, we testify the feasibility of the proposed algorithm and performance on 3d model classification. The experimental results show that the proposed scheme is feasible and effective on 3d model classification on the public datasets.

关键词： 3d model classification Feature extraction of 3d model Nonparametric discriminant analysis Kernel method

来源：评论

学校读者我要写书评

暂无评论

Anthropometric salient points and convolutional neural network (CNN) for 3d human body classification

引用

MULTIMEdIA TOOLS ANd APPLICATIONS 2022年第8期81卷 10497-10527页

作者： Basu, Semanti Li, Chenxi Cohen, Fernand Drexel Univ Dept Elect & Comp Engn Philadelphia PA 19104 USA

In this paper, we introduce a 3d body shape biometric for recognizing a person as one of C possible individuals stored in a database in 3d free form (scatter of 3d data points) using a couple of canonical images (front and side) taken of that individual. The first step is to reconstruct the full body 3d shape model of the individual based on their frontal and profile silhouette images. This is done by using a 3d generic model that gets morphed in accordance with the canonical images of the individual. Starting with a small set of anthropometric interconnected ordered intrinsic control points residing on the silhouette boundary of the projections of the generic model onto the frontal and profile image spaces, corresponding control points on two canonical images of the person are automatically found. This imports equivalent saliency between the two sets. The positions of these control points on the canonical images are attained using deep convolutional neural networks (CNNs) that have been trained offline on a set of images of different individuals. Further equivalent saliencies between the projected points from the generic model and the canonical images are established through loop-subdivision. To personalize the generic model, points on the generic model are morphed to be consistent with their equivalent points on the canonical images. The 3d reconstruction yields sub-resolution errors when tested on the CAESAR data set with 700 different individuals. classification based on the error between salient points with identical anthropometric meaning residing on nested sets of boundaries in the frontal and side projections, achieves an accuracy of 96%. This is to be compared to an accuracy of 72% when using KNN nearest distance point classification between test and base models.

关键词： 3d model classification CNN 3d reconstruction Landmark detection

来源：评论

学校读者我要写书评

暂无评论

View-aligned pixel-level feature aggregation for 3d shape classification

引用

COMPUTER VISION ANd IMAGE UNdERSTANdING 2024年 248卷

作者： Xu, Yong Pan, Shaohui Xu, Ruotao Ling, Haibin South China Univ Technol Sch Comp Sci & Engn Guangzhou 510000 Peoples R China PaZhou Lab Guangzhou Guangzhou 518000 Peoples R China Guangdong Prov Key Lab Multimodal Big Data Intelli Guangzhou 510000 Peoples R China South China Univ Technol Inst Super Robot Guangzhou 510000 Peoples R China SUNY Stony Brook Dept Comp Sci Stony Brook NY 11794 USA

Multi-view 3d shape classification, which identifies a 3d shape based on its 2d views rendered from different viewpoints, has emerged as a promising method of shape understanding. A key building block in these methods is cross-view feature aggregation. However, existing methods dominantly follow the "extract-thenaggregate"pipeline for view-level global feature aggregation, leaving cross-view pixel-level feature interaction under-explored. To tackle this issue, we develop a "fuse-while-extract'' pipeline, with a novel View-aligned Pixel-level Fusion (VPF) module to fuse cross-view pixel-level features originating from the same 3d part. We first reconstruct the 3d coordinate of each feature via the rasterization results, then match and fuse the features via spatial neighbor searching. Incorporating the proposed VPF module with ResNet18 backbone, we build a novel view-aligned multi-view network, which conducts feature extraction and cross-view fusion alternatively. Extensive experiments have demonstrated the effectiveness of the VPF module as well as the excellent performance of the proposed network.

关键词： Multi-view recognition 3d model classification Pixel-wise fusion

来源：评论

学校读者我要写书评

暂无评论

An improved memory networks based product model classification method

引用

INTERNATIONAL JOURNAL OF COMPUTER INTEGRATEd MANUFACTURING 2021年第3期34卷 293-306页

作者： Jian, Chengfeng Liang, Lingming Qiu, Keyi Zhang, Meiyu Zhejiang Univ Technol Comp Sci & Technol Coll Hangzhou Peoples R China

Existing CAd model classification methods are usually performed by extracting the geometric and topological information of the models. This is not suitable for the classification of model-based definition (MBd) models because of the lack of non-geometric semantic information. They cannot solve the problem, as the geometry and topology are similar but the product manufacturing information (PMI) is completely different. Firstly, this paper proposed a multi-granularity classification model based on MBd attribute adjacency graph (MAAG). And then an improved Long Short-Term Memory (LSTM) neural network with a new loss function and adaptive training times is put forward. This neural network model is trained to achieve fast and accurate classification of the MBd models. Finally, the experimental results show that the proposed method not only improves the accuracy of classification, but also effectively reduces the training time cost of the model.

关键词： CAd step model-based definition 3d model classification

来源：评论

学校读者我要写书评

暂无评论

Panorama based on multi-channel-attention CNN for 3d model recognition

引用

MULTIMEdIA SYSTEMS 2019年第6期25卷 655-662页

作者： Nie, Weizhi Wang, Kun Liang, Qi He, Roubing Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China

With the development of 3d model reconstruction, manufacturing, and 3d model vision technologies, 3d model recognition has attracted much attention recently. To handle the 3d model recognition problem, in this paper, we propose a panorama based on multi-channel-attention (MCA) CNN network for the representation of the 3d model. The proposed method is composed of three parts: extracting views, transform function learning, and generating 3d model descriptor. Concretely, we first extract the 2d panoramic views for each 3d model, and we use the multi-channel-attention neural network to extract the descriptor for each 3d model. Here, the attention model is used to find the unequal weights of each panorama view to generate the more robust 3d model descriptor. Finally, The fusion feature is used to handle the 3d model classification and retrieval problem. The popular data sets modelNet and ShapeNet are used to demonstrate the performance of our approach. The experiments also demonstrate the superiority of our proposed method over the state-of-art methods.

关键词： Panorama view 3d model retrieval 3d model classification Multi-channel CNN Attention

来源：评论

学校读者我要写书评

暂无评论

Multi-view Fusion with deep Learning for 3d Shape classification 6

Multi-view Fusion with Deep Learning for 3D Shape Classifica...

引用

International Conference on Audio, Language and Image Processing (ICALIP)

作者： Huang, Xiang Wang, Mantao Zhang, dejun Zhu, Yu Zou, Lu Sun, Jun Han, Fei He, Linchao Sichuan Agr Univ Coll Informat & Engn Yaan Peoples R China

ISBN: (纸本)9781538651957

3d model retrieval is all along a difficult and hotspot in computer vision. Recently, the view-based methods make use of the advanced convolutional neural networks which achieve excellent results. However, the structural information of the 3d model was destroyed by the projection and the relevance of multiple perspectives was not considered. In order to resolve this problem, this manuscript analyzes the process of human observation of 3d models and imitates the process of human recognition of 3d models through a combination of convolutional neural networks and recurrent neural networks. Our approach can convert the relevance between perspectives into the dependency relationship between structured recurrent neural networks and restore the structural information of the 3d model. We conducted experiments on the modelNet40 database, it shows strong performance on par or even better than state-of-the-art results.

关键词： CNN RNN 3d model classification image modelNet40

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：