oalib
Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
Deep Learning Representation using Autoencoder for 3D Shape Retrieval  [PDF]
Zhuotun Zhu,Xinggang Wang,Song Bai,Cong Yao,Xiang Bai
Computer Science , 2014,
Abstract: We study the problem of how to build a deep learning representation for 3D shape. Deep learning has shown to be very effective in variety of visual applications, such as image classification and object detection. However, it has not been successfully applied to 3D shape recognition. This is because 3D shape has complex structure in 3D space and there are limited number of 3D shapes for feature learning. To address these problems, we project 3D shapes into 2D space and use autoencoder for feature learning on the 2D images. High accuracy 3D shape retrieval performance is obtained by aggregating the features learned on 2D images. In addition, we show the proposed deep learning feature is complementary to conventional local image descriptors. By combing the global deep learning representation and the local descriptor representation, our method can obtain the state-of-the-art performance on 3D shape retrieval benchmarks.
A Survey of Recent View-based 3D Model Retrieval Methods  [PDF]
Qiong Liu
Computer Science , 2012,
Abstract: Extensive research efforts have been dedicated to 3D model retrieval in recent decades. Recently, view-based methods have attracted much research attention due to the high discriminative property of multi-views for 3D object representation. In this report, we summarize the view-based 3D model methods and provide the further research trends. This paper focuses on the scheme for matching between multiple views of 3D models and the application of bag-of-visual-words method in 3D model retrieval. For matching between multiple views, the many-to-many matching, probabilistic matching and semisupervised learning methods are introduced. For bag-of-visual-words application in 3D model retrieval, we first briefly review the bag-of-visual-words works on multimedia and computer vision tasks, where the visual dictionary has been detailed introduced. Then a series of 3D model retrieval methods by using bag-of-visual-words description are surveyed in this paper. At last, we summarize the further research content in view-based 3D model retrieval.
New Method for 3D Shape Retrieval  [PDF]
Abdelghni Lakehal,Omar El Beqqali
Computer Science , 2011, DOI: 10.5121/ijcsit.2011.3508
Abstract: The recent technological progress in acquisition, modeling and processing of 3D data leads to the proliferation of a large number of 3D objects databases. Consequently, the techniques used for content based 3D retrieval has become necessary. In this paper, we introduce a new method for 3D objects recognition and retrieval by using a set of binary images CLI (Characteristic level images). We propose a 3D indexing and search approach based on the similarity between characteristic level images using Hu moments for it indexing. To measure the similarity between 3D objects we compute the Hausdorff distance between a vectors descriptor. The performance of this new approach is evaluated at set of 3D object of well known database, is NTU (National Taiwan University) database.
NEW METHOD FOR 3D SHAPE RETRIEVAL  [PDF]
Abdelghni Lakehal,Omar El Beqqali
International Journal of Computer Science & Information Technology , 2011,
Abstract: The recent technological progress in acquisition, modeling and processing of 3D data leads to theproliferation of a large number of 3D objects databases. Consequently, the techniques used for contentbased 3D retrieval has become necessary. In this paper, we introduce a new method for 3D objectsrecognition and retrieval by using a set of binary images CLI (Characteristic level images). We propose a3D indexing and search approach based on the similarity between characteristic level images using Humoments for it indexing. To measure the similarity between 3D objects we compute the Hausdorffdistance between a vectors descriptor. The performance of this new approach is evaluated at set of 3Dobject of well known database, is NTU (National Taiwan University) database.
A New 3D Model Retrieval Method with Building Blocks  [PDF]
Mingquan Zhou,Qingsong Huo,Guohua Geng,Xiaojing Liu
International Journal of Computer Games Technology , 2009, DOI: 10.1155/2009/572030
Abstract: As the numbers of 3D models available grow in many application fields, there is an increasing need for a search method to help people find them. Unfortunately, traditional search techniques are not always effective for 3D data. In this paper, we describe a novel method of interactive 3D model retrieval with building blocks. First, by using a cube block as the baseblock in a 3D virtual space, we may construct the query model with human-computer interaction method. Then through retrieving the polygon model of the database generated by the voxel model, we may get retrieval results in real time. Experiments are conducted to evaluate the performance of the proposed method.
A Learning-Based Steganalytic Method against LSB Matching Steganography
Z. Xia,L. Yang,X. Sun,W. Liang
Radioengineering , 2011,
Abstract: This paper considers the detection of spatial domain least significant bit (LSB) matching steganography in gray images. Natural images hold some inherent properties, such as histogram, dependence between neighboring pixels, and dependence among pixels that are not adjacent to each other. These properties are likely to be disturbed by LSB matching. Firstly, histogram will become smoother after LSB matching. Secondly, the two kinds of dependence will be weakened by the message embedding. Accordingly, three features, which are respectively based on image histogram, neighborhood degree histogram and run-length histogram, are extracted at first. Then, support vector machine is utilized to learn and discriminate the difference of features between cover and stego images. Experimental results prove that the proposed method possesses reliable detection ability and outperforms the two previous state-of-the-art methods. Further more, the conclusions are drawn by analyzing the individual performance of three features and their fused feature.
Investigating the Bag-of-Words Method for 3D Shape Retrieval  [cached]
Xiaolan Li,Afzal Godil
EURASIP Journal on Advances in Signal Processing , 2010, DOI: 10.1155/2010/108130
Abstract: This paper investigates the capabilities of the Bag-of-Words (BWs) method in the 3D shape retrieval field. The contributions of this paper are (1) the 3D shape retrieval task is categorized from different points of view: specific versus generic, partial-to-global retrieval (PGR) versus global-to-global retrieval (GGR), and articulated versus nonarticulated (2) the spatial information, represented as concentric spheres, is integrated into the framework to improve the discriminative ability (3) the analysis of the experimental results on Purdue Engineering Benchmark (PEB) reveals that some properties of the BW approach make it perform better on the PGR task than the GGR task (4) the BW approach is evaluated on nonarticulated database PEB and articulated database McGill Shape Benchmark (MSB) and compared to other methods.
Investigating the Bag-of-Words Method for 3D Shape Retrieval  [cached]
Li Xiaolan,Godil Afzal
EURASIP Journal on Advances in Signal Processing , 2010,
Abstract: This paper investigates the capabilities of the Bag-of-Words (BWs) method in the 3D shape retrieval field. The contributions of this paper are (1) the 3D shape retrieval task is categorized from different points of view: specific versus generic, partial-to-global retrieval (PGR) versus global-to-global retrieval (GGR), and articulated versus nonarticulated (2) the spatial information, represented as concentric spheres, is integrated into the framework to improve the discriminative ability (3) the analysis of the experimental results on Purdue Engineering Benchmark (PEB) reveals that some properties of the BW approach make it perform better on the PGR task than the GGR task (4) the BW approach is evaluated on nonarticulated database PEB and articulated database McGill Shape Benchmark (MSB) and compared to other methods.
A Video Denoising Method with 3D Surfacelet Transform Based on Block matching and Grouping  [cached]
Peng Geng,He Jiang,Zhigang Zhang,Xiang Zheng
Journal of Computers , 2012, DOI: 10.4304/jcp.7.5.1130-1134
Abstract: This paper proposes a novel video denoising method combining block matching based on the E3SS and grouping these blok strategy, 3D Surfacelet transform. Firstly, we utilize the SAD standard and E3SS search algorithm which we proposed by searching all frames for blocks which are similar to the currently processed one. Secondly, the matched blocks are stacked together to form some new 3D Sub-video sequence and because of the similarity between them, the data in the video array exists high level of correlation. We apply the 3D surfacelet transform to them and effectively attenuate the noise by solid threshold shrinkage of the 3D transform coefficients. Finally, inversely transforming the coefficients and obtaining the denoising video. This algorithm is obviously better than other 3D method in the denoising effect and the PSNR is increased about 0.9 dB. In terms of visual quality, the proposed method can effectively preserve the video detail, and the trajectory of motion object is very smooth, which is especially adequate to process the video flames with acute movement and plenty of large area movement object and background movement.
3D Human Motion Recognition Method Based on Ensemble Learning in Subspace
基于子空间集成学习的3维人体运动识别

XIANG Jian,YE Lv,ZHU Hong-Li,
向坚
,叶绿,朱红丽

中国图象图形学报 , 2008,
Abstract: In this paper,a motion retrieval and recognition system is investigated from a ensemble learning model. In order to recognize and retrieve 3D motion data,first motion features are extracted from motion data. Due to the high dimensionality of motion's features,a generalized isomap nonlinear dimension reduction based on the estimation of underlying eigenfunction is used for training data of ensemble HMM learning. Then each action class is learned with one HMM. Since ensemble learning can effectively enhance supervised learning,ensembles of weak HMM learners are built. Experimental results show that our approaches are effective for information retrieval from large scale motion database.
Page 1 /100
Display every page Item


Home
Copyright © 2008-2017 Open Access Library. All rights reserved.