Multiresolution wavelet analysis of shape orientation for 3d shape retrieval

Liu, Zhenbao; Mitani, Jun; Fukui, Yukio; Nishihara, Seiichi

doi:10.1145/1460096.1460162

Cited by 11 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Wang et al [36] used a related view-based approach by projecting a number of uniformly sampled points along six directions to create six images to describe a 3D object. Liu et al [23] also generated six view planes around the bounding cube of a 3D object. However, their method further decomposed each view planes into several resolution and applied wavelet transforms to the extracted features from the view planes.…”

Section: Related Literaturementioning

confidence: 99%

3D object retrieval using salient views

Atmosukarto

Shapiro

2012

Int J Multimed Info Retr

View full text Add to dashboard Cite

This paper presents a method for selecting salient 2D views to describe 3D objects for the purpose of retrieval. The views are obtained by first identifying salient points via a learning approach that uses shape characteristics of the 3D points (Atmosukarto and Shapiro in International workshop on structural, syntactic, and statistical pattern recognition, 2008; Atmosukarto and Shapiro in ACM multimedia information retrieval, 2008). The salient views are selected by choosing views with multiple salient points on the silhouette of the object. Silhouette-based similarity measures from Chen et al. (Comput Graph Forum 22(3):223–232, 2003) are then used to calculate the similarity between two 3D objects. Retrieval experiments were performed on three datasets: the Heads dataset, the SHREC2008 dataset, and the Princeton dataset. Experimental results show that the retrieval results using the salient views are comparable to the existing light field descriptor method (Chen et al. in Comput Graph Forum 22(3):223–232, 2003), and our method achieves a 15-fold speedup in the feature extraction computation time.

show abstract

Section: Related Literaturementioning

confidence: 99%

3D object retrieval using salient views

Atmosukarto

Shapiro

2012

Int J Multimed Info Retr

View full text Add to dashboard Cite

show abstract

“…So the model group has 40086 vertices and 13790 triangles. We regard the model group as a whole, Firstly parameterization according to Section 3.1, and then perform orthogonal decomposition and reconstruction under the V-system according to equation (6). Fig.5 (a) is the model group; Fig.5 (b) is spectrum graph in three directions respectively, obviously, the larger spectrums are concentrated on low-frequency; Fig.5 (c) is the result of reconstruction using these spectrums.…”

Section: Journal Of Advanced Mechanical Design Systems and Manufactmentioning

confidence: 99%

Retrieval Method for 3D Object Group Based on V-system

Song

Dongxing

Wang

et al. 2012

JAMDSM

View full text Add to dashboard Cite

Based on the V-system, an orthogonal function system over triangular domain, we proposed a retrieval method for 3D model group consisting of several separate parts. The V-system is an efficient tool to precisely represent either continuous or separate geometric objects, which is its striking characteristic. The V-system can transform a 3D object to the frequency domain based on its triangular mesh, and generate related eigenvector which is invariant to rotation, translation, and scaling. With the V-system, we can successfully extend the orthogonal transformation methods widely used in 2D image retrieval to 3D model retrieval. Retrieval experimental results show that the proposed approach is practical and effective; and it has distinct advantage for model group retrieval. Comparing with the existed 3D model retrieval measures which can only be used to retrieve single model, this new approach can be used to retrieve a model group consisting of several separate parts, which is significant and has important application value in the reuse of model groups.

show abstract

“…The key idea behind this method is that it presents the signature of an object as a shape distribution sampled from a shape function that measures the global geometric properties of the object. (Liu et al, 2008a) utilized multiresolution wavelet analysis on shape orientation and the shape can be described by wavelet coefficients of each shape orientation function. (Liu et al, 2006) presented a novel 3D shape descriptor for effective shape matching and analysis that utilizes both local and global shape signatures.…”

Section: Previous Workmentioning

confidence: 99%

A 3D shape classifier with neural network supervision

Liu

Mitani

Fukui

et al. 2010

IJCAT

Self Cite

View full text Add to dashboard Cite

The task of 3D shape classification is to assign a set of unordered shapes into pre-tagged classes with class labels, and find the most suitable class for a newly given shape. In this paper, we present a 3D shape classifier approach based on supervision of the learning of point spatial distributions. In this classifier, we first extract the low-level features by characterizing the point spatial density distributions of 3D shapes, and train one feedforward neural network to learn these features by examples. The Konstanz shape database was chosen as the test database, and we grouped the classified objects into two sets, the training set and the test set, which each had an approximately equal number of shapes. We trained the network with the training set, and evaluated the accuracy rate on the test set. We also compared this classifier to k nearest neighbors classifier for 3D shapes. This approach can be used to classify 3D shapes and enhance the performance of the existent 3D shape retrieval methods.

show abstract

Multiresolution wavelet analysis of shape orientation for 3d shape retrieval

Cited by 11 publications

References 19 publications

3D object retrieval using salient views

3D object retrieval using salient views

Retrieval Method for 3D Object Group Based on V-system

A 3D shape classifier with neural network supervision

Contact Info

Product

Resources

About