• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.670-684
• /
• 2024

3D Cross-Modal Retrieval (3DCMR) is a task that retrieves 3D objects regardless of modalities, such as images, meshes, and point clouds. One of the most prominent methods used for 3DCMR is the Cross-Modal Center Loss Function (CLF) which applies the conventional center loss strategy for 3D cross-modal search and retrieval. Since CLF is based on center loss, the center features in CLF are also susceptible to subtle changes in hyperparameters and external inferences. For instance, performance degradation is observed when the batch size is too small. Furthermore, the Mean Squared Error (MSE) used in CLF is unable to adapt to changes in batch size and is vulnerable to data variations that occur during actual inference due to the use of simple Euclidean distance between multi-modal features. To address the problems that arise from small batch training, we propose a Noisy Center Loss (NCL) method to estimate the optimal center features. In addition, we apply the simple Siamese representation learning method (SimSiam) during optimal center feature estimation to compare projected features, making the proposed method robust to changes in batch size and variations in data. As a result, the proposed approach demonstrates improved performance in ModelNet40 dataset compared to the conventional methods.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.2 s.308
• /
• pp.72-80
• /
• 2006

In this paper, we propose a new descriptor for 3D model retrieval based on shape information. The proposed method consists of two steps including ray casting method and spherical harmonic function, considering geometric properties of model. In the ray casting method, an adaptive sampling is performed for external shape information. By increasing shape information included in the descriptor, we improve the discriminating power of the proposed descriptor. The coefficients of spherical harmonic function are adaptively calculated, considering geometric frequency characteristics. This makes the descriptor more compact and concise without decreasing the retrieval performance. By combining two methods, we achieve more improved retrieval results.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.3
• /
• pp.33-41
• /
• 2007

Owing to the development of multimedia and communication technologies, multimedia data become a common feature of the information systems and are on the increase. This has led to the need of 3D shape retrieval systems that, given a query object, retrieve similar 3D objects. Therefore, shape descriptor required to describe a 3D object effectively and efficiently. In this paper, a new descriptor for 3D model retrieval based on shape information is proposed. The proposed descriptor utilizes the curvedness together with the shape index that provides local geometry information. The existing 3D Shape Spectrum Descriptor (3D SSD), which is defined as the histogram of shape index values, represents the characteristics of local shapes of the 3D surface. However, it does not properly represent the local shape characteristics, because many points with different curvedness may have the same shape index value. Therefore, we add a new feature that represents the degree of curvedness, thereby improving the discriminating power of the shape descriptor. We evaluate the performance of the proposed method, compared with the previous method. The experimental results have shown that the performance of retrieval has been improved by 23.6%.

• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.176-190
• /
• 2018

This paper presents a novel convolutional neural network based multi-feature fusion learning method for non-rigid 3D model retrieval, which can investigate the useful discriminative information of the heat kernel signature (HKS) descriptor and the wave kernel signature (WKS) descriptor. At first, we compute the 2D shape distributions of the two kinds of descriptors to represent the 3D model and use them as the input to the networks. Then we construct two convolutional neural networks for the HKS distribution and the WKS distribution separately, and use the multi-feature fusion layer to connect them. The fusion layer not only can exploit more discriminative characteristics of the two descriptors, but also can complement the correlated information between the two kinds of descriptors. Furthermore, to further improve the performance of the description ability, the cross-connected layer is built to combine the low-level features with high-level features. Extensive experiments have validated the effectiveness of the designed multi-feature fusion learning method.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.759-760
• /
• 2008

In this paper, We propose the feature-based 3D model Retrieval System. 3D models are represented as triangle meshes. A first simple feature vector can be calculated from hull. After looking for meshes intersected with the hull, we compute the curvature of meshes. These curvature are used as the model descriptor.

• Journal of Korea Multimedia Society
• /
• v.12 no.11
• /
• pp.1692-1700
• /
• 2009

This paper proposes the direction distribution of surface normal vectors as a feature descriptor of three-dimensional models. Proposed the feature descriptor handles rotation invariance using a principal component analysis(PCA) method, and performs mesh simplification to make it robust and nonsensitive against noise addition. Our method picks samples for the distribution of normal vectors to be proportional to the area of each polygon, applies weight to the normal vectors, and applies interpolation to enhance discrimination so that the information on the surface with less area may be less reflected on composing a feature descriptor. This research measures similarity between models with a L1-norm in the probability density histogram where the distances of feature descriptors are normalized. Experimental results have shown that the proposed method has improved the retrieval performance described in an average normalized modified retrieval rank(ANMRR) by about 17.2% and the retrieval performance described in a quantitative discrimination scale by 9.6%~17.5% as compared to the existing method.

• The KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.509-518
• /
• 2004

Recently there has been some efforts to add XML full-text retrievals and XML updates into new standardization of XML queries. XML full-text retrievals plays an important role in XML query languages. of like tables in relational model an XML document has complex and unstructured natures. We believe that when we try to get some information from unstructured XML documents a full-text retrieval query is much more convenient approach than a regular structured query XML update is another core function that an XML query have to have. In this paper we propose an inverted index to support XML updates and XML full-text queries in relational environment. Performance comparisons exhibit that our approach maintains a comparable size of inverted indexes and it supports many full-text retrieval functions very well. It also shows very stable retrieval performance especially for large size of XML documents. Foremost our approach handles XML updates efficiently by removing cascading effects.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.403-410
• /
• 2004

Recently, studies of image analysis, as the preprocessing stage for medical image analysis or image retrieval, are actively carried out. This paper intends to propose a way of utilizing color components for image retrieval. For image retrieval, it is based on color components, and for analysis of color, CLCM (Color Level Co-occurrence Matrix) and statistical techniques are used. CLCM proposed in this paper is to project color components on 3D space through geometric rotate transform and then, to interpret distribution that is made from the spatial relationship. CLCM is 2D histogram that is made in color model, which is created through geometric rotate transform of a color model. In order to analyze it, a statistical technique is used. Like CLCM, GLCM (Gray Level Co-occurrence Matrix)[1] and Invariant Moment [2,3] use 2D distribution chart, which use basic statistical techniques in order to interpret 2D data. However, even though GLCM and Invariant Moment are optimized in each domain, it is impossible to perfectly interpret irregular data available on the spatial coordinates. That is, GLCM and Invariant Moment use only the basic statistical techniques so reliability of the extracted features is low. In order to interpret the spatial relationship and weight of data, this study has used Principal Component Analysis [4,5] that is used in multivariate statistics. In order to increase accuracy of data, it has proposed a way to project color components on 3D space, to rotate it and then, to extract features of data from all angles.

• Journal of Broadcast Engineering
• /
• v.14 no.1
• /
• pp.81-84
• /
• 2009

This paper explores the possibility of describing objects from the change in the shape according to the change in viewpoint. Specifically, we sample the shapes from various viewpoints of a 3-D model, and apply dimension reduction by locally linear embedding. A low dimensional distribution of points are constructed, and characteristics of the object are described from this distribution. Also, we propose two 3-D retrieval methods by applying the iterative closest point algorithm, and by applying Fourier transform and measuring similarity by modified Housdorff distance, and present experimental results. The proposed method shows that the change of shape according to the change in viewpoint can describe the characteristics of an object.

• Journal of KIISE:Databases
• /
• v.29 no.2
• /
• pp.110-118
• /
• 2002

This paper presents a 3-D graphic database system based on XML that supports content-based retrievals of 3-D images, Most of graphics application systems are currently centered around the processing of 2-D images and research works on 3-D graphics are mainly concerned about the visualization aspects of 3-D image. They do not support the semantic modeling of 3-D objects and their spatial relations. In our data model, 3-D images are represented as compositions of 3-D graphic objects with associated spatial relations. Complex 3-D objects are mode]ed using a set of primitive 3-D objects rather than the lines and polygons that are found in traditional graphic systems. This model supports content-based retrievals of scenes containing a particular object or those satisfying certain spatial relations among the objects contained in them. 3-D images are stored in the database as XML documents using 3DGML DTD that are developed for modeling 3-D graphic data. Finally, this paper describes some examples of query executed in our Web-based prototype database system.