• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.12
• /
• pp.5058-5072
• /
• 2015

Quaternions have been commonly employed in color image processing, but when the existing pure quaternion representation for color images is used in perceptual hashing, it would degrade the robustness performance since it is sensitive to image manipulations. To improve the robustness in color image perceptual hashing, in this paper a full quaternion representation for color images is proposed by introducing the local image luminance variances. Based on this new representation, a novel Full Quaternion Discrete Cosine Transform (FQDCT)-based hashing is proposed, in which the Quaternion Discrete Cosine Transform (QDCT) is applied to the pseudo-randomly selected regions of the novel full quaternion image to construct two feature matrices. A new hash value in binary is generated from these two matrices. Our experimental results have validated the robustness improvement brought by the proposed full quaternion representation and demonstrated that better performance can be achieved in the proposed FQDCT-based hashing than that in other notable quaternion-based hashing schemes in terms of robustness and discriminability.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.6
• /
• pp.39-46
• /
• 2004

One of the significant issues in cluster analysis is to identify a proper number of clusters hidden under given data. In this paper we propose a novel approach to systematically determine the number of clusters based on Input Representation Coverage (IRC), which is newly defined as a quantified value of how well original input data in Gaussian feature space can be captured with a certain number of clusters. Furthermore, its usability and applicability is also investigated via experiments with synthetic data. Our experiment results show that the proposed approach is quite useful in approximately finding the real number of clusters implicitly contained in the data.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.30 no.1 s.244
• /
• pp.8-15
• /
• 2006

A Sparse Point Representation(SPR) based on interpolation wavelets is presented. The SPR is implemented for the purpose of CFD data compression. Unlike conventional wavelet transformation, the SPR relieves computing workload in the similar fashion of lifting scheme that includes splitting and prediction procedures in sequence. However, SPR skips update procedure that is major part of lifting scheme. Data compression can be achieved by proper thresholding method. The advantage of the SPR method is that, by keeping even point physical values, low frequency filtering procedure is omitted and its related unphysical thresholing mechanism can be avoided in reconstruction process. Extra singular feature detection algorithm is implemented for preserving singular features such as shock and vortices. Several numerical tests show the adequacy of SPR for the CFD data. It is also shown that it can be easily extended to nonlinear adaptive wavelets for enhanced feature capturing.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.261-276
• /
• 2020

Digital contents services are one of the topics that have been intensively studied in the media industry, where various semantic and ontology techniques are applied. However, query execution for ontology data is still inefficient, lack of sufficient extensible definitions for node relationships, and there is no specific semantic method fit for media data representation. In order to make the machine understand digital contents (DCs) data well, we analyze DCs data, including static data and dynamic data, and use ontology to specify and classify objects and the events of the particular objects. Then the formal representation method is proposed which not only redefines DCs data based on the technology of OWL/RDF, but is also combined with media segmentation methods. At the same time, to speed up the access mechanism of DCs data stored under the persistent database, an ontology-based DCs query solution is proposed, which uses the specified distance vector associated to a surveillance of semantic label (annotation) to detect and track a moving or static object.

• Korean Journal of Computational Design and Engineering
• /
• v.1 no.1
• /
• pp.20-32
• /
• 1996

The boundary evaluation technique for Boolean operation on non-manifold models which is regarded as the most popular and powerful method to create and modify 3-D CAD models has been developed. This technique adopted the concept of Merge and Selection in which the CSG tree for Boolean operation can be edited quickly and easily. In this method, the merged set which contains complete information about primitive models involved is created by merging primitives one by one, then the alive entities are selected following the given CSG tree. This technique can support the hybrid representation of B-rep(Boundary Representation) and CSG(Constructive Solid Geometry) tree in a unified non-manifold model data structure, and expected to be used as a basic method for many modeling problems such as data representation of form features, and the interference between them, and data representation of conceptual models in design process, etc.

• Korean Journal of Computational Design and Engineering
• /
• v.7 no.4
• /
• pp.262-268
• /
• 2002

Octree representation has the advantage of being able to represent complex shapes approximately through the repetition of simple primitive shapes. Due to this reason, octree representation together with VRML(Virtual Reality Modelling Language) is usually used for approximating 3D shapes. Since the data size of octree representation increases rapidly as 3D shape to be represented is more and more complicated, its transmission time also increase. In this paper, provided is the new octree representation and encoding/decoding scheme for real-time transmission through the internet in order to visualize 3D geometric data of large size approximately.

• Journal of Korea Game Society
• /
• v.17 no.5
• /
• pp.103-112
• /
• 2017

In recent years, expansions and advances of the Internet of Things (IoTs) in a distributed MMOGs (massively multiplayer online games) architecture have resulted in massive growth of data in terms of server workloads. We propose a combing Sparse Autoencoder and one of platforms in MMOGs, ProGReGA. In the process of Sparse Autoencoder, data representation with respect to enhancing the feature is excluded from this set of data. In the process of load balance, the graceful degradation of ProGReGA can exploit the most relevant and less redundant feature of the data representation. We find out that the proposed algorithm have become more stable.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.118-121
• /
• 1998

Standardized representations and data codes are crucial for the exchange of information between systems, organizations, and people in the telecommunications operations area. ITU-T M.1400 recommends a unified representation for the international network routes which includes such location data elements as Town A, Suffix Code which was designed for the representation of domestic network locations to meet the ITU-T recommendation. This paper suggests an expanded building ID code for the representation of the international network locations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5427-5445
• /
• 2019

While deep neural networks have achieved remarkable performance in representation learning, a huge amount of labeled training data are usually required by supervised deep models such as convolutional neural networks. In this paper, we propose a new representation learning method, namely generative adversarial networks (GAN) based bagging deep convolutional autoencoders (GAN-BDCAE), which can map data to diverse hierarchical representations in an unsupervised fashion. To boost the size of training data, to train deep model and to aggregate diverse learning machines are the three principal avenues towards increasing the capabilities of representation learning of neural networks. We focus on combining those three techniques. To this aim, we adopt GAN for realistic unlabeled sample generation and bagging deep convolutional autoencoders (BDCAE) for robust feature learning. The proposed method improves the discriminative ability of learned feature embedding for solving subsequent pattern recognition problems. We evaluate our approach on three standard benchmarks and demonstrate the superiority of the proposed method compared to traditional unsupervised learning methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.5
• /
• pp.3000-3005
• /
• 2015

Reliable monitoring and diagnosis of industrial processes is quite important for in terms of quality and safety. The goal of fault diagnosis is to find process variables responsible for causing specific abnormalities of the process. This work presents a classification-based diagnostic scheme based on nonlinear representation of process data. The use of a nonlinear kernel technique is able to reduce the size of the data considered and provides efficient and reliable representation of the measurement data. As a filtering stage a preprocessing is performed to eliminate unwanted parts of the data with enhanced performance. The case study of an industrial batch process has shown that the performance of the scheme outperformed other methods. In addition, the use of a nonlinear representation technique and filtering improved the diagnosis performance in the case study.