• Journal of Korea Multimedia Society
• /
• v.9 no.12
• /
• pp.1552-1559
• /
• 2006

In a web environment, similar information exists in many different places in diverse formats. Even duplicate information is stored in the various databases using different terminologies. Since most information serviced in the current World Wide Web however had been constructed before the advent of ontology, it is practically almost impossible to construct ontology for all those resources in the web. In this paper, we assume that most information in the web environment exist in the form of RDBMS, and propose a matching method between domain ontology and existing RDBMS tables for semantic retrieval. In the processing of extracting a local ontology, some problems such as losing domain in formation can occur since the correlation of domain ontology has not been considered at all. To prevent these problems, we propose an instance-based matching which uses relational information between RDBMS tables and relational information between classes in domain ontology. To verify the efficiency of the method proposed in this paper, several experiments are conducted using the digital heritage information currently serviced in the countrywide museums. Results show that the proposed method increase retrieval accuracy in terms of user relevance and satisfaction.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.9
• /
• pp.377-384
• /
• 2015

In this paper we propose a visualization tool for distortion-free time-series matching. Supporting distortion-free is a very important factor in time-series matching to get more accurate matching results. In this paper, we visualize the result of time-series matching, which removes various time-series distortions such as noise, offset translation, amplitude scaling, and linear trend by using moving average, normalization, linear detrending transformations, respectively. The proposed visualization tool works as a client-server model. The client sends a user-selected time-series, of which distortions are removed, to the server and visualizes the matching results. The server efficiently performs the distortion-free time-series matching on the multi-dimensional R*-tree index. By visualizing the matching result as five different charts, we can more easily and more intuitively understand the matching result.

• Proceedings of the IEEK Conference
• /
• 2000.11d
• /
• pp.263-266
• /
• 2000

We proposes a new fingerprint minutia matching algorithm which matches the fingerprint minutiae by using adaptive distance. In general, fingerprint is deformed by pressure and orientation when a user press his fingerprint to sensor. These nonlinear deformations change the distance between minutiae and reduce verification rate. We define the adaptive distance using ridge frequency. Adaptive distance normalizes the distance between minutiae and compensates for nonlinear deformation. Our algorithm can distinguish two different fingerprints better and is more robust. Experimental results show that the performance of the proposed algorithm is superior to using Euclidean distance.

• Journal of KIISE:Software and Applications
• /
• v.36 no.2
• /
• pp.144-152
• /
• 2009

To provide intelligent service in mobile environment, it needs to estimate user's intention or requirement, through analyzing context information of end-users such as preference or behavior patterns. In this paper, we infer context information from uncertain log stored in mobile device. And we propose the inference method of end-user's behavior to match context information with service, and the proposed method is based on context-tree. We adopt bayesian probabilistic method to infer uncertain context information effectively, and the context-tree is constructed to utilize non-numerical context which is hard to handled with mathematical method. And we verify utility of proposed method by appling the method to intelligent phone book service.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.2
• /
• pp.242-246
• /
• 2010

In this paper, we propose a quality assessment method of biometrics for estimating an authentication result in an user authentication system. The proposed quality assessment method is designed to compute a quality score called CIMR (Confidence Interval Matching Ratio) as a result by small-sample analysis like T-test. We use the C/MR-based quality assessment method for testing how to well draw a distinction between various biometrics in a multimodal biometric system. We also test a predictability for authentication results of obtained biometrics using the mean $\bar{X}$ and the variance $s^2$ in T-test-based CIMR. As a result, we achieved the maximum 88% accuracy for estimation of user authentication results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.3
• /
• pp.835-854
• /
• 2012

In this paper, we propose a novel positioning system for indoor navigation which helps a user navigate easily to desired destinations in an unfamiliar indoor environment using his mobile phone. The system requires only the user's mobile phone with its basic equipped sensors such as a camera and a compass. The system tracks user's positions and orientations using a vision-based approach that utilizes $360^{\circ}$ panoramic images captured in the environment. To improve the robustness of the vision-based method, we exploit a digital compass that is widely installed on modern mobile phones. This hybrid solution outperforms existing mobile phone positioning methods by reducing the error of position estimation to around 0.7 meters. In addition, to enable the proposed system working independently on mobile phone without the requirement of additional hardware or external infrastructure, we employ a modified version of a fast and robust feature matching scheme using Histogrammed Intensity Patch. The experiments show that the proposed positioning system achieves good performance while running on a mobile phone with a responding time of around 1 second.

• Journal of Digital Contents Society
• /
• v.5 no.4
• /
• pp.269-274
• /
• 2004

The field based morping requires the user to set most of the control lines manually which require much time and skill to get satisfactory results. This tjesis proposes a method to acquire semi-automation of image morphing through first acquiring shape information from the source image and the target image, than after the user manually designates the least amount of a pair of feature points, these are used as standards for polygon based vertex to set the appropriate control line to the source image and target image, and then using the ratio of control line lengths and space. Using the proposed method the user can reduce the time setting the control line and unskilled persons can get natural image morphing results while desingnating the least amount of control line.

• Journal of Korea Multimedia Society
• /
• v.18 no.4
• /
• pp.557-564
• /
• 2015

There are many prior studies for more natural Human-Computer Interaction. Until now, the efforts is continued in order to recognize motions in various directions. In this paper, we suggest a user-specific recognition by hit detection method using Kinect camera and human proportion. This algorithm extracts the user-specific valid recognition rage after recognizing the user's body initially. And it corrects the difference in horizontal position between the user and Kinect, so that we can estimate a action of user by matching cursor to target using only one frame. Ensure that efficient hand recognition in the game to take advantage of this method of suggestion.

• Journal of the Korean Society for information Management
• /
• v.29 no.4
• /
• pp.101-121
• /
• 2012

Since IR systems which adopt only Boolean IR model can not provide ranked search result, users have to conduct time-consuming checking process for huge result sets one by one. This study proposes a method to provide search results ranked by using coupling information between tags instead of index weight information in Boolean IR model. Because document queries are used instead of general user queries in the proposed method, key tags used as queries in a relevant document are extracted. A variety of groups of Boolean queries based on tag couplings are created in the process of extracting queries. Ranked search result can be extracted through the process of matching conducted with differential information among the query groups and tag significance information. To prove the usability of the proposed method, the experiment was conducted to find research trend analysis information on selected research information. Aslo, the service based on the proposed methods was provided to get user feedback for a year. The result showed high user satisfaction.

• ETRI Journal
• /
• v.33 no.4
• /
• pp.589-599
• /
• 2011

This paper presents an image description and matching scheme using synthetic features for a recommendation service. The recommendation service is an example of smart search because it offers something before a user's request. In the proposed extraction scheme, an image is described by synthesized spatial and statistical features. The spatial feature is designed to increase the discriminability by reflecting delicate variations. The statistical feature is designed to increase the robustness by absorbing small variations. For extracting spatial features, we partition the image into concentric circles and extract four characteristics using a spatial relation. To extract statistical features, we adapt three transforms into the image and compose a 3D histogram as the final statistical feature. The matching schemes are designed hierarchically using the proposed spatial and statistical features. The result shows that each feature is better than the compared algorithms that use spatial or statistical features. Additionally, if we adapt the proposed whole extraction and matching scheme, the overall performance will become 98.44% in terms of the correct search ratio.