• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.153-156
• /
• 2003

This paper proposes a video tracking method for a deformable moving object using an active contour model. In order to decide the convergent directions of the contour points automatically, a new energy function based on a frame difference map and an updating rules of the frame difference map are presented. Experimental results on a set of synthetic and real image sequences showed that the proposed method can fully track a speedy deformable object while extracting the boundary of the object exactly in every frame.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.385-386
• /
• 2020

In this paper, we propose a collaborative filtering recommendation algorithm based on the LDA2Vec topic model. By extracting and analyzing the article's content, calculate their semantic similarity then combine the traditional collaborative filtering algorithm to recommend. This approach may promote the system's recommend accuracy.

• Journal of Communications and Networks
• /
• v.16 no.1
• /
• pp.92-97
• /
• 2014

A novel method for extracting frequency slippage signal from radar full pulse sequence is presented. For the radar full pulse sequence received by radar interception receiver, radio frequency (RF) and time of arrival (TOA) of all pulses constitute a two-dimensional information sequence. In a complex and intensive electromagnetic environment, the TOA of pulses is distributed unevenly, randomly, and in a nonstationary manner, preventing existing methods from directly analyzing such time series and effectively extracting certain signal features. This work applies Gaussian noise insertion and structure function to the TOA-RF information sequence respectively such that the equalization of time intervals and correlation processing are accomplished. The components with different frequencies in structure function series are separated using empirical mode decomposition. Additionally, a chaos detection model based on the Duffing equation is introduced to determine the useful component and extract the changing features of RF. Experimental results indicate that the proposed methodology can successfully extract the slippage signal effectively in the case that multiple radar pulse sequences overlap.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.177-180
• /
• 2008

Many researches have been tried to extract building models and created a 3D cyber city from LiDAR data. In this paper, the approach of extracting complex building by using airborne LiDAR data combined with airborne orthoimagery has been performed. The pseudo-building elevations were derived from modified discrete return LiDAR data. Based on information property of the pseudo-height, building features could be extracted. The results of this study indicated the improvement of building extraction.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.10
• /
• pp.87-94
• /
• 2018

This paper proposes a method of detecting the license plates of vehicles. The proposed technology applicable to different formats of license plates detects the numbers by standardizing the images at edge points. Specifically, in accordance with the format of each license plate, the technology captures the image in the character segment, and compares it against the sample model to derive their similarity and identify the numbers. Characters with high similarities are used to form a group of candidates and to extract the final characters. Analyzing the experimental results found the similarity of the extracted characters exceeded 90%, whereas that of less identifiable numbers was markedly lower. Still, the accuracy of the extracted characters with the highest similarity was over 80%. The proposed technology is applicable to extracting the character patterns of certain formats in diverse and useful ways.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3498-3512
• /
• 2021

This article describes how events that make up text stories can be represented and extracted. We also address the results from our simple experiment on extracting and clustering events in terms of emotions, under the assumption that different emotional events can be associated with the classified clusters. Each emotion cluster is based on Plutchik's eight basic emotion model, and the attributes of the NLTK-VADER are used for the classification criterion. While comparisons of the results with human raters show less accuracy for certain emotion types, emotion types such as joy and sadness show relatively high accuracy. The evaluation results with NRC Word Emotion Association Lexicon (aka EmoLex) show high accuracy values (more than 90% accuracy in anger, disgust, fear, and surprise), though precision and recall values are relatively low.

• Korean Journal of Computational Design and Engineering
• /
• v.2 no.1
• /
• pp.11-18
• /
• 1997

Scientific volume visualization addresses the representation, manipulation, and rendering of volumetric data sets, providing mechanisms for looking closely into structures and understanding their complexity and dynamics. In the past several years, a tremendous amount of research and development has been directed toward algorithms and data modeling methods for a scientific data visualization. But there has been very little work on developing a mathematical volume model that feeds this visualization. Especially, in flow visualization, the volume model has long been required as a guidance to display the very large amounts of data resulting from numerical simulations. In this paper, we focus on the mathematical representation of volumetric data sets and the method of extracting meaningful information from the derived volume model. For this purpose, a B-spline volume is extended to a high dimensional trivariate model which is called as a flow visualization model in this paper. Two three-dimensional examples are presented to demonstrate the capabilities of this model.

• Journal of the Ergonomics Society of Korea
• /
• v.32 no.2
• /
• pp.179-187
• /
• 2013

Objective: The purpose of this study is to extract GOMS manual operator, except for an experiment with participants. Background: The GOMS model has advantage of rapid modeling which is suitable for the environment of technology development which has a short life cycle products with a fast pace. The GOMS model was originally designed for desktop environment so that it is not adequate for implementing into the latest HCI environment such as small touch screen device. Therefore, this research proposed GOMS manual operator extraction methodology which is excluded experimental method. And flick Gesture was selected to explain application of proposed methodology to extract new operator. Method: Divide into start to final step of hand gesture needed to extract as an operator through gesture task analysis. Then apply the original GOMS operator to each similar step of gesture and modify the operator for implementation stage based on existing Fitts' law research. Steps that are required to move are modified based on the Fitts' law developed in touch screen device. Finally, new operator can be derived from using these stages and a validation experiment, performed to verify the validity of new operator and methodology by comparing human performance. Results: The average movement times of the participants' performance and the operator which is extracted in case study are not different significantly. Also the average of movement times of each type of view study is not different significantly. Conclusion: In conclusion, the result of the proposed methodology for extracting new operator is similar to the result of the experiment with their participants. Furthermore the GOMS model included the operator by the proposed methodology in this research could be applied successfully to predict the user's performance. Application: Using this methodology could be applied to develop new finger gesture in the touch screen. Also this proposed methodology could be applied to evaluate the usability of certain system rapidly including the new finger gesture performance.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.2
• /
• pp.171-176
• /
• 2015

We present a speaker verification method by extracting i-vectors based on dominant state information of Hidden Markov Model (HMM) - Universal Background Model (UBM). Ergodic HMM is used for estimating UBM so that various characteristic of individual speaker can be effectively classified. Unlike Gaussian Mixture Model(GMM)-UBM based speaker verification system, the proposed system obtains i-vectors corresponding to each HMM state. Among them, the i-vector for feature is selected by extracting it from the specific state containing dominant state information. Relevant experiments are conducted for validating the proposed system performance using the National Institute of Standards and Technology (NIST) 2008 Speaker Recognition Evaluation (SRE) database. As a result, 12 % improvement is attained in terms of equal error rate.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2005.05a
• /
• pp.34-39
• /
• 2005

The progress of silicon technology enables to implement a highly complex digital system on a given chip area. However, even the modern design environment is not so efficient to catch up with the progress of process technology. Design reuse is a promising approach to designing such a complex system in an efficient way. However, the rigidness and inflexibility of a model has been an obstacle to design reuse. This paper proposes a high-level model management methodology by introducing attributed AND-OR graph(AOG), a (formal semantics for representing the possible structure of a model. Using the formalism enables a designer to extract, extend and reuse the pre-modeled and pre-verified design. A complete process of constructing a cache operational model, extending the model and extracting executable models is exemplified to show effectiveness of the proposed framework.