• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.94-98
• /
• 2009

A video caption recognition system has been developed for broadcasting sport events such as major league baseball. The purpose of the system is to translate the information expressed in English units such as miles per hour (MPH) to the international system of units (SI) such as km/h. The system detects the ball speed displayed in the video and recognizes the numerals. The ball speed is then converted to km/h and displayed by the following character generator (CG) system. Although neural-network based methods are widely used for character and numeral recognition, we use template matching to avoid the training process required before the broadcasting. With the proposed template matching method, the operator can cope with the situation when the caption’s appearance changed without any notification. Templates are configured by the operator with a captured screenshot of the first pitch with ball speed. Templates are updated with following correct recognition results. The accuracy of the recognition module is over 97%, which is still not enough for live broadcasting. When the recognition confidence is low, the system asks the operator for the correct recognition result. The operator chooses the right one using hot keys.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.2
• /
• pp.11-19
• /
• 2020

When a character's pose changes, its center of mass(COM) also changes. The change of COM has distinctive patterns corresponding to various motion types like walking, running or sitting. Thus the motion type can be predicted by using COM movement. We propose a motion generator that uses character's center of mass information. This generator can generate various motions without annotated action type labels. Thus dataset for training and running can be generated full-automatically. Our neural network model takes the motion history of the character and its center of mass information as inputs and generates a full-body pose for the current frame, and is trained using simple Convolutional Neural Network(CNN) that performs 1D convolution to deal with time-series motion data.

• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.1-13
• /
• 2021

In this research, we study the problem of font image skeletonization using an end-to-end deep adversarial network, in contrast with the state-of-the-art methods that use mathematical algorithms. Several studies have been concerned with skeletonization, but a few have utilized deep learning. Further, no study has considered generative models based on deep neural networks for font character skeletonization, which are more delicate than natural objects. In this work, we take a step closer to producing realistic synthesized skeletons of font characters. We consider using an end-to-end deep adversarial network, SkelGAN, for font-image skeletonization, in contrast with the state-of-the-art methods that use mathematical algorithms. The proposed skeleton generator is proved superior to all well-known mathematical skeletonization methods in terms of character structure, including delicate strokes, serifs, and even special styles. Experimental results also demonstrate the dominance of our method against the state-of-the-art supervised image-to-image translation method in font character skeletonization task.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.15 no.4
• /
• pp.295-299
• /
• 2015

The developed security scheme for user authentication, which uses both a password and the various devices, is always open by malicious user. In order to solve that problem, a keystroke dynamics is introduced. A person's keystroke has a unique pattern. That allows the use of keystroke dynamics to authenticate users. However, it has a problem to authenticate users because it has an accuracy problem. And many people use passwords, for which most of them use a simple word such as "password" or numbers such as "1234." Despite people already perceive that a simple password is not secure enough, they still use simple password because it is easy to use and to remember. And they have to use a secure password that includes special characters such as "#!($^*$)^". In this paper, we propose the automatic fortified password generator system which uses special characters and keystroke feature. At first, the keystroke feature is measured while user key in the password. After that, the feature of user's keystroke is classified. We measure the longest or the shortest interval time as user's keystroke feature. As that result, it is possible to change a simple password to a secure one simply by adding a special character to it according to the classified feature. This system is effective even when the cyber attacker knows the password.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.8
• /
• pp.1363-1369
• /
• 2008

As game and character animation industries are growing, techniques for reproducing realistic character behaviors have been required in various fields. Therefore, intensive researches have been performed in order to find various methods for realistic character animation. The most common approaches to character animation involves tedious user input method, simulation with physical laws based on dynamics, and measurement of actors' behaviors with input devices such as motion capture system. These approaches have their own advantages, but they all have common disadvantage in character control. In order to provide users with convenient control, the realistic animation must be generated with high-level parameters, and the modification should also be made with high-level parameters. In this paper we propose techniques for developing an automated character animation tool which operates with high-level parameters, and introduce techniques for developing actual games by utilizing this tool.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1591-1596
• /
• 2005

In this paper, we designed the aspheric lens by mathematical methods which are solved by refractive index. Based on these mathematical method, we manufactured the aspheric lens. Because of the usefulness of manufacturing, we used the acryl as the material. And we used a high speed machine to manufacture the aspheric lens. Also it sits in judgment the aberration of spherical distribution by using the grid fringe. Asource of laser produced by laser sheet generator passed the optical system of the aspheric lens. Though a character is to verify that the accuracy of the aspheric lens by experiment of the straight character.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1871-1874
• /
• 2003

Knowledge-based numeric open caption recognition is proposed that can recognize numeric captions generated by character generator (CG) and automatically superimpose a modified caption using the recognized text only when a valid numeric caption appears in the aimed specific region of a live sportscast scene produced by other broadcasting stations. in the proposed method, mesh features are extracted from an enhanced binary image as feature vectors, then a valuable information is recovered from a numeric image by perceiving the character using a multiplayer perceptron (MLP) network. The result is verified using knowledge-based hie set designed for a more stable and reliable output and then the modified information is displayed on a screen by CG. MLB Eye Caption based on the proposed algorithm has already been used for regular Major League Base-ball (MLB) programs broadcast five over a Korean nationwide TV network and has produced a favorable response from Korean viewer.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.559-562
• /
• 1999

In this paper, we developed on internet based assembly information display system for the blind. The system is consist of hardware and software. The hardware is consist of a voice synthesis device and a tactile display for character information, and the software is consist of internet web browser for the blind and braille program. The tactile-device system consists of a control unit, pin array, pin generator, serial port, and a power supply. The pin exerted by a electromagnetic method, solenoid. The internet web browser separates the character and image from internet web page, and character information in the web page is converted to braille and fed to sound system. Also the image in the web page can be printed developed tactile display. As the results of experiment, the blind could access the internet web site by using this system and understand various internet information.

• Proceedings of the KIEE Conference
• /
• 2006.10d
• /
• pp.62-64
• /
• 2006

본 논문에는 영구자석 내삽형 동기 발전기의 기전력 특성에 해석에 관한 연구이다. 기전력 해석시 측정값과 시뮬레이션의 값의 차이의 원인 중 하나를 영구자석에 있다고 가정 하고 이에 대한 영향을 자석을 세그먼트화 하여 비교 실험하였다. 실제 측정값과 시뮬레이션의 기전력의 차이의 원인에 대해 비교하였다.

• Korean Journal of Materials Research
• /
• v.9 no.9
• /
• pp.919-925
• /
• 1999

Grain boundary characteristics and corrosion behavior of Alloy 600 material were investigated using the concept of grain boundary control by thermomechanical treatment(TMT). The grain boundary character distribution (GBCD) was analyzed by electron backscattered diffraction pattern. The effects of GBeD variation on intergranular at tack(JGA) and primary water stress corrosion cracking(PWSeC) were also evaluated. Changes in the fraction of coinci dence site lattice(CSL) boundaries in each cycle of TMT process were not distinguishable, but the total eSL boundary frequencies for TMT specimens increased about 10% compared with those of the commercial Alloy 600 material. It was found from IGA tests that the resistance to IGA was improved by TMT process. However, it was found from PWSCC test that repeating of TMT cycles resulted in the gradual decrease of the time to failure and the maximum load due to change in grain boundary characteristics, while the average crack propagation rate of primary crack increased mainly due to suppression of secondary crack propagation. It is considered that these corrosion characteristics in TMT specimens is attributed to 'fine tuning of grain boundary' mechanism.