• Journal of Korea Multimedia Society
• /
• v.25 no.4
• /
• pp.568-574
• /
• 2022

In this paper, direction normalization and CNN deep learning are used to develop a more reliable license plate recognition system. The existing license plate recognition system consists of three main modules: license plate detection module, character segmentation module, and character recognition module. The proposed system minimizes recognition error by adding a direction normalization module when a detected license plate is inclined. Experimental results show the superiority of the proposed method in comparison to the previous system.

• Bulletin of the Korean Mathematical Society
• /
• v.48 no.3
• /
• pp.469-474
• /
• 2011

The Kauffman bracket skein module $K_t$(M) of a 3-manifold M becomes an algebra for t = -1. We prove that this algebra has no non-trivial nilpotent elements for M being the exterior of the twist knot in 3-sphere and, therefore, it is isomorphic to the $SL_2(\mathbb{C})$-character ring of the fundamental group of M. Our proof is based on some properties of Chebyshev polynomials.

• Bulletin of the Korean Mathematical Society
• /
• v.57 no.4
• /
• pp.973-990
• /
• 2020

For the question "when is E(_RR) a flat left R-module for any ring R?", in this paper, we deal with a class of modules partaking in the hierarchy of injective and cotorsion modules, so-called Harmanci injective modules, which turn out by the motivation of relations among the concepts of injectivity, flatness and cotorsionness. We give some characterizations and properties of this class of modules. It is shown that the class of all Harmanci injective modules is enveloping, and forms a perfect cotorsion theory with the class of modules whose character modules are Matlis injective. For the objective we pursue, we characterize when the injective envelope of a ring as a module over itself is a flat module.

• Science of Emotion and Sensibility
• /
• v.14 no.4
• /
• pp.483-494
• /
• 2011

This paper purposes to develop an artificial emotion reflecting emotional features contains situations, time, and characteristics, also to develop an interactive character having this artificial emotion with a smart phone. The artificial emotion has an Emotion Module and Drive Module for expressing emotion according to external emotional stimulus and internal drive. The Emotion Module administrates emotions according to time, characteristic, interrelation between different emotions. The Drive Module controls sensitivities of emotion according to changing drives over long time. Also due to defence mechanism for expressing emotions, emotions are processed by two pathways: The first pathway which is affected by the Emotion Module and the Drive Module, and the second pathway that is not to be done. We developed an interactive character having the artificial emotion with this structure using smart phone. And we simulated the artificial emotion what differences there are according to situations, characteristic, and time under same input conditions. The result of this paper has meanings developing the interactive character having the artificial emotion actually, and making it possible to personalize an artificial emotion with expressing the artificial emotion using smart phone.

• Journal of KIISE:Information Networking
• /
• v.37 no.1
• /
• pp.57-65
• /
• 2010

Recently, the character recognization technique is strongly needed to enable the mobile communication devices with cameras to gather input information from the users. In general, it is not easy to reuse a CBOCR(Camera Based Optical Character Recognizer) module because of its dependency on a specific platform. In this paper, we propose a software architecture for CBOCR module providing the easy adaptability to various mobile communication platforms. The proposed architecture is composed of the platform dependency support layer, the interface layer, the engine support layer, and the engine layer. The engine layer adopts a plug-in data structure to support various hardware endian policies. We show the effectiveness of the proposed method by applying the architecture to a practical product.

• Journal of the Korean Mathematical Society
• /
• v.42 no.2
• /
• pp.365-386
• /
• 2005

Let L be the free Lie superalgebra generated by a $Z_2$-graded vector space V over C. Suppose that g is a Lie superalgebra gl(m, n) or q(n). We study the g-module structure on the kth homogeneous component Lk of L when V is the natural representation of g. We give the multiplicities of irreducible representations of g in Lk by using the character of Lk. The multiplicities are given in terms of the character values of irreducible (projective) representations of the symmetric groups.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2008.10a
• /
• pp.1525-1528
• /
• 2008

High-luminance CNT-FED character-displays using simple line-rib-structure was performed. One display-panel had $48{\times}480$-dots and the sub-pixel pitch was 1mm. Another panel had $32{\times}256$-color-pixels, and the subpixel size was $0.6mm{\times}1.8mm$. The power consumption was less than 10W at character-displaying module. It should be useful for public display even under emergent no-power condition.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.1076-1084
• /
• 2019

In this paper, we introduced a system that extracts metadata by recognizing characters and objects in media using deep learning technology. In the field of broadcasting, multimedia contents such as video, audio, image, and text have been converted to digital contents for a long time, but the unconverted resources still remain vast. Building media archives requires a lot of manual work, which is time consuming and costly. Therefore, by implementing a deep learning-based metadata generation system, it is possible to save time and cost in constructing media archives. The whole system consists of four elements: training data generation module, object recognition module, character recognition module, and API server. The deep learning network module and the face recognition module are implemented to recognize characters and objects from the media and describe them as metadata. The training data generation module was designed separately to facilitate the construction of data for training neural network, and the functions of face recognition and object recognition were configured as an API server. We trained the two neural-networks using 1500 persons and 80 kinds of object data and confirmed that the accuracy is 98% in the character test data and 42% in the object data.

• Journal of Korea Game Society
• /
• v.15 no.6
• /
• pp.131-140
• /
• 2015

The character is one of most important interest-element in role playing game genres since it shows the individuality. In general cases, game players allocate points to talent clauses that they choose. However, it is not easy to provide the suitable character-growing to players in generic system since the cases are too simple and based on just humans choices. In this paper, we propose the character growing system based on the player type inference module. Growth morphology is determined by player's behavior or type. The determination is based on petri-net. Our experimental results and analysis show that our proposed approach is suitable for character-growing system.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.74-79
• /
• 2019

In this paper, we develop a virtual experimental environment to investigate users' eye gaze in human-robot social interaction, and verify it's potential for further studies. The system consists of a 3D robot character capable of hosting simple interactions with a user, and a gaze processing module recording which body part of the robot character, such as eyes, mouth or arms, the user is looking at, regardless of whether the robot is stationary or moving. To verify that the results acquired on this virtual environment are aligned with those of physically existing robots, we performed robot-guided quiz sessions with 120 participants and compared the participants' gaze patterns with those in previous works. The results included the followings. First, when interacting with the robot character, the user's gaze pattern showed similar statistics as the conversations between humans. Second, an animated mouth of the robot character received longer attention compared to the stationary one. Third, nonverbal interactions such as leakage cues were also effective in the interaction with the robot character, and the correct answer ratios of the cued groups were higher. Finally, gender differences in the users' gaze were observed, especially in the frequency of the mutual gaze.