• The Journal of the Acoustical Society of Korea
• /
• v.15 no.6
• /
• pp.90-98
• /
• 1996

In this paper we have proposed the sign language transformation system for deaf based on a morpheme analysis. The proposed system extracts phoneme components and connection informations of the input character sequence by using a morpheme analysis. And then the sign image obtained by component analysis is correctly and automatically generated through the sign image database. For the effective sign language transformation, the language description dictionary which consists of a morpheme analysis part for analysis of input character sequence and sign language description part for reference of sign language pattern is costructed. To avoid the duplicating sign language pattern, the pattern is classified a basic, a compound and a similar sign word. The computer simulation shows the usefulness of the proposed system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1287-1292
• /
• 2005

This paper presents an effective pattern classification model by designing an artificial neural network based pattern classifiers for face recognition. First, a RGB image inputted from a frame grabber is converted into a HSV image which is similar to the human beings' vision system. Then, the coarse facial region is extracted using the hue(H) and saturation(S) components except intensity(V) component which is sensitive to the environmental illumination. Next, the fine facial region extraction process is performed by matching with the edge and gray based templates. To make a light-invariant and qualified facial image, histogram equalization and intensity compensation processing using illumination plane are performed. The finally extracted and enhanced facial images are used for training the pattern classification models. The proposed H-ART2 model which has the hierarchical ART2 layers and F-LVQ model which is optimized by fuzzy membership make it possible to classify facial patterns by optimizing relations of clusters and searching clustered reference patterns effectively. Experimental results show that the proposed face recognition system is as good as the SVM model which is famous for face recognition field in recognition rate and even better in classification speed. Moreover high recognition rate could be acquired by combining the proposed neural classification models.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.04a
• /
• pp.255-259
• /
• 2003

Moire topography method isa well-known non-contacting 3-D measurement method as afast non-contact test for three-dimension shape measuring method. Recently, it's important to study the automatic three-dimension measurement by moire topography because it is frequently applied to the reverse engineering , the medical , the entertainment fields. Three-dimension measurement using projection of moire topography is very attractive because of its high measuring speed and high sensitivity. In this paper, the classical moire method is computerized-so called digital moire when a virtual grating pattern is projected on a surface, the captured image by the CCD camera has three-dimension information of the objects. The moire image can be obtained through a simple image processing and a reference grating pattern. and it provides similar results without physical grating pattern. digital projection moire topography turn out to be very effective for the three-dimension measurement of objects. Using different N-bucket algorithm method of digital projection moire topography is tested to measuring object with the 2-ambiguity problem. Experimental results prove that the proposed scheme is capable of finding measurement errors that decreased more by using the four-three step algorithm method instead of the same step in the phase shifting of different pitch.

• Journal of the Korean Home Economics Association
• /
• v.35 no.5
• /
• pp.249-264
• /
• 1997

The purpose of this study was to provide the reference information for user and potential users of apparel CAD system is Korea. Two interviews were carried out for the study. The apparel CAD system of Assyst, Gerber and Yuka was selected for technical comparative study. The results were as follows: 1. The future development of the apparel CAD system is the transfer of the developed pattern design from a 3D design system and of CIM concept. 2. The share of data is working closely in a module function. So the Assyst system provide connectivity and communication between all apparel CAD system's module and other automation programs. This system is suitable for CIM production line. 3. The Gerber system is developed the Apparel CAD system which is given by the CAM system's technical ability. This system is given high insurance of ability to the service and data transportation with other systems from users in the Korea. 4. The Yuka system is developed pattern making by the Apparel CAD system. This system's different methods which is compared with other systems are the split grading and auto pattern making. So this system is suitable for users which want to product many items and a little amount garment by using the Apparel CAD system.

• Journal of Information Management
• /
• v.37 no.3
• /
• pp.85-97
• /
• 2006

In a Digital Age contents are comprized of knowledge and information. Also distinction between the sinner and loser is very clear thus only those who can rise up to challenge of changes can become the strong and a principal player. In this study this author presented a model for forecasting information service program(FISP) which is devised for the purpose of innovation of service pattern related to providing information which is ultimate goal of a library. This model is an innovative strategy escaping boldly from negative and inactive information service pattern known in analog age. Through this model this author attempted to outline methodology for heightening ideal of professional librarians and for assuring success in organizational system.

• The Korean Journal of Food & Health Convergence
• /
• v.3 no.1
• /
• pp.1-7
• /
• 2017

The study has made theoretical system by thesis journals at home and abroad, material of the Association of Convenience Store Industry of Korea, materials of Statistics Korea and reference books. First, the study examined convenience store's brand image, cognized value, quality level, reliability upon brand, structural relation of purchasing intention, and designed models and theses. Second, the first questionnaire consisted of test items of precedent study, and inspected in advance to inspect reliability and appropriateness, and made correction and supplemented problems. Third, SPSS and AMOS statistics were used to conduct empirical analysis and to find out conclusion and implications. In this study, the subject was consumers who visited local convenience stores such as GS25, Seven Eleven and CU last 3 months to buy PB food. Consumers' consumption pattern and culture made change to be reasonable and practical owing to aging society, nuclear family, women's entering into the society, one person household consumer, and convenient and prompt buying to make different consumption pattern and to make change of commodity distribution pattern. Convenience store took action against change of the trend to expand business area by new distribution channels to get another growth source. Private brand (PB) food that was distributor's brand was expanded. The PB product has been competitiveness of food service industry.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.10
• /
• pp.53-58
• /
• 1999

Even I the Electronic Speckle Pattern Interferometry(ESPI) method that measure the strain of object within wavelength of light is less visibility than Holographic Interferometry(HI) method, the merits of application, convenience and time-save have made the method practical in industry. However, the existing ESPI methods that are based on dual-exposure, real-time and time-average method have difficulties for accurate measurement, due to irregular intensity and shake of phase. Recently, in order to solve this problem, phase shifting method have been proposed. In this method, the path of reference light in interference is shifted to make improvement in distinction and precision. But this method includes too many noise, caused by the problem of relationship between object and phase. Therefore, a method to reduce noise muse be introduced. In this paper, least square fitting method is proposed. As results, the phase-map is influenced by precise phase shifting and current of notes and speckle pattern obtained by phase shifting method is improved on the existing method driven from time-average method.

• Journal of Fashion Business
• /
• v.12 no.6
• /
• pp.81-92
• /
• 2008

The purpose of this study is to develop the applied brassiere pattern of women which are fitting for 75A. The constructing of this experimental brassiere were lower cup, upper cup, front panel and U-wing as well as a full cup embcing the entire breasts. Basing on the bra model from domestic experiment results, development of an applied design, round side type pattern, has been suggested. Thus, suggesting the round variation design bra, which is an applied design based on the basic model based on the breast volume. Based on the sizes that are in reference to Size Korea (2004) and related previous researches, the basic model that has been experimented with 11.4% polyurethane and 88.6% Nylon as the materials, has been selected as the model of research. This takes 75A, the size of which is set according to the underbust circumference and the breasts circumference, as the basic model. It is an application in terms of design, and there is no change to the cup volume or size because it has been moved only from the cutting line. The applied design changes the right side of the lower cup into an easily-movable form and attaches it to the upper cup, and the lower cup takes the right part of the upper cup to form a cup shape of round variation design. It also changes basic straight form of the wings, and alters them into U-shape.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.12
• /
• pp.3115-3123
• /
• 1993

This paper presents a real-time correction method of the movemont errors of a translatory precision machine axis. This method is a null-balances technique in which two plane mirrors are used to generate an interferometric fringe pattern utilizing the optical principles of TwymanGreen interferometry. One mirror is fixed on a reference frame, while the other is placed on the machine axis being supported by three piezoelectric actuators. From the fringe pattern, one translatory and two rotational error components of the machine axis are simultaneously detected by using CCD camera vision and image processing techniques. These errors are then independently suppressed by activating the peizoelectric actuators by real-time feedback control while the machine axis is moving. Experimental results demonstrate that a machine axis can be controlled with movement errors less than 10 nm in vertical straightness, 0.1 arcsec in pitch, and 0.06 arcsec in roll for 50mm travel by adopting the real-time correction method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.6
• /
• pp.797-803
• /
• 2014

In this paper, 3D face recognition system is designed by using polynomial based on RBFNNs. In case of 2D face recognition, the recognition performance reduced by the external environmental factors such as illumination and facial pose. In order to compensate for these shortcomings of 2D face recognition, 3D face recognition. In the preprocessing part, according to the change of each position angle the obtained 3D face image shapes are changed into front image shapes through pose compensation. the depth data of face image shape by using Multiple Point Signature is extracted. Overall face depth information is obtained by using two or more reference points. The direct use of the extracted data an high-dimensional data leads to the deterioration of learning speed as well as recognition performance. We exploit principle component analysis(PCA) algorithm to conduct the dimension reduction of high-dimensional data. Parameter optimization is carried out with the aid of PSO for effective training and recognition. The proposed pattern classifier is experimented with and evaluated by using dataset obtained in IC & CI Lab.