• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1312-1317
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• Journal of the Korean Society for Library and Information Science
• /
• v.48 no.1
• /
• pp.27-52
• /
• 2014

The employment prospects of graduates in the Library and Information academic has largely concentrated in the field of librarianship as well as the curriculum of the academic itself. Since there are limitations in increasing the number of libraries and the available posts in the librarianship, the full-time jobs in the field are also limited. Even for the available posts in the field of librarianship, the majority is in contract based posts which does not guarantee a good working environment. The purpose of this research is to make policy implications to improve the employment rates of librarians. The main research methods include literature review of the previous studies and available statistical data, and a questionnaire targeting students and librarians. The targeting policy implications can be categorized into 4 factors, including, as supply side, improvements in the qualification of librarian certificate, in training for librarians, and as demand side, laws on library employment, and improvement of library services for co-operatives. There are 15 detailed strategies to support the 4 factors. For the improvement of strategies in library related laws, the following elements will be considered; supporting system for temporary jobs, the title of librarian post and the library itself, and librarian placement criteria in terms of its realization and mandatory, and obligations in library evaluation. The Council discussions propose the expansion of librarian award system, provision of information systems for librarian jobs, and developments in promotional materials and their deployment for librarians.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.108-114
• /
• 1995

Cylindrical chamber mufflers with an extended inlet or outlet are extensively used in many application fields to reduce the propagated noise in ducts. The basic attenuation effectivencess in the low frequency region can be explained by the reactive wave action inside the expansion chamber associated with the geometric configurations of the inlet and outlet locations, and the area expansion of the jacket. In this study, an acoustic analysis is carried out for a concentric extended pipe inserted into a simple expansion chamber. An algebraic equation is derived by using the eigenfuction expansion and orthogonality principle in which the acoustic pressures and particle velocities defined on each subdivided surface are expressed by the separable coordinates. By using the proposed analytical method, transmission losses are predicted for several configurations of the concentric extended systems and they agree very well with experimental results.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.683-685
• /
• 2010

Augmented reality is a technology for showing virtual objects overlapped with the real world as seen from the eyes of users. Studies are being conducted on effective communication methods using hand movements in augmented reality. Hand movements are an important means of human communication along with writing and voice. Space arrangement technology and hand tracking technology using markers to acquire virtual information in augmented reality have many limitations. This paper proposes tracking hand area for augmented object. The augmented objects change viewpoints by hand positions which improves the sense of three dimensions and immersion.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.15-17
• /
• 2021

Handwriting recognition research is mainly focused on deep learning techniques and has achieved a great performance in the last few years. Especially, handwritten Thai digit recognition has been an important research area including generic digital numerical information, such as Thai official government documents and receipts. However, it becomes also a challenging task for a long time. For resolving the unavailability of a large Thai digit dataset, this paper constructs our dataset and learns them with some variants of the CNN model; Decision tree, K-nearest neighbors, Alexnet, LaNet-5, and VGG (11,13,16,19). The experimental results using the accuracy metric show the maximum accuracy of 98.29% when using VGG 13 with batch normalization.

• Horticultural Science & Technology
• /
• v.28 no.5
• /
• pp.836-844
• /
• 2010

This study was carried out to investigate plant characteristics and nutritional components of the genetically modified (GM) Chinese cabbage and its control line grown in the central and northern parts of Korea in order to establish the evaluating protocol and standard assessment. The GM and non-GM Chinese cabbage was planted with normal and concentrated density at two locations in spring and fall of 2008 and 2009. From the statistic analysis on plant characteristics and nutritional components, there were not many significant differences between GM and non-GM Chinese cabbage. Only few differences in the plant characteristics were found between the dense and normal planting. In the dense planting, there was no significant difference between GM and non-GM Chinese cabbages except for three out of 18 plant traits, such as leaf shape, hairiness and midrib length. On the other hand, nine plant traits including leaf length, leaf width, leaf color, leaf shape, fresh weigh of ground part, number of leaf, midrib length, midrib width and root diameter were slightly different between GM and non-GM Chinese cabbage in the normal planting. In case of leaf length, midrib length, midrib width and fresh weigh of ground part, there were significantly differences not only between two lines, but also between two locations. From nutritional component analysis, only five fatty acids were identified in the Chinese cabbage: palmitic acid, oleic acid, stearic acid, linoleic acid and linolenic acid. Except linoleic acid, four fatty acids in one gram of dried sample from GM line were little higher than those from non-GM line. However, there were no significant differences in total contents of fatty acids not only between GM and non-GM Chinese cabbage line, but also between northern and central cultivating areas in the normal and dense planting. According to the composition of inorganic elements identified in the samples from both lines, there were six macro-elements, such as N, P, Ca, K, Mg and Na, and four micro-elements, Cu, Fe, Mn and Zn. Based on the result from PCA analysis, specific clusters were not found between GM Chinese cabbage and the control line, but found between two regions.

• KIISE Transactions on Computing Practices
• /
• v.22 no.3
• /
• pp.127-132
• /
• 2016

Several methods have been proposed to apply artificial neural networks to text compression in the past. However, the networks and targets are both limited to the small size due to hardware capability in the past. Modern GPUs have much better calculation capability than CPUs in an order of magnitude now, even though CPUs have become faster. It becomes possible now to train greater and complex neural networks in a shorter time. This paper proposed a method to transform the distribution of original data with a probabilistic neural predictor. Experiments were performed on a feedforward neural network and a recurrent neural network with gated-recurrent units. The recurrent neural network model outperformed feedforward network in compression rate and prediction accuracy.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.8
• /
• pp.684-692
• /
• 2016

In this paper, a non-offset longitudinal shunt slot excited by an asymmetry compound iris on the broad wall of a rectangular waveguide is presented as an element for a waveguide slot-array antenna(WSAA). By properly adjusting the iris dimension, a resonance of the slot at a desired frequency can be achieved. The proposed resonant slot has some advantageous properties, such as a wide range of normalized resonant conductance, and minimum change of phase in the waveguide at the resonance. In addition, when the slots are arrayed for a waveguide slot antenna, the unwanted cross-polarization level can be reduced because each slot is placed in a straight line. A $8{\times}1$ WSAA with -20 dB side-lobe level(SLL) is designed, fabricated, and tested experimentally. The measured results are well agreed with the simulated ones and have an SLL of -18.13 dB and a cross-polarization level of -48.85 dB at 9.41 GHz, which was improved by about 15 dB of that of the conventional longitudinal slot array antenna.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.5
• /
• pp.503-509
• /
• 2002

Cylindrical chamber silencers with an extended inlet and outlet are extensively used in many application fields to reduce the propagated noise in ducts. The basic attenuation effectiveness in the low frequency region can be explained by the reactive wave action inside the expansion chamber associated with the geometric configurations of the inlet and outlet locations, and the area expansion of the jacket. In this study. an acoustic analysis is carried out for a concentric extended pipe inserted into a simple expansion chamber. An algebraic equation is derived by using the eigenfunction expansion and orthogonality principle in which the acoustic pressures and particle velocities defined on each subdivided surface are expressed by the separable coordinates. By using the proposed analytical method, transmission losses are predicted for several configurations of the concentric extended systems and they agree very well with experimental results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.1-8
• /
• 2018

Recently, the convolutional neural network shows high performance in many computer vision tasks. However, convolutional neural networks require enormous amount of operation, so it is difficult to adopt them in the embedded environments. To solve this problem, many studies are performed on the ASIC or FPGA implementation, where an efficient representation method is required. The fixed-point representation is adequate for the ASIC or FPGA implementation but causes a performance degradation. This paper proposes a separate optimization of representations for the convolutional layers and the batch normalization layers. With the proposed method, the required bit width for the convolutional layers is reduced from 16 bits to 10 bits for the ResNet-50 neural network. Since the computation amount of the convolutional layers occupies the most of the entire computation, the bit width reduction in the convolutional layers enables the efficient implementation of the convolutional neural networks.