• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.7C
• /
• pp.675-686
• /
• 2005

In this paper, we propose an efficient face region detection technique for the content-based video summarization. To segment video, shot changes are detected from a video sequence and key frames are selected from the shots. We select one frame that has the least difference between neighboring frames in each shot. The proposed face detection algorithm detects face region from selected key frames. And then, we provide user with summarized frames included face region that has an important meaning in dramas or movies. Using Bayes classification rule and statistical characteristic of the skin pixels, face regions are detected in the frames. After skin detection, we adopt the projection method to segment an image(frame) into face region and non-face region. The segmented regions are candidates of the face object and they include many false detected regions. So, we design a classifier to minimize false lesion using CART. From SGLD matrices, we extract the textual feature values such as Inertial, Inverse Difference, and Correlation. As a result of our experiment, proposed face detection algorithm shows a good performance for the key frames with a complex and variant background. And our system provides key frames included the face region for user as video summarized information.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.361-368
• /
• 2014

The LPR(License plate recognition) system has been developed to efficient control for complex traffic environment and currently be used in many places. However, because of light, noise, background changes, environmental changes, damaged plate, it only works limited environment, so it is difficult to use in real-time. This paper presents a heuristic segmentation algorithm for robust to noise and illumination changes and introduce a real-time license plate recognition system using it. In first step, We detect the plate utilized Haar-like feature and Adaboost. This method is possible to rapid detection used integral image and cascade structure. Second step, we determine the type of license plate with adaptive histogram equalization, bilateral filtering for denoise and segment accurate character based on adaptive threshold, pixel projection and associated with the prior knowledge. The last step is character recognition that used histogram of oriented gradients (HOG) and multi-layer perceptron(MLP) for number recognition and support vector machine(SVM) for number and Korean character classifier respectively. The experimental results show license plate detection rate of 94.29%, license plate false alarm rate of 2.94%. In character segmentation method, character hit rate is 97.23% and character false alarm rate is 1.37%. And in character recognition, the average character recognition rate is 98.38%. Total average running time in our proposed method is 140ms. It is possible to be real-time system with efficiency and robustness.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.388-396
• /
• 2017

Since there are many variables such as various poses, illuminations and occlusions in a face detection problem, a high performance detection system is required. Although CNN is excellent in image classification, CNN operatioin requires high-performance hardware resources. But low cost low power environments are essential for small and mobile systems. So in this paper, the CPU-FPGA integrated system is designed based on 3-stage cascade CNN architecture using small size FPGA. Adaptive Region of Interest (ROI) is applied to reduce the number of CNN operations using face information of the previous frame. We use a Field Programmable Gate Array(FPGA) to accelerate the CNN computations. The accelerator reads multiple featuremap at once on the FPGA and performs a Multiply-Accumulate (MAC) operation in parallel for convolution operation. The system is implemented on Altera Cyclone V FPGA in which ARM Cortex A-9 and on-chip SRAM are embedded. The system runs at 30FPS with HD resolution input images. The CPU-FPGA integrated system showed 8.5 times of the power efficiency compared to systems using CPU only.

• Journal of Science and Technology Studies
• /
• v.14 no.2
• /
• pp.281-318
• /
• 2014

This paper aims to examine women's understanding of technoscience by analyzing girls' comics(少女漫畵, Sonyeo Manhwa). The idea that women were not interested in science was a socially accepted. But this paper reveals that women are interested in science in a different way by analyzing Korean SF girls' comics. By examining an image of science in SF girls' comics in comparison to SF boys' comics(少年漫畵, Sonyeon Manhwa), this paper shows that women look technoscience through 'reflexivity' focused on 'human' and that this special character is derived from the feature of women's culture. SF girls comics have two features. First, girls comics reflect on power made by technoscience rather than describe it elaborately. And the reflexivity is expressed through a mental state, an emotion, and relations between human beings focused on a human nature, an ego, and an identity. It is different from boys comics that give weight to the mechanics and that show simple plot such as utopia or distopia, or a battle of good versus evil. Second, girls comics express technoscience as daily practices. In girls comics, some technosciences are linked to our daily lives and cartoonists and readers consider an 'essence of knowledge' together. It is different from men's view that regards knowledge as power or means.

• Korean Journal of Social Welfare
• /
• v.56 no.3
• /
• pp.89-112
• /
• 2004

The purpose of this study is to systemize volunteer program for the people with chronic mental health problems to participate in helping the community as service providers not receivers, and then to examine empowerment effects of this volunteer program. The distinctive feature of this program was to volunteer the mental ill to help other people. Therefore, this volunteer program had specially strengthened preliminary stage which make not only the mental ill be ready to work but also the community to use them as volunteer, and to invite general citizen of the community as co-volunteers. The result showed this program empowered the mental disorders to have more positive self-concept. It revealed that co-volunteer's attitude toward the mental disorders was changed positively through this program, also. These results told us not only the chronic mental ill could be volunteers helping others using their abilities, but also this activity would make their self-image better and citizen's perception toward mental disorder less prejudiced. The volunteer program presented in this paper was expected to be useful for their empowerment and social integration.

• Journal of The Korean Association For Science Education
• /
• v.34 no.6
• /
• pp.601-611
• /
• 2014

The purpose of this study is to analyze the Korean science magazine, Science Donga providing scientific facts, phenomenons, and issues with infographic for the readers by time series analysis and to search for the application of infographic on the science education. The criteria for the infographic analysis of Science Donga consisted of three categories such as storytelling type, visual perception, and framework level because infographic presents complex information quickly and clearly by integrating various images, words, and graphics. We found that the articles emphasized by including image about science issue have been published from 1986 to 2014. Particularly, after 2008, the articles including infographic sharply rose. So we set up 2008 as $T_c$(Critical time point). The articles including infographic after 2008 have been more variously distributed and frequently used in storytelling types category such as location, time, number, connection, function, and process based infographic, in visual perception of Gestalt Theory such as proximity, similarity, continuation, and closure than before 2008. Lastly, in framework level category, location, time, number, and process based infographic mainly had total range level but function and connection based infographic changed in the framework level. The three features about storytelling type, visual perception, framework level are important changes to influence $T_c$ in the infographic analysis about Science Donga. Through the results of this study, we analyzed the feature of change on infographic from 1986 to 2014. Thus, we hope that the results suggest a basic criteria for making materials including infographic in science education.

• Journal of the Korean Vacuum Society
• /
• v.19 no.2
• /
• pp.128-133
• /
• 2010

ZnO:Al films were deposited by DC-pulsed magnetron sputtering using a two-step process involving the control of the oxygen pressure. The seed layers were prepared with various Ar to oxygen flow ratios and the bulk layers were deposited under pure Ar. As the oxygen pressure during the deposition of the seed layer increased, the crystallinity and degree of (002) texturing increased. The resistivity gradually decreased with increasing crystallinity from $4.7\times10^4\Omega{\cdot}cm$ (no seed) to $3.7\times10^4\Omega{\cdot}cm$ (Ar/$O_2$ = 9/1). The etched surface showed a crater-like structure and an abrupt morphology change appeared as the crystallinity was increased. The sample deposited at an Ar/$O_2$ flow ratio of 9/1 showed a very high haze value of 88% at 500 nm, which was explained by the large feature size of the craters, as shown in the AFM image.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.2
• /
• pp.81-81
• /
• 2012

Since the ultraviolet (UV) flux of an integrated population is a good tracer of recent star formation activities, UV observations provide an important constraint on star formation history (SFH) in galaxies. We present UV color-magnitude relations (CMRs) of early-type dwarf galaxies in the Virgo cluster, based on Galaxy Evolution Explorer (GALEX) UV data and the Extended Virgo Cluster Catalog (EVCC, Kim, S. in prep.). The EVCC covers an area 5.4 times larger (750 deg2) than the footprint of the classical Virgo cluster catalog by Binggeli and collaborators. We secure 1304 galaxies as members of the Virgo cluster and 526 galaxies of them are new objects not contained in the VCC. Morphological classification of galaxies in the EVCC is based on the optical image ("Primary Classification") and spectral feature ("Secondary Classification") of the SDSS data. We find that dwarf lenticular galaxies (dS0s) show a surprisingly distinct and tight locus separated from that of ordinary dwarf elliptical galaxies (dEs), which is not clearly seen in previous CMRs. The dS0s in UV CMRs follow a steeper sequence than dEs and show bluer UV-optical color at a given magnitude. Most early type dwarf galaxies with blue UV colors (FUV-r < 6 and NUV-r < 4) are identified as those showing spectroscopic hints of recent or ongoing star formation activities. We explore the observed CMRs with population models of a luminosity-dependent delayed exponential star formation history. The observed CMR of dS0s is well matched with models with relatively long delayed star formation. Our results suggest that dS0s are most likely transitional objects at the stage of subsequent transformation of late-type progenitors to ordinary red dEs in the cluster environment. In any case, UV photometry provides a powerful tool to disentangle the diverse subpopulations of early-type dwarf galaxies and uncover their evolutionary histories.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.5
• /
• pp.895-907
• /
• 2020

With the recent increasing influence of multimedia content other than the text-based content, services that help to process information in content brings us great convenience. These services' representative features are searching and masking the sensitive data. It is not difficult to find the solutions that provide searching and masking function for text information and image. However, even though we recognize the necessity of the technology for searching and masking a part of the audio data, it is not easy to find the solution because of the difficulty of the technology. In this study, we propose web application that provides searching and masking functions for audio data using audio partitioning method. While we are achieving the research goal, we evaluated several speech to text conversion APIs to choose a proper API for our purpose and developed regular expressions for searching sensitive information. Lastly we evaluated the accuracy of the developed searching and masking feature. The contribution of this work is in design and implementation of searching and masking a sensitive information from the audio data by the various functionality proving experiments.

• Archives of design research
• /
• v.12 no.4
• /
• pp.99-108
• /
• 1999

The interior space in a passenger car is consisted with many partial elements, and the instrument panel is the most important part from all of them, which is designate the total image of the interior design and the space variation, drivability and safety of the interior space. ] The instrument panel of a passenger car in the early age had the concept of a wall between the engine room and the passenger cabin on which the instrument for the driver were fitted. Therefore the central mounting of the instruments was the typical feature regardless of the position of a driver seat. As the automobiles became more functional with many equipments, driver oriented instrument panel with energy absorbing materials had been developed, and that was the beginning of the various instrument panel design of these days. The recent instrument panels of passenger car have the tendency of going back to the central instrument mounting as it was at the past on a few cars for the strict safety regulation, a new production technology and for the enhanced drivability. It can be summarized into a few results as these with the analysis of a few recent instrument panels. -minimizing the total volume for the better frontal visibility. -energy absorbing and passive structures for the strict impact regulations. -revival of central instrument mounting for the convenience and safety through minimizing the difference of the focal length of a driver.