• The Journal of the Korea Contents Association
• /
• v.13 no.8
• /
• pp.334-347
• /
• 2013

This study aimed to develop positioning strategies through the preparation of a positioning map by introducing brand personality to online shopping malls. Such a study will be able to furnish useful information for establishing differentiated marketing strategies in the online shopping mall market, which has faced fierce competition. For research subjects, the study was aimed at students who were attending S college in the Busan region. The results of an empirical analysis are as follows. The brand personality of online shopping malls were deduced to be the following factors: "competence refinement", "vitality", "intimateness", and "reliability". Then the study prepared a positioning map with these assessment attributes. As a result, there were mutually significant differences among competitive shopping malls in the positioning of consumers. The most differentiated attributes in the perception of the entire group were discovered to be "intimateness" and "vitality", whereas the least differentiated attribute was found to be "reliability". In addition, also in terms of the preference and ideal points for online shopping malls in accordance with brand personality between the entire group and segmented groups, there were mutually significant differences.

• Journal of Korea Multimedia Society
• /
• v.10 no.8
• /
• pp.981-996
• /
• 2007

In this paper, we describe a method that can recognize gestures by obtaining motion features information with principal factor analysis from sequential gesture images. In the algorithm, firstly, a two dimensional silhouette region including human gesture is segmented and then geometric features are extracted from it. Here, global features information which is selected as some meaningful key feature effectively expressing gestures with principal factor analysis is used. Obtained motion history information representing time variation of gestures from extracted feature construct one gesture subspace. Finally, projected model feature value into the gesture space is transformed as specific state symbols by grouping algorithm to be use as input symbols of HMM and input gesture is recognized as one of the model gesture with high probability. Proposed method has achieved higher recognition rate than others using only shape information of human body as in an appearance-based method or extracting features intuitively from complicated gestures, because this algorithm constructs gesture models with feature factors that have high contribution rate using principal factor analysis.

• Journal of Korea Multimedia Society
• /
• v.13 no.2
• /
• pp.316-323
• /
• 2010

In this paper, we propose fingertip extraction and hand motion recognition method for augmented reality applications. First, an input image is transformed into HSV color space from RGB color space. A hand area is segmented using double thresholding of H, S value, region growing, and connected component analysis. Next, the end points of the index finger and thumb are extracted using morphology operation and subtraction for a virtual keyboard and mouse interface. Finally, the angle between the end points of the index finger and thumb with respect to the center of mass point of the palm is calculated to detect the touch between the index finger and thumb for implementing the click of a mouse button. Experimental results on various input images showed that our method segments the hand, fingertips, and recognizes the movements of the hand fast and accurately. Proposed methods can be used the input interface for augmented reality applications.

• The KIPS Transactions:PartB
• /
• v.16B no.5
• /
• pp.377-384
• /
• 2009

A new algorithm in order to classify various contents in the image documents, such as text, figure, graph, table, etc. is proposed in this paper by classifying contents using texture-based PCA, and by segmenting document images using local entropy-based histogram. Local entropy and histogram made the binarization of image document not only robust to various transformation and noise, but also easy and less time-consuming. And texture-based PCA algorithm for each segmented region was taken notice of each content in the image documents having different texture information. Through this, it was not necessary to establish any pre-defined structural information, and advantages were found from the fact of fast and efficient classification. The result demonstrated that the proposed method had shown better performances of segmentation and classification for various images, and is also found superior to previous methods by its efficiency.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.137-151
• /
• 2014

This paper proposes a method of detecting object of interest(OOI) in general natural images. OOI is subjectively estimated by human in images. The vision of human, in general, might focus on OOI. As the first step for automatic detection of OOI, candidate regions of OOI are detected by using a saliency map based on the human visual perception. A saliency map locates an approximate OOI, but there is a problem that they are not accurately segmented. In order to address this problem, in the second step, an exact object region is automatically detected by combining graph-based image segmentation and skeletonization. In this paper, we calculate the precision, recall and accuracy to compare the performance of the proposed method to existing methods. In experimental results, the proposed method has achieved better performance than existing methods by reducing the problems such as under detection and over detection.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.1
• /
• pp.123-128
• /
• 2018

In this paper, we propose a multi-vehicle object detection algorithm using feature point matching that tracks efficient vehicle objects. The proposed algorithm extracts the feature points of the vehicle using the FAST algorithm for efficient vehicle object tracking. And True if the feature points are included in the image segmented into the 5X5 region. If the feature point is not included, it is processed as False and the corresponding area is blacked to remove unnecessary object information excluding the vehicle object. Then, the post processed area is set as the maximum search window size of the vehicle. And A minimum search window using the outermost feature points of the vehicle is set. By using the set search window, we compensate the disadvantages of the search window size of mean-shift algorithm and track vehicle object. In order to evaluate the performance of the proposed method, SIFT and SURF algorithms are compared and tested. The result is about four times faster than the SIFT algorithm. And it has the advantage of detecting more efficiently than the process of SUFR algorithm.

• 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 Integrative Natural Science
• /
• v.11 no.3
• /
• pp.139-147
• /
• 2018

Hippocampal atrophy is a well-established imaging biomarker of Alzheimer disease (AD). However, hippocampus is a non-homogenous structure with cytoarchitecturally and functionally distinct sub-regions or subfield, with each region performing distinct functions. Certain regions of the subfield have shown selective vulnerability to AD. Here, we are interested in studying the effects of normal aging and mild cognitive impairment on these sub-regional volumes. With a reliable automated segmentation technique, we segmented these subregions of the hippocampus in 101 cognitively normal (CN), 135 early mild cognitive impairment (EMCI), 67 late mild cognitive impairment (LMCI) and 48 AD subjects. Thereby, dividing the hippocampus into hippocampal tail (tail), subiculum (SUB), cornu ammonis 1 (CA1), hippocampal fissure (fissure), presubiculum (PSUB), parasubiculum (ParaSUB), molecular layer (ML), granule cells/molecular layer/dentate gyrus (GCMLDG), cornu ammonis 3(CA3), cornu ammonis 4(CA4), fimbria and hippocampal-amygdala transition area (HATA). In this cross sectional study of 351 ADNI subjects, no differences in terms of age, gender, and years of education were observed among the groups. Though, the groups had statistically significant differences (p < 0.05 after the multiple comparison correction) in the Mini-Mental State Examination (MMSE) scores. There was asymmetrical volume loss in the early stages of AD with the left hemisphere showing volume loss in regions that were unaffected in the right hemisphere. Bilateral parasubiculum, right cornu ammonis 1, 3 and 4, right fimbria and right HATA regions did not show any volume loss till the late MCI stages. Our findings suggest that the hippocampal subfield regions are selectively vulnerable to AD and also that these vulnerabilities are asymmetrical especially during the early stages of AD.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.06a
• /
• pp.1493-1510
• /
• 2000

Theoretical models that can be used to predict the range of main lobe widths and the probability distribution of the peak sidelobe levels of two-dimensionally sparse arrays are presented here. The arrays are considered to comprise microphones that are randomly positioned on a segmented grid of a given size. First, approximate expressions for the expected squared magnitude of the aperture smoothing function and the variance of the squared magnitude of the aperture smoothing function about this mean are formulated for the random arrays considered in the present study. By using the variance function, the mean value and the lower end of the range i.e., the first I percent of the mainlobe distribution can be predicted with reasonable accuracy. To predict the probability distribution of the peak sidelobe levels, distributions of levels are modeled by a Weibull distribution at each peak in the sidelobe region of the expected squared magnitude of the aperture smoothing function. The two parameters of the Weibull distribution are estimated from the means and variances of the levels at the corresponding locations. Next, the probability distribution of the peak sidelobe levels are assumed to be determined by a procedure in which the peak sidelobe level is determined as the maximum among a finite number of independent random sidelobe levels. It is found that the model obtained from the above approach predicts the probability density function of the peak sidelobe level distribution reasonably well for the various combinations of two different numbers of microphones and grid sizes tested in the present study. The application of these models to the design of random, sparse arrays having specified performance levels is also discussed.

• The Korean Journal of Community Living Science
• /
• v.20 no.2
• /
• pp.145-156
• /
• 2009

The purpose of this study was to explore socio-economic factors as determinants of food behavior and self-evaluation on meeting dietary guidelines. The data were derived from the KNHANES collected in 2007. A multidimensional framework of the determinants of food behavior was used, including age, gender, region, occupation, education, income and nutritional knowledge. The determinants of food behavior and self-evaluation were estimated by ordered logistic regression models. Food behavior was measured by dietary diversity scores including six food groups, which were cereals, vegetables, meats, fruits, milk, and oils. Self-evaluation on meeting dietary guidelines was based on responses from questionnaires for implementing Korean dietary guidelines. In general, the respondents who fulfilled all criteria were few. There were some differences between dietary diversity scores and self-evaluation on meeting dietary guidelines. Age, gender, and educational level showed effect on food behavior and self-evaluation. For dietary diversity scores, the individuals who were younger male, graduated from college were more likely to consume more various foods. The individuals who were older female, graduated from high school were more likely to meet dietary guidelines. Occupation was associated only with self-evaluation. Age and gender were associated with food behavior as well as self-evaluation. Income and marital status were associated only with dietary diversity scores. Reading food label and occupation were associated only with self-evaluation. The food behavior of married individuals was less in line with the dietary diversity scores than singles. In conclusion the differences between objective measure and subjective measure on individuals' diet showed more efforts like segmented nutritional education would be needed to increase the quality of dietary life.