• Journal of the Korea Convergence Society
• /
• v.8 no.6
• /
• pp.163-170
• /
• 2017

In this paper want to recognize competition and cooperation as a non-contact sensing method among the social emotion that are caused by interaction. Experiments were conducted in a pattern matching task divided into competition and cooperation situations. Data collection was performed by extracting the micro-movement data of 15Hz component from the upper body image. We compared and analyzed the amount and the variation and synchronization. As a result, Amount and variation are bigger in competition than cooperation. Synchronization was higher in cooperation than competition. This can be seen as the difference between two people trying to win when they are in competition and trying to breathe each other in cooperation. This study is significant in confirming the possibility of competition and cooperation through non contact sensing method based on physiological response.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2209-2215
• /
• 2014

This paper presents, a deinterlacing method by improving the Direction-Oriented Interpolation (DOI) technique. The technique is considered to be a very strong tool for intrafield-based deinterlacing. However, DOI has some problems such as long processing time, wrong edge detection in periodic pattern. To remedy this problem, we replace the full search in DOI by a two-step search to reduce processing time and introduces two additional processes to improve image quality. In the proposed method, the spatial direction vectors (SDVs) misread data are reconsidered to prevent them utilizing in the next interpolation step, resulting in an accurate deinterlacing method. We conduct experiments with ISO experimental images to compare the proposed method with the existing methods including line evarage (LA), edge-based line averaging (ELA), DOI, selective deinterlacing algorithm (SDA). Experimental results show the proposed method gives better performance in objective and subjective quality than existing deinterlacing methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.1
• /
• pp.106-112
• /
• 2015

In this paper, we propose an on-line signature recognition algorithm using fingertip point in the air from the depth image acquired by Kinect. We use ten statistical features for each X, Y, Z axis to react to changes in Shifting and Scaling of the signature trajectories in three-dimensional space. Artificial Neural Network is a machine learning algorithm used as a tool to solve the complex classification problem in pattern recognition. We implement the proposed algorithm to actual on-line signature recognition system. In experiment, we verify the proposed method is successful to classify 4 different on-line signatures.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.1
• /
• pp.190-196
• /
• 2013

Curved integral imaging is a simple method to display 3D images in space using lens array and provides wide viewing angle. In this paper, we propose a nonlinear 3D correlator based on the direct pixel-mapping (DPM) method in order to improve the recognition performance of 3D target object in curving-effective integral imaging. With this scheme, the elemental image array (EIA) originally picked up from a partially occluded 3-D target object can be converted into a resolution enhanced new EIA by using DPM method. Then, through nonlinear cross-correlations between the reconstructed reference and the target plane images, the improved pattern recognition can be performed from the correlation outputs. To show the feasibility of the proposed method, some preliminary experiments are carried out and results are presented by comparing the conventional method.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.2
• /
• pp.89-94
• /
• 2016

This paper proposed a facial expression recognition approach using SIFT feature and SVM classifier. The SIFT was generally employed as feature descriptor at key-points in object recognition fields. However, this paper applied the SIFT descriptor as feature vector for facial expression recognition. In this paper, the facial feature was extracted by applying SIFT descriptor at each sub-block image without key-point detection procedure, and the facial expression recognition was performed using SVM classifier. The performance evaluation was carried out through comparison with binary pattern feature-based approaches such as LBP and LDP, and the CK facial expression database and the JAFFE facial expression database were used in the experiments. From the experimental results, the proposed method using SIFT descriptor showed performance improvements of 6.06% and 3.87% compared to previous approaches for CK database and JAFFE database, respectively.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.8
• /
• pp.2061-2074
• /
• 1998

In pattern recognition and image analysis upplications, a graph is a useful tool for complex obect representation and recognition. However it takes much time to pair proper nodes between the prototype graph and an input data graph. Futhermore it is difficult to decide whether the two graphs in a class are the same hecause real images are degradd in general by noise and other distortions. In this paper we propose a matching algorithm using a matrix. The matrix is suiable for simple and easily understood representation and enables the ordering and matching process to be convenient due to its predefined matrix manipulation. The nodes which constitute a gaph are ordered in the matrix by their geometrical positions and this makes it possible to save much comparison time for finding proper node pairs. for the classification, we defined a distance measure thatreflects the symbo's structural aspect that is the sum of the mode distance and the relation distance; the fornet is from the parameters describing the node shapes, the latter from the relations with othes node in the matrix. We also introduced a subdivision operation to compensate node merging which is mainly due t the prepreocessing error. The proposed method is applied to the recognition of musteal symbols and the result is given. The result shows that almost all, except heavily degraded symbols are recognized, and the recognition rate is approximately 95 percent.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.653-662
• /
• 2002

Fingerprint recognition is a task to find a matching pattern in a database for a specific persons fingerprint. To accomplish this task, preprocessing, classification, and matching steps are taken for a large-scale fingerprint database but only the matching step is taken without classification for a small-scale database. The primary matching method is based on minutiae (ridge ending point, bifurcation). This matching method, however, requires a very complex computation to extract minutiae and match minutiae-to-minutiae accurately due to translation, rotation, nonlinear deformation of fingerprint and occurrence of spurious minutiae. In addition, this method requires a laborious preprocessing step in order to improve the quality of fingerprint Images. This paper proposes a new simple method to eliminate these problems. With this method, Gabor variance is used instead of minutiae for fingerprint recognition. The Gabor variance is computed from Gabor features that result from filtering a fingerprint image through Gabor filter. In this paper, this method is described and its test result is shown, demonstrating the potential of using this new method for fingerprint recognition.

• Korean Journal of Applied Biomechanics
• /
• v.13 no.2
• /
• pp.65-74
• /
• 2003

The purpose of this study was to analyze kinematic variables in the badminton smash motion through 3-dimensional image analysis. The kinematic variables were velocity of joints in upper limbs, the angle of wrist in the impact, and the angular velocity of the top of racket head. The smash motions of four male badminton players in H University and four male students at department of the physical education in K University who were not majoring in badminton were analyzed kinematically and the attained conclusions were as follow. 1. The velocity of segments in upper limbs of the unskilled group was faster than that of the skilled group. The movement pattern was fast back swing-slow impact moment-fast fellow through in the unskilled group, but slow back swing-fast impact moment-slow follow through in the sullied group. 2. As the BS phases, the velocity of segment in right shoulder was different significantly between groups. Right elbow and right wrist segments, velocity of racket head was different significantly between groups(p<.05) by IP phases. As the FT phases, there was no significant difference. 3. The angle of right wrist at the impact, the angle of palm flexion and the angle of palm flexion in aspect were shown that the skilled group was higher than unskilled group. There was no significant difference. 4. The velocity of racket head was shown that the unskilled group has fast velocity, but the angle velocity was shown the unskilled group has slow. 5. The angle velocity of racket head in aspect were no significant difference between groups, but maximal angle velocity was different significantly between groups(p<.05).

• Journal of Fashion Business
• /
• v.13 no.4
• /
• pp.85-98
• /
• 2009

Advance development of the internet has brought significant changes to the distribution structure of the fashion industry, resulting in decreased sales in Road shops and sudden growth of online fashion specialty shopping malls. As detailed analysis on internet fashion shopping malls is necessary in order to make a future projection on changes in the fashion industry, this thesis aims to study the color, fabric / pattern, silhouette, item / detail, image, etc of 2008 S/S apparel fashion style sold in the top ten shopping malls, selected in terms of sales volume and awareness. The results were further analyzed to characterize each individual shopping malls, upon which the design was compared with the five main trends for the season provided by three fashion research agencies in order to study the level of trend acceptance. Studies showed that 'Romantic Sake' trend was most widely accepted, followed by 'Eco Nature' which most reflected the characteristics of Spring. 'Modern Ethenic' trend was most aggressively accepted at more upscale shopping malls targeting older demographic, while " Play Urban' was highly accepted by shopping malls specializing in young casual. Due to the disadvantage of not being able to try on the items before purchase, styles following the 'City Luxe' trend featuring fitted suits showed the lowest trend acceptance. Amongst the design elements, color was most widely accepted.

• Journal of Fashion Business
• /
• v.18 no.3
• /
• pp.148-166
• /
• 2014

The purpose of this study is to establish the basic materials necessary for red carpet fashion design by examining the formativeness and fashion images of red carpet dresses at film festivals in the Great China Region. For the purpose of this study, research methods include a literature review on the origin and significance of red carpet dresses, the characteristics of film festivals in the Great China Region and their red carpet dresses as well as an analysis of the formative features and images of 615 red carpet dresses collected from each film festival official homepage, diverse media articles, and online search sites (www.google.com, www.hao123.com). The research finding can be summarized as follows: First, the formative features of red carpet dress designs were analyzed herein. It was found that the most frequently appearing type of silhouette was straight followed by hourglass and bulk in order. More specifically these included fit and flare, mermaid, trapeze, and slim in order. For the neckline styles, strapless was the most frequently seen followed by camisole, jewel, and one shoulder. Solid colors were more often seen than multiple colors. Bk, W, R, and YR were the most frequent main solid colors in order. Solid materials were frequent as well, such as soft and shiny materials. Non-patterned and unadorned styles were most frequent as for pattern types and details and trimmings. Second, the fashion images of red carpet dresses in the Great China Region were analyzed. The most frequent images were elegant, feminine, ethnic, modern, classic, avant-garde, others, mannish and sportive, in order.