• Journal of IKEEE
• /
• v.14 no.3
• /
• pp.224-231
• /
• 2010

Automatic detection of objects in images has been one of core challenges in the areas such as computer vision and pattern analysis. Especially, with the recent deployment of personal mobile devices such as smart phone, such technology is required to be transported to them. Usually, these smart phone users are equipped with devices such as camera, GPS, and gyroscope and provide various services through user-friendly interface. However, the smart phones fail to give excellent performance due to limited system resources. In this paper, we propose a new scheme to improve object recognition performance based on pre-computation and simple local features. In the pre-processing, we first find several representative parts from similar type objects and classify them. In addition, we extract features from each classified part and train them using regression functions. For a given query image, we first find candidate representative parts and compare them with trained information to recognize objects. Through experiments, we have shown that our proposed scheme can achieve resonable performance.

• Fashion & Textile Research Journal
• /
• v.16 no.4
• /
• pp.625-634
• /
• 2014

This study develops a sizing system of mass-customized male suits for wheelchair users. One hundred and three male wheelchair users' 21 anthropometric dimensions were measured to identify body shapes and develop a sizing system. The measured wheelchair users' body sizes were compared with the average body sizes of Korean males from the $6^{th}$ Korean Body Size Survey to understand the body size differences between two groups. As a result of body shape classification using the KS's Drop method, wheelchair user body shapes were classified into four shapes for upper-body (A: 32%, B: 26%, BB: 24%, and Y: 18%), and two shapes for lower-body (B: 70% and A: 30%). The upper-body of wheelchair users was relatively developed than Korean males; however, the lower-body was relatively stunted. The key dimensions of a sizing system were selected as chest circumference, waist circumference, and trunk length, outside leg length based on the correlation analysis between anthropometric measures. The top sizes were determined considering chest and waist circumferences for horizontal sizes, and additionally the trunk length was divided into short, medium, and long groups for vertical sizes. The bottom sizes were selected considering the waist and hip circumferences for horizontal sizes, and additionally their outside leg length was divided into short, medium, and long groups for vertical sizes.

• Fashion & Textile Research Journal
• /
• v.18 no.4
• /
• pp.477-488
• /
• 2016

This study classified and analyzed the types of images posted on official accounts operated by domestic and foreign SPA brands on Instagram and Pinterest, which are image-based fashion curations, and performed a survey on preferred image types in the fashion curations of SPA brands. It aims to induce active apparel purchasing behavior of consumers through the suggestion of image types about fashion curations for effective communication between fashion brands and consumers. The survey to targets the 20s and 30s was carried out from October 23, 2015 until November 22 and conducted factor analysis, paired t-test. The above images were classified into four types based on previous studies: product images, brand images, lifestyle images, multiple images. The results of the survey were also divided into four factors in line with the classification of image types. Generally, foreign SPA brands(H&M, Uniqlo, Zara) used image-based fashion curation services more frequently than domestic SPA brands(8Seconds, Mixxo, Spao, Tngt). The analysis of image types in the fashion curations of SPA brands showed that product images accounted for the highest proportion of images used in the official accounts of SPA brands. However, the comparison of averages on the preferred image types of survey respondents showed that the users who had once visited the official accounts of SPA brands on Instagram and Pinterest preferred in the order of lifestyle information > product information > brand information > multiple information provided by SPA brands, which was statistically significant.

• Journal of Korea Society of Industrial Information Systems
• /
• v.13 no.4
• /
• pp.145-154
• /
• 2008

In this paper, we propose the pet robot control system using hand gesture recognition in image sequences acquired from a camera affixed to the pet robot. The proposed system consists of 4 steps; hand detection, feature extraction, gesture recognition and robot control. The hand region is first detected from the input images using the skin color model in HSI color space and connected component analysis. Next, the hand shape and motion features from the image sequences are extracted. Then we consider the hand shape for classification of meaning gestures. Thereafter the hand gesture is recognized by using HMMs (hidden markov models) which have the input as the quantized symbol sequence by the hand motion. Finally the pet robot is controlled by a order corresponding to the recognized hand gesture. We defined four commands of sit down, stand up, lie flat and shake hands for control of pet robot. And we show that user is able to control of pet robot through proposed system in the experiment.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.5
• /
• pp.477-481
• /
• 2008

Place recognition is necessary for a mobile user to be provided with place-dependent information. This paper proposes real-time video based place recognition system that identifies users' current place while moving in the building. As for the feature extraction of a scene, there have been existing methods based on global feature analysis that has drawback of sensitive-ness for the case of partial occlusion and noises. There have also been local feature based methods that usually attempted object recognition which seemed hard to be applied in real-time system because of high computational cost. On the other hand, researches using statistical methods such as HMM(hidden Markov models) or bayesian networks have been used to derive place recognition result from the feature data. The former is, however, not practical because it requires huge amounts of efforts to gather the training data while the latter usually depends on object recognition only. This paper proposes a combined approach of global and local feature analysis for feature extraction to complement both approaches' drawbacks. The proposed method is applied to a mobile information system and shows real-time performance with competitive recognition result.

• Journal of Korean Academy of Nursing Administration
• /
• v.11 no.4
• /
• pp.401-414
• /
• 2005

Purpose: This study was to evaluate the utilization of health care service and to provide supportive data for health care policy making in one urban area in Korea. Method: This study tested the significance of public health service using the database of an university hospital and public health center from Feb. 2000 to Dec. 2004. Data were analyzed by multidimensional analysis and data mining technique and produced the information on the classification of utilization characteristics by main disease and the total cost of use and disease association with the users of the public health center. Results: The Results were as follows: 1) Top 10 diseases in the area accounted for 22.4% of total frequency for the most recent 5 years in university hospital, while 59.0% in public health center. 2) There were significant correlations between university hospital and public health center user's insurance type and place of residence: It showed higher use of public health center for free service beneficiaries residing in Seoul than residents in nearby or local area. The medical insurance types for hospital users were more various than those for public health center users. 3) The use of hospital for patients of hypertension, diabetes mellitus and hyperlipidemia was tended to concentrate in mostly autumn and winter since August 2000, while the cost of using public health center for those patients has been steadily reduced since July 2000. 4) As a result of cluster analysis, there were classified into three homogeneous groups according to the total cost of using public health service, age, and the frequency of use. 5) The association analysis on patients with chronic disease in public health center produced a detailed information on accompanying diseases related to the incidence rate of disease of high frequency due to aging, information on drug abuse and immune disease. Conclusion: The health care policy for local community should be evaluated continuously. And the policy to build an integrated data warehousing by public health indicator system and to enhance the faithfulness of data is required.

• Journal of Korea Multimedia Society
• /
• v.15 no.8
• /
• pp.1059-1066
• /
• 2012

With the development of Smartphone, Smartphone contains diverse functions including many sensors that can describe users' state. So there has been increased studies rapidly about activity recognition and life pattern recognition with Smartphone sensors. This research suggest modeling of the activity data to classify extracted data in existing activity recognition study. Activity data is divided into two parts: Physical activity and Logical Activity. In this paper, activity data modeling is theoretical analysis. We classified the basic activity(walking, standing, sitting, lying) as physical activity and the other activities including object, target and place as logical activity. After that we suggested a method of visualizing modeling data for users. Our approach will contribute to generalize human's life by modeling activity data. Also it can contribute to visualize user's activity data for existing activity recognition study.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.3
• /
• pp.608-613
• /
• 2006

There are many e-showing mall because of revitalization of e-commerce system. It is necessary to recommending system of products that is for saving time and effort of customer. In this paper, we propose the system that is applying classification among data mining techniques to analysis of log data of customer. This log data contains access of user and purchasing of products. The proposed system operates in two phases. The first phase is composed of data filter module and association extraction module among web pages. The second phase is composed of personalization module and rule generation module. Customer can easily know the recommended sites because the proposed system can present rank of the recommended web pages to customer. As a result, the proposed system can efficiently do recommending of products to customer.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2006.11a
• /
• pp.567-570
• /
• 2006

Recently because of rising of international oil prices, plant industry market has been active and purchase orders of big project are tending upwards. For strengthening of overseas plant competitive power and successful project operating, it is essential the project management technology and method. but procurement management of plant industry has evaluated uncompetitive. In this study, we analyzed the process of procurement founded and main contents and information. we study flowing of procurement information. user and creation time though detailing procurement information, then, we suggest the Contents Classification System and Management Model of Procurement Information.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.887-892
• /
• 2005

Under pure P2P environments, collaborative filtering must be provided with only a few service items by real time information without accumulated data. However, in case of collaborative filtering with only a few service items collected locally, quality of recommended service becomes low. Therefore, it is necessary to research a method to improve quality of recommended service by users' context information. But because a great volume of users' context information can be recognized in a moment, there can be a scalability problem and there are limitations in supporting differentiated services according to fields and items. In this paper, we solved the scalability problem by clustering context information Per each service field and classifying il per each user, using SOM. In addition, we could recommend proper services for users by measuring the context information of the users belonging to the similar classification to the service requester among classified data and then using collaborative filtering.