• 한국식생활문화학회지
• /
• 제20권4호
• /
• pp.459-467
• /
• 2005

The purpose of this study is to provide useful information for establishing desirable table manner culture by investigating the perception, practice of traditional basic table manner. The subjects were consisted of 1,261 participants(618 males and 643 females) in Daegu and Kyungpook. The recognition, practice of traditional basic table manner were measured on the five-point Likert scale. The results were summarized as follows: The overall recognition score on ordinary table manner was 3.74 points, and of methods and kinds of dinner services was 2.99 points. The education score on table manner of parents for sons and daughters was 3.66 points, and the necessity score of table manner was 3.92 points. The scolding score of adults for table manner was 2.79 points, and cooking score of side dishes for adult was 3.25 points. In result of analyzing difference between perception and performance of traditional table manner, perception is much higher than performance. Respondents consider that the most perceptional and performant traditional table manner item is 'eating foods inside mouth by not seeing and rushing out'. Meanwhile, 'eating and taking some foods from a main dish' was the lowest perception and performance. The total recognition score on traditional table manner was 77.78 points, and the total practice score on traditional table manner was 71.72 points.

• 정보보호학회논문지
• /
• 제29권5호
• /
• pp.1007-1017
• /
• 2019

현재 대부분의 생체인증 시스템은 단일 생체정보를 이용하여 사용자를 인증하고 있는데, 이러한 방식은 노이즈로 인한 문제, 데이터에 대한 민감성 문제, 스푸핑, 인식률의 한계 등 많은 문제점들을 가지고 있다. 이를 해결하기 위한 방법 중 하나로 다중 생체정보를 이용하는 방법이 제시되고 있다. 다중 생체인증 시스템은 각각의 생체정보에 대해서 information fusion을 수행하여 새로운 정보를 생성한 뒤, 그 정보를 활용하여 사용자를 인증하는 방식이다. Information fusion 방법들 중에서 score-level fusion 방법을 보편적으로 많이 사용한다. 하지만 정규화 작업이 필요하다는 문제점을 갖고 있고, 데이터가 같아도 정규화 방법에 따라 인식률이 달라진다는 문제점을 갖고 있다. 이에 대한 대안으로 정규화 작업이 필요 없는 rank-level fusion 방법이 제시되고 있다. 하지만 기존의 rank-level fusion 방법들은 score-level fusion 방법보다 인식률이 낮다. 이러한 문제점을 해결하기 위해 상관계수를 이용하여 score-level fusion 방법보다 인식률이 높은 rank-level fusion 방법을 제안한다. 실험은 홍채정보(CASIA V3)와 얼굴정보(FERET V1)를 이용하여 기존의 존재하는 rank-level fusion 방법들의 인식률과 본 논문에서 제안하는 fusion 방법의 인식률을 비교하였다. 또한 score-level fusion 방법들과도 인식률을 비교하였다. 그 결과로 인식률이 약 0.3%에서 3.3%까지 향상되었다.

• 대한치과기공학회지
• /
• 제32권2호
• /
• pp.91-102
• /
• 2010

Purpose : The purpose of study was 500 people who are not related to dentistry in order to survey image about dental technicians. Methods : The subjects were composed of 500 people who are not related in Daegu Metropolitan city. This study was done using the Statistical Package for Social Sciences 17.0 for Windows. As for the analysis methods, the study used the frequency analysis, percentage, mean, t-test, analysis of variance. Results : The score on the image of dental technicians declined in the order of occupational image(2.98), work image(3.14), personal image(3.26), social image(2.87). 'It is hard and stressful' in the occupational image had the highest score with 3.69, 'Dentist and companionship are strong' in the occupational image had the lowest score with 2.21. 'It need expert knowledge and a skilled technology' in the work image had the highest score with 3.69, 'Health medical treatment side of health technique is occupation.' in the work image had the lowest score with 3.69. 'It always work busily' in the personal image had the highest score with 3.69, 'It is value and is effect work.' in the personal image had the lowest score with 3.69. 'An employment is easy after license acquisition.' in the social image had the highest score with 3.69, 'It admit independence' in the social image had the lowest score with 3.69. Conclusion : Dental technition research in order to image improvement and recognition, as the medical professional must construct the desirable dental technition image and recognition.

• 한국정보통신학회논문지
• /
• 제17권5호
• /
• pp.1064-1069
• /
• 2013

본 논문에서는 SOM과 개선된 ART-1을 이용하여 악보를 인식하는 방법을 제안한다. 악보 인식을 위해 스캔된 악보 이미지를 호프 변환, Otsu's 이진화를 원본 이미지에 적용하고, 히스토그램 분석을 통해 구분된 작은악절에서 오선을 제거하여 악보의 음표 성분을 추출할 수 있는 이미지 전처리 단계를 수행한다. 오선이 제거된 작은악절은 레이블링을 이용하여 음표 성분을 분리한다. 추출된 음표들은 SOM 알고리즘을 적용하여 일정한 크기로 정규화하고, 정규화된 음표 정보들을 개선된 ART-I 알고리즘을 적용하여 학습과 인식한다. 제안된 방법을 적용하여 음표 인식 실험을 한 결과, 제안된 방법이 음표 인식에 효율적임을 확인하였다.

• 한국음향학회지
• /
• 제10권3호
• /
• pp.31-36
• /
• 1991

본 논문에서는 대용량 음성인식 시스템의 인식시간을 감축하기 위하여 후보단어를 선정하는 효과적인 방법을 제안하고 이 방법의 성능을 향상시키기 위하여 spectral smoothing과 temporal smoothing을 사용하는 것에 관하여 연구하였다. 제안된 방법은 사전내의 각 단어에 대하여 음성인식 단위의 음성 spectrum관찰확률과 길이정보를 이용하여 대강의 관찰확률을 계산하여 후보단어를 선정한다. 제안된 방법을 음소단위의 HMM을 이용하는 1160단어 인식 시스템에 적용한 결과, 전체 계산량의 74% 가량을 감축할 수 있었으며 이때 인식율의 감소는 매우 작았다. 또한 제안된 대감의 likelihood점수 계산방법은 Viterbi방법에 의하여 계산되는 likelihood 점수를 잘 추정함을 알 수 있었다.

• 대한영양사협회학술지
• /
• 제9권3호
• /
• pp.185-196
• /
• 2003

In order to investigate the recognition of processed foods, use of food labeling, and their influencing factors in adolescents, 277(male 125, female 152) middle school students were conveniently selected from Cheonan city, and were surveyed by self-recording questionnaire on June, 2000. Subjects' parents were also surveyed using the similar questionnaire. Food labels of all 222 processed foods collected from stores around schools, were well labeled in most items, but food additives(35.6%) and the origin of major ingredient(27.0) were not well indicated. The recognition score of processed foods was 55.0 out of a full score 100 in students and 68.5 in parents. The scores of students were positively correlated with those of their parents and with father's education years, while negatively correlated with snacking expenses. The rate of reading food labels was significantly different between students(51.3%) and their parents(89.9%). The main purposes of reading food labels, in case of students, were to check expiry date(93.7%), price(70.4%), and how to eat(46.5%) in order. While in parents, those were to check expiry date(95.6%), additives(59.0%), and manufacturer(45.8%). Similarly, the most three important items in food labels were expiry date, price, and quantity to the students, but to the parents they were expiry date, manufacturer, and ingredient. The most significant reason not to confirm food labels was because of small size and complication of labels. The students who did not read food labels had more snacking money and more frequent snacking, and showed lower recognition score of processed food, compared with the students who read food labels. In conclusion, the students did not well recognise processed foods and only a half of them read food labels at purchasing. The recognition score of processed foods, snacking moneys, and snacking frequency may be influencing factors on the reading of food labels in students. The high recognition of processed food of parents may positively affect the students' recognition, but did not affect directly the reading food labels.

• 한국학교보건학회지
• /
• 제22권1호
• /
• pp.17-32
• /
• 2009

Purpose: This study was performed to investigate the attitude and recognition on how to describe the elderly of elementary school students. Methods: The subject of this study was total 806 students of 4, 5, 6 grade at 2 elementary schools in Gyunggi-do. The data were collected through self-reporting questionnaires for a month. Results: First, the score of attitude about the elderly was 107.8 and image score was the highest. Second, there were significant differences in the attitude about the elderly according to grade, birth order of siblings, domestic atmosphere, and economic status, domestic education on respect about the elderly, and education about the elderly at school. Third, there were significant differences in the attitude about the elderly according to parent-grandparent relationship, health and economic status of grandparents, meeting frequency with grandparents. Fourth, the score of word recognition about the elderly was 43.3 and social score was the highest. fifth, there were significant differences in recognition on how to describe the elderly according to grade, birth order of siblings of students and parents, domestic atmosphere, and economic status, domestic education on respect about the elderly. Sixth, there were significant differences in recognition on how to describe according to parent-grandparent relationship, health status and economic status of grandparents, meeting frequency with grandparents. Lastly, The attitude and recognition about the elderly showed significant positive relationship. Conclusion: We should provide qualitative education programs to improve the attitude and recognition about the elderly of elementary school students.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권8호
• /
• pp.3984-4005
• /
• 2017

Image recognition has become an increasingly important topic for its wide application. It is highly challenging when facing to large-scale database with large variance. The recognition systems rely on a key component, i.e. the low-level feature or the learned mid-level feature. The recognition performance can be potentially improved if the data distribution information is exploited using a more sophisticated way, which usually a function over hidden variable, model parameter and observed data. These methods are called generative score space. In this paper, we propose a discriminative extension for the existing generative score space methods, which exploits class label when deriving score functions for image recognition task. Specifically, we first extend the regular generative models to class conditional models over both observed variable and class label. Then, we derive the mid-level feature mapping from the extended models. At last, the derived feature mapping is embedded into a discriminative classifier for image recognition. The advantages of our proposed approach are two folds. First, the resulted methods take simple and intuitive forms which are weighted versions of existing methods, benefitting from the Bayesian inference of class label. Second, the probabilistic generative modeling allows us to exploit hidden information and is well adapt to data distribution. To validate the effectiveness of the proposed method, we cooperate our discriminative extension with three generative models for image recognition task. The experimental results validate the effectiveness of our proposed approach.

• 대한의용생체공학회:의공학회지
• /
• 제31권5호
• /
• pp.385-394
• /
• 2010

Automatic gain control(AGC) is used in hearing aids to compensate for the hearing level as to reduced dynamic range. AGC is consisted of the main 4 factors which are compression threshold, compression ratio, attack time, and release time. This study especially focus on each individual need for optimum release time parameters that can be changed within 7 certain range such as 12, 64, 128, 512, 2094, and 4096ms. To estimate the effect of various release time in AGC, twelve normal hearing and twelve hearing impaired listeners are participated. The stimuli are used by one syllable and sentence which have the same acoustic energy respectively. Then, each of score of the word recognition score is checked in quiet and noise conditions. As a result, it is verified that most people have the different best recognition score on specific release time. Also, if hearing aids is set by the optimum release time in each person, it is helpful in speech recognition and discrimination.

• International Journal of Contents
• /
• 제10권4호
• /
• pp.11-17
• /
• 2014

The influence of acquisition environment on music score images captured by a camera has not yet been seriously examined. All existing Optical Music Recognition (OMR) systems attempt to recognize music score images captured by a scanner under ideal conditions. Therefore, when such systems process images under the influence of distortion, different viewpoints or suboptimal illumination effects, the performance, in terms of recognition accuracy and processing time, is unacceptable for deployment in practice. In this paper, a novel, lightweight but effective approach for dealing with the issues caused by camera based music scores is proposed. Based on the staff line information, musical rules, run length code, and projection, all regions of interest are determined. Templates created from inverse filter are then used to recognize the music symbols. Therefore, all fragmentation and deformation problems, as well as missed recognition, can be overcome using the developed method. The system was evaluated on a dataset consisting of real images captured by a smartphone. The achieved recognition rate and processing time were relatively competitive with state of the art works. In addition, the system was designed to be lightweight compared with the other approaches, which mostly adopted machine learning algorithms, to allow further deployment on portable devices with limited computing resources.