• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.10
• /
• pp.1131-1146
• /
• 1992

In this paper, we suggest a new algorithm applied to the segmentation of published documents to obtain constituent and layout information of document. Firstly, we begin the process of blocking and labeling on a 300dpi scanned document. Secondly, we classify the blocked document by individual sub-regions. Thirdly, we group sub-regions into graphic areas and text areas. Finally, we extract information for layout recognition by using the data. From an experiment on papers of an academic society, we obtain the above 98% of region classification rate and extraction rate of information for the layout recognition.

• Journal of the Korean School Mathematics Society
• /
• v.22 no.4
• /
• pp.501-520
• /
• 2019

This study compared and analyzed Korean, American, Singaporean, and Japanese middle school mathematics curriculum standards and the learning contents in statistics. Through a comparative analysis of the curriculums of these four countries, I found several overall features and differences between the curriculums. First, all four countries emphasized statistical education in a real-life context. Second, all four countries emphasized the use of technological tools. Third, there is a middle school grade in which only Korea does not deal with statistical domains. Fourth, the statistical areas of the United States, Singapore, and Japan focused on identifying trends or variability in data distribution. Fifth, I have found some contents that only Korea does not deal with. Based on this, the following recommendations were developed for the development of the next curriculum and new textbooks in Korea. First, the statistics curriculum should be changed from one that focuses on understanding statistical concepts to one that focuses on statistical activity that utilizes these concepts. Second, in terms of middle school statistical curriculum contents, the addition of interquartile range (IQR) and box plots as learning contents should be considered. IQR and box plots are simple and practical techniques for the comparison of multiple sets of data that can be easily learned and drawn by middle school level students and applied to real-life-related statistical data to expand statistical literacy. Through this study, it is suggested that IQR and box plots need to be included in the statistical curriculum of middle schools in Korea.

• Journal of the Korean Society for Library and Information Science
• /
• v.48 no.2
• /
• pp.331-352
• /
• 2014

In this study, the picture book reviews shown in Korean periodicals were analyzed to provide the developmental foundation for picture book reviews and expand the professional area of librarians as the producers of book review. Through the literature research and the Delphi Technique the desirable standard of book reviews was suggested, the contents in domestic book review mediums were analyzed for the rightness of describing based on the standard of the book review and henceforward the way of development was suggested. The result from analysis of book review showed that the outstanding book reviews should be more produced based on the desirable standard of book review and the evaluative statements should be developed more than the descriptive statements. Depending on the mediums the contents of the book review were different by the book reviewers' occupations, so the book reviewers should develop their professional knowledges in literature and art. Because the longer book review made the outstanding book review with the rightness of the desirable standard of book review, the certain quantity of book review should be needed and the role of librarians as the book reviewers should be further extended.

• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.5
• /
• pp.1-9
• /
• 2021

Children's drawings are widely used in the diagnosis of children's psychology as a means of expressing inner feelings. This paper proposes a children's drawings-based object detection algorithm applicable to children's psychology analysis. First, the sketch area from the picture was extracted and the data labeling process was also performed. Then, we trained and evaluated a Faster R-CNN based object detection model using the labeled datasets. Based on the detection results, information about the drawing's area, position, or color histogram is calculated to analyze primitive information about the drawings quickly and easily. The results of this paper show that Artificial Intelligence-based object detection algorithms were helpful in terms of psychological analysis using children's drawings.

• Journal of Korean Home Economics Education Association
• /
• v.35 no.3
• /
• pp.1-20
• /
• 2023

In order to develop a picture book for desirable eating habits of young children, the contents of nutrition education in picture books were analyzed. A total of 128 picture books were analyzed: 42 picture books from the Nuri-curriculum teacher's guide (Nuri), 40 picture books recommended by the National Library for Children & Young Adults (NLCY), and 46 picture books published by the Center for Children's Food-service Management (CCFM). As a result of analysis of dietary guidelines for Koreans, the item that appeared most frequently in picture books was 'Consume a variety of foods every day' (28.91%). The second most common dietary guidelines in the picture books was 'Enjoy a diet that incorporates local ingredients and is environmentally conscious' (21.88%). As a result of examining the main goal of 'eating right' in the Nuri Curriculum, 'healthy food' accounted for 36.72% and 'eating a variety of food' accounted for 30.47%. 'Eating with the right attitude' 4.69%, 'valuing food' 3.13%, and 'dining etiquette' 6.25% were low. Therefore, it is necessary to develop and distribute picture books that reflect the contents that are insufficient.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.233-236
• /
• 2000

최근 수많은 인쇄된 문서들이 HTML과 같은 디지털 문서로 바뀌고 있으며 이를 자동으로 변환해 주는 문자인식 기술에 대한 관심이 증가하고 있다. 본 논문에서는 그림과 글자가 공존하는 문서에서 자동으로 문자영역을 추출해서 문자를 인식하는 방법을 제안한다. 우선 입력문서는 유사한 칼라로 이루어진 영역들로 나누어진 뒤 휴리스틱 룰에 의해 문자후보 영역과 비 문자 영역으로 나누어진다. 그 다음 이들 문자후보영역들은 문자인식기를 이용하여 문자 혹은 문자의 일부분으로 인식된다. 제안된 방법으로 여러 문서들에 대하여 실험한 결과를 보이며 그 성능을 평가한다.

• The Journal of Korean Association of Computer Education
• /
• v.3 no.1
• /
• pp.97-107
• /
• 2000

In children education, it takes a much time for teachers to prepare teaching materials and tools. Most teaching materials and tools consist of pictures so that children may easily understand the contents of a study. If instructors free from laborious work for preparing these materials, they can provide children with better education by focusing more creative works. In this study, we manufactured many picture data which are used in children education, and developed a program that is used by teachers for the purpose of utilizing these pictures according to study topics. This program provides a feature that easily search more than 3700 pictures according to subjects and areas, and also provides various editing facilities such as expanding, reducing pictures and writing statements.

• Proceedings of the Optical Society of Korea Conference
• /
• 2003.02a
• /
• pp.94-95
• /
• 2003

광학식 3차원 형상측정 기술은 산업현장과 의료분야 등에서 광범위하게 사용되어지고 있으며, 이에 대한 연구도 활발히 진행되고 있다. 본 연구에서는 푸리에 변환법에 의한 위상정보 추출 기술을 개발하고, 주파수 영역에서의 창함수 필터에 따른 위상추출 특성을 분석하였다. 광조사 장치로는 LCD 프로젝터를 이용한 투영방식(그림 1)과 레이저 간섭계 투영방식(그림 2)을 사용하였다. (중략)

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.434-434
• /
• 2011

가뭄은 홍수와는 달라서 정확한 발생시점, 지속시간, 피해반경 등을 정의하기 어렵다. 가뭄은 가뭄지수를 통해서 정의되며 정해진 지속시간에 따라서 가뭄의 특성을 평가하는 것이 일반적이다. 이러한 가뭄의 심도를 평가하기 위해서 많이 사용되는 지수로 표준강수지수(standardized precipitation index)가 있다. 본 연구에서는 6개월 지속시간에 SPI 지수를 대상으로 연구를 수행하였다. 최근 가뭄연구에서 시공간적 거동을 평가하는 연구가 중요한 연구주제로 자리 잡고 있다. 가뭄은 홍수와는 달리 공간적으로 전이되는 특성을 가지고 있어서 가뭄의 시작점과 영역반경을 평가하는 것은 가뭄을 예측하는데 있어서 기본적으로 선결되어야 한다. 그러나 상대적으로 가뭄의 시공간적 분석 연구는 많이 진행되지 않았다. 본 연구에서는 질량모멘트 개념을 도입하여 가뭄의 중심과 영역을 평가하는 기법을 개발하였다. 가뭄의 중심(centroid)은 1차모멘트를 통해서 추정되며 가뭄의 영역은 2차모멘트 즉, x방향의 공분산, y방향의 공분산, xy의 공분산을 통해서 타원(ellipse)형태로 수치적 접근이 가능하다. 다음 그림과 같이 가뭄의 중심을 1차모멘트로 추정하게 되면 +형태로 표시될 수 있으며 분산을 타원체로 표현하여 가뭄의 영역을 정의할 수 있다. 1, 2차모멘트를 추정하는데 있어서 Threshold 로 -2.0 이하의 값만을 이용하였으며 각 격자별 SPI 강도를 가중인자로 이용하였다. 그림과 같이 가뭄이 서해안에서 시작되어 시간에 따라 중동부로 퍼져나가는 것을 정량적으로 확인할 수 있다. 본 모형을 통해서 추출된 1, 2차 모멘트 정보를 활용하여 가뭄의 특성을 범주화하고 이를 기상학적 특성과 연결시키면 기상특성을 고려한 가뭄 예측모형으로의 개발도 가능할 것으로 판단된다.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.509-516
• /
• 2002

This paper proposes an efficient algorithm which recognizes the mixed document image consisting of the images, texts, tables, and straight lines. This system is composed of three steps. The first step is the detection of rotation angle for complementing skewed images, the second is detection of erasing an unnecessary background region and last is the classification of each component included in document images. This algorithm performs preprocessing of detecting rotation angles and correcting documents based on the detected rotation angles in order to minimize the error rate by skewness of the documentation. We detected the rotation angie using only horizontal and vertical components in document images and minimized calculation time by erasing unnecessary background region in the detecting process of component of document. In the next step, we classify various components such as image, text, table and line area included in document images. we applied this method to various document images in order to evaluate the performance of document recognition system and show the successful experimental results.