• Annual Conference on Human and Language Technology
• /
• 2000.10d
• /
• pp.63-67
• /
• 2000

In order to develop a character recognition system, it is an essential preceding work that gathers an image data of the standard. On this purpose a data of the digitized images of a handwritten characters was collected. The types of a gathered image data are Korean character, Chiness character, Numeral, English character, Special character, and so on. This paper deals with a handwritten character image data base, and the image data base different from the general storage structure of a lame capacity multimedia was designed and builded.

• Journal of Korean Society of Archives and Records Management
• /
• v.22 no.4
• /
• pp.129-149
• /
• 2022

Records have temporal characteristics, including the past and present; linguistic characteristics not limited to a specific language; and various types categorized in a complex way. Processing records such as text, video, and audio in the life cycle of records' creation, preservation, and utilization entails exhaustive effort and cost. Primary natural language processing (NLP) technologies, such as machine translation, document summarization, named-entity recognition, and image recognition, can be widely applied to electronic records and analog digitization. In particular, Korean deep learning-based NLP technologies effectively recognize various record types and generate record management metadata. This paper provides an overview of Korean NLP technologies and discusses considerations for applying NLP technology in records management. The process of using NLP technologies, such as machine translation and optical character recognition for digital conversion of records, is introduced as an example implemented in the Python environment. In contrast, a plan to improve environmental factors and record digitization guidelines for applying NLP technology in the records management field is proposed for utilizing NLP technology.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.6B
• /
• pp.820-827
• /
• 2001

한글은 둘 또는 세 개의 자모가 사각형 영역 안에 적절히 배치된 구조로 되어 있다. 이와 같은 구성 방법에 따라 글자의 영상을 합성하고 이를 실시간에 Pseudo 2D HMM으로 변환하는 방법을 제안한다. 본 방법에 따라 실시간 합성된 모델과 추가의 필러(filler) 모델, 여백 모델을 문서 영상의 글자 영역에서 핵심어 검출에 적용하였다. 실험 결과 최소한의 설계 변수 조정으로도 오검출, 미검출률이 낮고 언어 모델 없이 숫자 89%, 한글 80%의 검출성능을 보였으며, 따라서 제안된 방법이 인쇄 문자 패턴의 실시간 모델링 및 키워드 검출에 효과가 있음을 보였다. 본 연구 결과는 내용 기반의 광학 문서 색인 등에 활용할 수 있다.

• Journal of Korean Elementary Science Education
• /
• v.43 no.1
• /
• pp.64-80
• /
• 2024

This study aims to investigate the characteristics of verbal interaction in science class demonstrations conducted by elementary school pre-service teachers. Specifically, the study intends to examine the use of elements of verbal interaction and the progression of these interactions. Additionally, the study intends to analyze the perception of pre-service teachers about effective questioning and feedback and to determine the correlation between the proportions of the types of questioning and feedback positively perceived by the pre-service teachers and of the types of questioning and feedback used during class demonstration. Toward this end, the study analyzed the science class demonstration videos and class evaluation sheets submitted by 38 fourth-year students at the S University of Education. The results are as follows. First, pre-service elementary school teachers generally use close-ended questions during science class demonstrations. Moreover, they predicted that students would primarily provide the correct responses and would not engage in extended interaction by providing immediate feedback for the responses of the majority of the students. Second, pre-service elementary school teachers perceived the utilization of close-ended questions and immediate feedback in science class demonstrations more favorably than they did that of open-ended questions and delayed feedback. The study observed a weak positive correlation between the positive perception of specific types of questions and feedback and the use of such types in class demonstration. The results demonstrated that pre-service elementary school pre-service teachers tend to engage in fragmented verbal interactions during science class demonstrations. They primarily use close-ended questions and immediate feedback. This tendency is seemingly related to their perception of questions and feedback. Therefore, education institutions for training pre-service teachers need to provide opportunities for reflecting on verbal interactions, which tend to involve close-ended questions and immediate feedback. Lastly, assessing the perception of pre-service teachers of questions and feedback is also necessary.

• The Journal of the Korea Contents Association
• /
• v.11 no.1
• /
• pp.72-82
• /
• 2011

This is an experimental research with the theoretical background of agenda setting effect and elaboration likelihood model studying 'whether visual cues such as imagery and subtitle of TV environmental news have effect on the viewers' perception?', 'whether visual cues such as imagery and subtitle of TV environmental news have differential effect on the viewers' perception, depending on the viewers' involvement in the environmental issue?'. This experimental research found that the more highly exposed subjects considers environment issue more important than the less exposed, during the process, visual cues such as imagery and subtitle in TV news have an effect on agenda setting. Futhermore visual cues such as imagery and subtitle have stronger effect on the perception of the less involved than that of the more highly involved as a unified peripheral cue. However the effect of environmental involvement as independent peripheral cue couldn't have meaningful statistical support. Despite the fact that many previous researchers have shown that verbal cues of TV news have effect on the perception of viewers, little attempt has been made to investigate effect of visual cues on the TV viewers' perception. Therefore, this research has an important implication as an early proof in a new stream of visual agenda setting and elaboration research.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.3
• /
• pp.86-95
• /
• 2009

SIFT is an algorithm to extract vectors at pixels around keypoints, in which the pixel colors are very different from neighbors, such as vertices and edges of an object. The SIFT algorithm is being actively researched for various image processing applications including 3D image reconstructions and intelligent vision system for robots. In this paper, we implement a hardware to sift feature detection algorithm for real time processing in embedded systems. We estimate that the hardware implementation give a performance 25ms of $1,280{\times}960$ image and 5ms of $640{\times}480$ image at 100MHz. And the implemented hardware consumes 45,792 LUTs(85%) with Synplify 8.li synthesis tool.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.341-348
• /
• 2022

Formulaic sequences are continuous or discontinuous series of words that are seemingly treated like single units. Formulaic sequences play a key role in language development, and formulaic sequences acquisition determines the success or failure of language development. This study proposes a reading aloud activity as a way for international students to learn formulaic sequences. A class focused on reading aloud was conducted with 41 international students taking a general English course at a university in Seoul. For 15 weeks, video lectures and real-time Zoom classes were conducted in parallel. The animated film Frozen was used as course material. In the video lectures, the teacher interpreted the movie script in easy Korean and read aloud formulaic sequences. Students were tasked with reading the sentences with formulaic sequences aloud, recording themselves reading aloud, and submitting their recordings. During real-time class meetings, students performed the activity of reading aloud the formulaic sequences they had studied in the video lectures. There was a significant increase in the interpretation and sentence writing of formulaic sequences in participants' post-evaluation compared to the pre-evaluation. Through the study's survey, students exhibited positive views in the affective domains.

• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.481-491
• /
• 2013

This paper is introducing on a strategy of storytelling which is utilized as a core skill in developing cultural contents. The proposed storytelling method consists of three steps(planning, production, editing). The method of storytelling strategy is based on rhetoric metaphors and classifies rhetoric metaphors into three kinds of image metaphor, image personification and image simile. This thesis produced and studied 3 visual-image contents including 1 metaphor, 1 personification and 1 simile. As a result, visual-image contents can be a resonable method of the communicational act of visual-image contents with a rhetoric expression. This result will contribute to recognize the possibility of expressing visual-image contents by various figure. Recently, there are a lot of concernments on the expression by creative visual-image contents, but a theoretical study on creative idea for visual-image contents is insufficient. So, in the future, this thesis will be used for basic materials to express a creative visual-image contents, and also contribute to offering basic theories for visual-image contents study and teaching.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.4
• /
• pp.133-142
• /
• 2021

With the recent advancements of deep learning, companies such as smart home, healthcare, and intelligent transportation systems are utilizing its functionality to provide high-quality services for vehicle detection, emergency situation detection, and controlling energy consumption. To provide reliable services in such sensitive systems, deep learning models are required to have high accuracy. In order to develop a deep learning model for analyzing previously mentioned services, developers should utilize the state of the art deep learning models that have already been verified for higher accuracy. The developers can verify the accuracy of the referenced model by validating the model on the dataset. For this validation, the developer needs structural information to document and apply deep learning models, including metadata such as learning dataset, network architecture, and development environments. In this paper, we propose a description language that represents the network architecture of the deep learning model along with its metadata that are necessary to develop a deep learning model. Through the proposed description language, developers can easily verify the accuracy of the referenced deep learning model. Our experiments demonstrate the application scenario of a deep learning description document that focuses on the license plate recognition for the detection of illegally parked vehicles.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.322-327
• /
• 2007

Researchers in the field of psychology used Electroencephalographic (EEG) to record activities of human brain lot many years. As technology develope, neural basis of functional areas of emotion processing is revealed gradually. So we measure fundamental areas of human brain that controls emotion of human by using EEG. Hands gestures such as shaking and head gesture such as nodding are often used as human body languages for communication with each other, and their recognition is important that it is a useful communication medium between human and computers. Research methods about gesture recognition are used of computer vision. Many researchers study emotion recognition method which uses one of physiological signals and gestures in the existing research. In this paper, we use together physiological signals and gestures for emotion recognition of human. And we select the driver emotion as a specific target. The experimental result shows that using of both physiological signals and gestures gets high recognition rates better than using physiological signals or gestures. Both physiological signals and gestures use Interactive Feature Selection(IFS) for the feature selection whose method is based on a reinforcement learning.