• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.976-977
• /
• 2023

본 논문은 시각장애인 안내견이 부족한 상황 개선과 시각장애인에게 안전하고 자유로운 이동을 제공해주는 "시각장애인의 안전한 이동을 도와주는 지능형 카트"를 제안한다. 주요 특징은 다음과 같다. 첫째, 지문 인식 센서를 활용해 지문 등록 후 본인 인증을 하고 압력 센서를 활용해 카트 손잡이를 잡았을 경우에만 카트가 출발하도록 한다. 둘째, 라이다, 카메라를 이용하여 자율 주행 한다. 셋째, 음성인식 통해 목적지 설정, 속도 조절, 경고 알림 기능을 제공한다. 넷째, 짐칸을 설치하여 음성인식으로 여닫을 수 있도록 한다. 다섯째, 앱을 통해 카트 운전 모드를 변경할 수 있다.

• Journal of the HCI Society of Korea
• /
• v.7 no.2
• /
• pp.49-56
• /
• 2012

The camera-based mobile applications such as color, pattern and object reading can improve the living quality of blind people. However currently available camera-based applications are uncomfortable for the blind, since these applications do not reflect accessibility requirements of the blind especially on touch screen. We investigated accessibility requirements about rapidly growing camera-based mobile applications on touch screen devices for the blind. In order to identify accessibility requirements, we conducted a usability testing for color reading applications with three different types of interfaces on Android OS. The results of the usability testing were as follows: (1) users preferred short depth of menu hierarchy, (2) the initial audio help was more useful than just-in-time help, (3) users needed both manual and automatic camera shooting modes although they preferred manual to automatic mode, (4) users wanted the OS supported screen reader function to be turned off during the color reading application was running, and (5) users required tactile feedback to identify touch screen boundary. We designed a new user interface for blind people by applying the identified accessibility requirements. From a usability testing of the new user interface with 10 blind people, we showed that the identified accessibility requirements were very useful accessibility guidelines for camera-based mobile applications.

• Journal of Elementary Mathematics Education in Korea
• /
• v.20 no.3
• /
• pp.479-498
• /
• 2016

Time is important in children's lives since their preschool years. However, previous studies indicate that many children struggle with the acquisition of time concepts. Also teachers do not know how to help them. This study aims to investigate elementary school students' understanding about time and induce its educational implications. To do this, about 130 children from first to fifth grades were tested for their ability to recognize(read and record) the analogue and digital times and to solve elapsed-time problems. The results showed that even first graders were able to read and record the minute times on digital clocks. And second graders were able to read and record the minute times on analogue clocks. Therefore, the ability to recognize analogue times was mastered by second grade. In case of the elapsed-time problems, there was statistically significant difference according to school years or types of problems. Students were successful in solving simple problems. However, the problems that include regrouping hour and minute remained difficult even for the older children. Based on these results, we made a few suggestions for teaching practice about time.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.478-484
• /
• 2009

Automatic speech recognition(ASR) is attractive technique in trend these day that seek convenient life. Although many approaches have been proposed for ASR but the performance is still not good in noisy environment. Now-a-days in the state of art in speech recognition, ASR uses not only the audio information but also the visual information. In this paper, We present a novel lip detection method for visual speech recognition in mobile environment. In order to apply visual information to speech recognition, we need to extract exact lip regions. Because eye-detection is more easy than lip-detection, we firstly detect positions of left and right eyes, then locate lip region roughly. After that we apply K-means clustering technique to devide that region into groups, than two lip corners and lip center are detected by choosing biggest one among clustered groups. Finally, we have shown the effectiveness of the proposed method through the experiments based on samsung AVSR database.

• Journal of the Korean School Mathematics Society
• /
• v.10 no.2
• /
• pp.207-219
• /
• 2007

Students have a hard time with a formal proof, which is one of most important part in mathematics education. They were taught the proof with algebraic visual materials using technology and specialized visual materials. But, they experienced the difficulty in justifying due to the lack of experimental recognition with the representation using technology. The specialized visual materials limited the extension of mathematics thinking of students because it worked only for the case that is fixed. In order to solve this type of problem, we made algebraic visual materials for 9th graders using technology and generalized visual materials so that students experience for themselves to help them to experience experimental justification, thus we recognized that they were improved in enhancing mathematical thinking.

• 전기의세계
• /
• v.33 no.12
• /
• pp.726-734
• /
• 1984

본고에서는 아직도 연구지향의 성격을 띄고 있는 인공지능로보트의 시각시스템에 관해 기술하였고, 이들의 연구를 바탕으로 하여 needs에 답하는 형식인 응용지향인 산업용로보트의 시각시스템에 관해 언급하였다. 끝으로 필자의 연구실에서 발표한 인쇄악보의 인식에 관해 간단히 소개하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.229-230
• /
• 2020

컴퓨터 하드웨어, 소프트웨어의 급속한 발전에도 불구하고 인간의 정보처리능력에 뒤지는 경우도 있다. 이와 같이 인간의 정보처리체계가 어떻게 이런 문제를 해결할 수 있는지에 대한 연구가 활발히 진행 중이다. 본 논문에서는 인간의 시각 정보 처리의 특성에 의한 인지 정보 처리 모델링을 기반으로 학습 가능성을 보이고 일반적인 영상 인식 모델과의 차이를 비교 분석하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.994-995
• /
• 2023

일상생활에서도 불편함을 겪는 시각 장애인들을 위해 기초적인 생활을 보완할 수 있는 음성인식 다용도 계량기를 개발하고자 하였다. 본 제품은 API를 통해 저울의 측정값을 한국어 음성으로 변환하여 출력하는 음성 저울과 음성인식을 통해 슬라이드 포트로 정수기를 제어하는 작동 기기로 구성되어 있다. 현재 음성인식 다용도 계량기 개발을 완료했으며, Web, APP 등의 개선 방안을 연구 및 적용하는 중에 있다. 본 계량기를 통하여 시각장애인·시력저하자의 일상생활 및 삶의 질 향상뿐만 아니라 병원 등의 공공시설 개선에도 도움을 줄 수 있을 것으로 기대된다.

• Journal of Science and Technology Studies
• /
• v.10 no.2
• /
• pp.107-141
• /
• 2010

Visualization techniques are transformed into reliable representations through socio-technological processes which include the agreement on the instrument and the embodiment of practices in relevant scientific communities. Visual representations thus produced are justified by realistic and epistemic virtues in science. This paper analyzes different visual images presented in the scientific papers of two research groups who argue different theories about the mechanism of face perception. These two scientific groups use the same fMRI technology; yet, different experimental paradigms and visual stimuli change their hypotheses into distinct testable theories, which in turn lead to different evidences to support their own theories. Visual evidences are intermediate representations which lie between fMRI brain images and scientific theories, and theoretical models obtain the scientific value based on the consistency in the chain of visual representations. This study shows that representations in science tend to be good representations within the context of scientific communities. It will provide a chance to think of the value and limit of the scientific knowledge

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.5
• /
• pp.1996-2001
• /
• 2012

Visual inspection systems are widely proposed for the well formed surface materials like electronics parts. But the materials with ill reflection ability have many troubles when visual inspection system is introduced. We have developed a robust visual inspection system that can work well in spite of low reflection ratio and with much noise when truth model is not known in the mixed production line. A workpiece identification technique using k-means has been proposed to identify the type. Based on the identified type, a robust-to-noise segmentation method, called active contour, has been applied to segment the features from the image. Finally, Kalman filter has been applied to adapt the error variation. Experiment shows that performance is about to match the accuracy of manual measurement using projectors.