• Korean Institute of Interior Design Journal
• /
• v.15 no.6 s.59
• /
• pp.205-212
• /
• 2006

The premise of this study is that an ultimate objective in planning an exhibition space is spectators' experiences shaped by a result of their first-hand experiences and responses within an exhibition space, and this result can be recognized in the spectators' movement. Thus, the sign system that can directly affects viewers' main line of flow and movement patterns was examined vis--vis a mutually complementary relation in a triangular composition with the structure of exhibition space and the exhibition contents. Based on the findings, predictive values before and after a complementary application of the sign system to the structure of exhibition space was analyzed and its validity was assessed. The results of this research analysis were drawn as follows. It was shown that an understanding of the locations of direction signs and the degree of recognition can function as an important factor to predict viewers' movement, along with an understanding of topological characteristics of an exhibition space. In terms of the connection and disconnection of space units that form the space structure, it suggests that the distribution of signs and the degree of recognition can adjust the degree of connection and disconnection. Even though exhibition spaces for research subjects were selected from a relatively large number of museums, but the research was limited with a focus on the structure of exhibition space and sign systems. Thus, it is proposed that future studies should be conducted by including varieties of exhibition and environmental factors.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.3
• /
• pp.140-147
• /
• 2024

In the Republic of Korea, people with hearing impairments are the second-largest demographic within the registered disability community, following those with physical disabilities. Despite this demographic significance, research on sign language translation technology is limited due to several reasons including the limited market size and the lack of adequately annotated datasets. Despite the difficulties, a few researchers continue to improve the performacne of sign language translation technologies by employing the recent advance of deep learning, for example, the transformer architecture, as the transformer-based models have demonstrated noteworthy performance in tasks such as action recognition and video classification. This study focuses on enhancing the recognition performance of sign language translation by combining transformers with 3D-CNN. Through experimental evaluations using the PHOENIX-Wether-2014T dataset [1], we show that the proposed model exhibits comparable performance to existing models in terms of Floating Point Operations Per Second (FLOPs).

• Transactions on Control, Automation and Systems Engineering
• /
• v.2 no.1
• /
• pp.47-55
• /
• 2000

In this paper, a vision-based roadway detection algorithm for an automated vehicle control system, based on roadway sign information on roads, is proposed. First, in order to detect roadway signs, the color scene image is enhanced under hue-invariance. Fuzzy logic is employed to simplify the enhanced color image into a binary image and the binary image is morphologically filtered. Then, an effective algorithm of locating signs based on binary rank order transform (BROT) is utilized to extract signs from the image. This algorithm performs better than those previously presented. Finally, the inner shapes of roadway signs with curving roadway direction information are recognized by neural networks. Experimental results show that the new detection algorithm is simple and robust, and performs well on real sign detection. The results also show that the neural networks used can exactly recognize the inner shapes of signs even for very noisy shapes.

• Proceedings of the KSR Conference
• /
• 2006.11b
• /
• pp.1567-1574
• /
• 2006

To prevent safety accidents such as injury or death from falling by blocking platforms from trains, the Seoul Metropolitan Subway Corp. have gradually installed screen doors in platforms of 115 subway stations in Seoul on lines 1, 2, 3, and 4. Installation in nine areas among those has been completed and screen doors are being operated as a model operation. Traffic signs should be clear for users. The essential functions of signs should be fully investigated from the aspect of user as well as the visual beauty and recognition. Signs should be able to provide users with information regarding location, position, directions, etc. Particularly, safety and convenient signs should be visually and sensually correlated. However, the entire screen doors in platforms installed in line 2 subway in Seoul are used for commercial advertisement, consequently, the functions and roles as public signs are not fulfilled aggravating inconvenience for users. In this study, cases have been studied to investigate requirements for user-oriented sign system in platform and public sign space to fulfill the functions of sign system in platform. Using an anthropometry approach, the study aimed to obtain the space to install the sign system and to systemize necessary and sufficient conditions for user-oriented system for platform in which screen doors have been installed using. The study suggests fundamental information to obtain the space of public sign system on the entire screen door.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.517-521
• /
• 2008

Hand motion classification problem is considered as basis for sign or gesture recognition. We promote optical flow as main feature extracted from images sequences to simultaneously segment the motion's area by its magnitude and characterize the motion' s directions by its orientation. We manage the flow orientation histogram as motion descriptor. A motion is encoded by concatenating the flow orientation histogram from several frames. We utilize simple histogram matching to classify the motion sequences. Attempted experiments show the feasibility of our method for hand motion localization and classification.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.01a
• /
• pp.205-208
• /
• 2012

지하철 실내의 표지판은 다양한 정보들을 포함하고 있다. 그 중에서 시설물의 형상을 단순화하여 나타낸 픽토그램 사인은 국제적으로 표준화 되어 있어 검출이 용이하다고 볼 수 있다. 일반적으로 객체를 인식하는 방법은 후보영역을 설정하는 검출단계와 후보영역을 인식하는 단계로 나뉘어 진다. 본 논문에서는 후보영역 검출단계에서 단일 값을 가지는 이진화로 픽토그램 영역이 분리가 잘 안되는 문제점을 해결하기 위하여 적응적 이진화를 사용하였고 인식을 위한 특징추출로 HOG서술자를 사용하고 학습과 인식에는 SVM을 사용하였다. 실험 결과를 통하여 HOG서술자로 픽토그램 사인을 인식하는 것이 적합한 것인지 확인한다.

• Korean Journal of Computational Design and Engineering
• /
• v.14 no.1
• /
• pp.42-49
• /
• 2009

Virtual manufacturing technology has been applied in actual production sites with the development of virtual reality technology. However, the current virtual manufacturing technology requires experts for application of the system. Furthermore, the sense of reality is diminished as the entire simulation is driven by virtual objects. In contrast, mixed reality can visualize virtual objects and an actual work place simultaneously, and thus the sense of reality of the virtual manufacturing simulation can be improved. This paper introduces a method that applies mixed reality in the manufacturing process, and proposes a method to adapt general safety sign post in the factory instead of a black square marker for visual fiducial recognition.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.07a
• /
• pp.323-326
• /
• 2014

본 논문에서는 깊이 카메라를 이용한 사용자의 손 모양, 특히 수화를 인식하는 방법에 대해 제안한다. 손 모양 인식은 손가락 검출과 손 인식으로 크게 2가지로 나눌 수 있다. 손가락 검출을 위해 본 시스템에서는 Distance Transform을 이용하여 손의 뼈대를 검출 하고, Convex Hull을 통해 손가락을 검출하는 방법을 제안한다. 뼈대 검출은 보다 정확한 손가락을 검출할 수 있는 장점이 생긴다. 손 인식에는 손 중심과 손가락의 길이, 손의 축, 손가락의 축, 팔 중심의 위치 등을 이용하여 Decision Tree를 생성하고, 반복적 검사를 통해 인식의 오류율을 줄였다. 실험결과에서는 수화 인식이 성공적으로 잘 인식 되었다는 것을 보인다.

• Proceedings of the KSR Conference
• /
• 2003.05a
• /
• pp.176-184
• /
• 2003

Railway sign(graphic sign, diagraphics) designs require good recognition with universality to transmit accurate and speedy information as they connect people around the station and other transport systems. An important point of signs is how to design and deliver the contents to the viewers as a communication service tools. It needs to establish design guidelines with standardization and unified system to show their contents and images clearly like common language with visuality, attractivity and generality. These requisites are important for both aesthetics legibility and unified standards to maximize the effectiveness of pictograms for the use of the general public, who require systematic suggestion and management.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.772-774
• /
• 2005

간판인식은 관광지의 간판을 자동 인식하여 외국인 또는 외지인에게 편리한 관광 정보제공을 목적으로 연구되고 있다. 이러한 연구의 효율적인 진행을 위해 객관적인 간판영상 데이터베이스가 필수적이다. 이 논문은 전주 한옥마을을 대상으로 수집한 간판영상 데이터베이스에 대해 기술한다. 총 45개의 서로 다른 간판에 대해 각각 50개씩 영상을 다양한 조건에서 획득하였다.