• Journal of the Korea Society of Computer and Information
• /
• v.23 no.9
• /
• pp.1-6
• /
• 2018

In this paper, we propose a method dividing effectively the hand and fingers using general webcam. The method executes 4 times empirically preprocessing one to erase noise. First, it erases the overall noise of the image using Gaussian smoothing. Second, it changes from RGB image to HSV color model and YCbCr color model, executes a global static binarization based on the statistical value for each color model, and erase the noise through bitwise-OR operation. Third, it executes outline approximation and inner region filling algorithm using RDP algorithm and Flood fill algorithm and erase noise. Lastly, it erases noise through morphological operation and determines the threshold propositional to the image size and selects the hand and fingers area. This paper compares to existing one color based hand area division method and focuses the noise deduction and can be used to a gesture recognition application.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.171-172
• /
• 2009

Nowadays the music market is getting bigger while students are losing their creativity because of the cramming education even in the music class. Based on the growing music market, we made a project for students to play the musical instruments more easily. The suggested program is different from any other system because, with this program, we can play the musical instruments if only we have a keyboard made of paper and Webcam, which made us save money. When an user put his finger on the paper keyboard, Webcam makes a sound recognizing the position of the finger on the keyboard. We can choose one instrument out of four; Piano, drum, base and guitar. With this system, we can get an opportunity to learn many sounds of musical instruments and make our own melody.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.285-294
• /
• 2021

This study developed a responsive healthcare system that users can easily use in real life to prevent turtle neck syndrome by posture correction. We propose a system that naturally induces direct posture improvement by adjusting the height with a responsive cradle through a turtle neck discrimination algorithm detecting the turtle neck posture in real time using a webcam. The turtle neck algorithm was developed based on machine learning, using the points that the distance relationship between the jaw line and the shoulder varies depending on the posture. For the younger age group, which is particularly problematic due to the increase in the use of IT devices, image data in different situations according to the height and posture of the cradle was collected and learned as a support vector machine classifier. In addition, a height-adjustable cradle that can support a laptop has been created and expanded into a responsive cradle that can be controlled with software by interlocking with the Arduino. Therefore, this service enables posture correction of many modern people suffering from turtle neck syndrome and will become an essential platform in the increasing online environment in the non-contact era.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.3
• /
• pp.245-251
• /
• 2023

Facial expression recognition plays a significant role in understanding human emotional states. With the advancement of AI and computer vision technologies, extensive research has been conducted in various fields, including improving customer service, medical diagnosis, and assessing learners' understanding in education. In this study, we develop a model that can infer emotions in real-time from a webcam using transfer learning with TensorFlow.js and MobileNet. While existing studies focus on achieving high accuracy using deep learning models, these models often require substantial resources due to their complex structure and computational demands. Consequently, there is a growing interest in developing lightweight deep learning models and transfer learning methods for restricted environments such as web browsers and edge devices. By employing MobileNet as the base model and performing transfer learning, our study develops a deep learning transfer model utilizing JavaScript-based TensorFlow.js, which can predict emotions in real-time using facial input from a webcam. This transfer model provides a foundation for implementing facial expression recognition in resource-constrained environments such as web and mobile applications, enabling its application in various industries.

• Proceedings of the KAIS Fall Conference
• /
• 2010.11a
• /
• pp.88-91
• /
• 2010

최근 무선통신 기술의 발당과 인터넷의 발달로 웹캠을 활용하여 얼굴인식, 몸동작 인식, 제스처 인식 등의 연구가 활발히 진행되고 있다. 본 연구에서는 웹캠으로부터 입력되는 손동작 동영상을 처리하여 수화 패턴 신호를 인식하는 손동작 인식 알고리즘을 제안한다. 제안방법은 프레임간의 차 연산을 이용하여 움직이는 오브젝트를 추출하고, YCbCr로 변환하여 손 모양 영역을 추출하여 특정 크기의 정규화 영상으로 변화하며, 정규화 영상의 오브젝트의 무게중심점을 기준으로 원의 반지름을 결정하고 원을 탐색하여 손가락의 펴짐과 굽힘에 대한 패턴 비교를 통하여 손 모양을 인식한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11c
• /
• pp.2281-2284
• /
• 2002

최근 내장형 리눅스(Embedded Linux)에 대한 연구가 활발하게 이루어지고 있다. 그중에 내장형 리눅스를 이용한 감시 카메라는 DVR(Digital Video Recorder) 시스템과 카메라와 내장형 보드가 합체된 일체형 카메라를 개발하는 부분으로 연구가 진행 중이다. 본 연구는 내장형 리눅스를 바탕으로 한 웹캠을 이용한 인터넷상에서 감시시스템을 컴퓨터상에서 구현해 봄으로서 웹캠의 구조와 감시 시스템에 대한 연구이다. 내장형 리눅스를 이용한 웹캠은 인터넷을 통한 원격 감시와 DVR 서버를 통한 영상 편집, 제공을 할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.1006-1007
• /
• 2014

본 시스템은 웹캠을 통해 렌더링한 영상을 통해 화재를 감지하는 기술에 관한 것으로, 더욱 상세하게는 whitecount 알고리즘을 이용한 화재인식에 관한 것이다. 서버를 개설하여 화재가 감지되면 서버에 실시간으로 사진을 저장하고 화재 감지 시 관리자 또는 119에 자동으로 신고할 수 있는 시스템이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.549-551
• /
• 2012

본 논문에서는 기존의 화소값 차영상 기법이 저속으로 움직이는 물체의 동작정보 감지에 취약한 점을 보완하기 위하여 실시간 영상 처리를 목적으로 연속된 프레임(Frame)에서 움직임이 있는 프레임을 찾아내고, 움직임 영역을 추출하는 움직임 검출에 관한 연구를 통해 웹캠 기반의 객체 감지시스템을 제안하였다. 제안 시스템은 단일 객체뿐 아니라 다중 객체의 움직임까지 파악할 수 있다는 장점을 가지고 있다.

• The Journal of the Korea Contents Association
• /
• v.20 no.7
• /
• pp.47-55
• /
• 2020

Along with the increased use of smart devices, the incidence of turtle neck syndrome among modern people has increased. Turtle neck syndrome is a posture in which the head is forward compared to the torso due to longer front muscles in the neck and shorter upper muscles, and it is more effective to fix the usual posture habits than surgery or medication. Thus, in this paper, a system is proposed to detect and warn posture that can cause turtle neck syndrome in real time. Image data of correct posture and turtle neck posture are collected to create a CNN-based learning model. Using only the webcam(Built-in camera), the sitting position that enters the camera is verified in real time through the learning model, and if it is a turtle neck position, it generates a warning sound and induces the correct posture. The system can induce people to correct their usual posture habits to treat turtle neck syndrome and prevent more serious diseases such as neck discs.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.4
• /
• pp.1849-1856
• /
• 2012

This paper proposes a method to track the center of pupil and perform the remote control for interface based on the substituted commands according to movements of pupil under smart phone environment. The proposed method, which is a remote control through the movement of eyes, may be helpful for the handicapped people or users who want a more convenient input method. A method based on webcam, which is representative one among the previous methods to track pupil of user, has a few limitations on distance and angle between location of user and webcam. However, this paper uses smart phone that is convenient to carry. The proposed method can perform the remote control through tracking of pupil using wireless network without any restriction on the location of users. Thus, the method is effectively applied for controlling the smart TV that should be controlled on the distance as well as the remote control for PC.