• Journal of KIISE:Software and Applications
• /
• v.30 no.1_2
• /
• pp.93-102
• /
• 2003

A slant correction method for handwritten Korean strings based on analysis of stroke distribution, which effectively reflects structural properties of Korean characters, is presented in this paper. The method aims to deal with typical problems which have been frequently observed in slant correction of handwritten Korean strings with conventional approaches developed for English/European languages. Extracted strokes from a line of text image are classified into two clusters by applying the K-means clustering. Gaussian modeling is applied to each of the clusters and the slant angle is estimated from the model which represents the vertical strokes. Experimental results support the effectiveness of the proposed method. For the performance comparison 1,300 handwritten address string images were used, and the results show that the proposed method has more superior performance than other conventional approaches.

• Journal of The Korean Association For Science Education
• /
• v.40 no.6
• /
• pp.611-620
• /
• 2020

The purpose of the study is to find creativity factors of students in the process of small group modeling and relate them to the types of interactions among students. In order to capture students' detailed interactions, this study was conducted as an 'essential case study' through qualitative analysis. We have developed the modules of nine lessons about terraforming, and they were used in an actual classroom. In order to understand the creativity of the students in the process of modeling, students' discourses and interview data were analyzed using 19 creative factors or abilities. The findings are as follows. Frequently found creativity factors are Elaboration, Evaluation, Visualization, Resist premature closer, Originality, Analysis and Concentration. And students' interactions that affect students' creativity in the process of modeling can be classified into four categories: Suggestion, Agreement, Questioning, Refutation, and Conversion. Through each interaction, students demonstrated the process of expressing and modifying their own thoughts and ideas in the modeling process. The findings of the study suggest that it is important to the teachers to understand types of interactions among students and the relationship between the types of interaction and creativity factors for students' creative modeling in modeling-based learning.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.1
• /
• pp.162-172
• /
• 2015

In this paper, we propose an adaptive detection algorithm of footstep and a classification algorithm for activities of the detected footstep. The proposed algorithm can detect and classify whole movement as well as individual and irregular activities, since it does not use continuous footstep signals which are used by most previous research. For classifying movement, we use feature vectors obtained from frequency spectrum from FFT, CWT, AR model and image of AR spectrogram. With SVM classifier, we obtain classification accuracy of single footstep activities over 90% when feature vectors using AR spectrogram image are used.

• Convergence Security Journal
• /
• v.8 no.4
• /
• pp.161-166
• /
• 2008

This paper proposes a new approach to align 3D data sets by using curvatures of feature surface. We use the Gaussian curvatures and the covariance matrix which imply the physical characteristics of the model to achieve registration of unaligned 3D data sets. First, the physical characteristics of local area are obtained by the Gaussian curvature. And the camera position of 3D range finder system is calculated from by using the projection matrix between 3D data set and 2D image. Then, the physical characteristics of whole area are obtained by the covariance matrix of the model. The corresponding points can be found in the overlapping region with the cross-projection method and it concentrates by removed points of self-occlusion. By the repeatedly the process discussed above, we finally find corrected points of overlapping region and get the optimized registration result.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.3
• /
• pp.70-77
• /
• 2017

Recently, Internet of Things (IoT) and deep learning techniques have affected video surveillance systems in various ways. The surveillance features that perform detection, tracking, and classification of specific objects in Closed Circuit Television (CCTV) video are becoming more intelligent. This paper presents real-time algorithm that can run in a PC environment using only a low power CPU. Traditional tracking algorithms combine background modeling using the Gaussian Mixture Model (GMM), Hungarian algorithm, and a Kalman filter; they have relatively low complexity but high detection errors. To supplement this, deep learning technology was used, which can be trained from a large amounts of data. In particular, an SRGB(Sequential RGB)-3 Layer CNN was used on tracked objects to emphasize the features of moving people. Performance evaluation comparing the proposed algorithm with existing ones using HOG and SVM showed move-in and move-out error rate reductions by 7.6 % and 9.0 %, respectively.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.684-691
• /
• 2001

In this paper, we design and implement a system which recognizes and tracks a human head on a sequence of images. In this paper, the color of the skin and ellipse modeling is used as feature vectors to recognize the human head. And the modified time-varying edge detection method and the vertical projection method is used to acquire regions of the motion from images with very complex backgrounds. To select the head from the acquired candidate regions, the process for thresholding on the basis of the I-component of YIQ color information and mapping with ellipse modeling is used. The designed system shows an excellent performance in the cases of the rotated heads, occluded heads, and tilted heads as well as in the case of the normal up-right heads. And in this paper, the combinational technique of motion-based tracking and recognition-based tracking is used to track the human head exactly even though the human head moves fast.

• Journal of Broadcast Engineering
• /
• v.6 no.1
• /
• pp.50-57
• /
• 2001

A digital watermarking is a newly developed scheme to embed invisible or inaudible information Into the host data in order to insist the copyright of the owner or the creator. This paper describes a robust data embedding scheme that employs inner product and adaptive quantization. Compared to the previous works for digital watermarking, our proposed scheme can embed relatively large amount of Information, since a secrete key Is not directly relaxed to the watermark data. A secret key is used for the design of random direction vectors. which are taken Inner product with the DCT transformed feature set data. In odder to achieve robustness against malicious attacks. we exploit the Properties of human visual system In designing the random direction vectors which behave as embedded noises. Experimental results show that we can recover the embedded information without utilizing the original host data. We also demonstrate that the ownership assertion is possible even though The watermarked data may undergo common signal processing operations, such as JPEG compression. clopping. and filtering.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.8
• /
• pp.309-314
• /
• 2014

To generate a complete 3D model from depth images of multiple RGB-D cameras, it is necessary to find 3D transformations between RGB-D cameras. This paper proposes a convenient view calibration technique using a spherical object. Conventional view calibration methods use either planar checkerboards or 3D objects with coded-pattern. In these conventional methods, detection and matching of pattern features and codes takes a significant time. In this paper, we propose a convenient view calibration method using both 3D depth and 2D texture images of a spherical object simultaneously. First, while moving the spherical object freely in the modeling space, depth and texture images of the object are acquired from all RGB-D camera simultaneously. Then, the external parameters of each RGB-D camera is calibrated so that the coordinates of the sphere center coincide in the world coordinate system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.1-11
• /
• 2004

In this paper we proposed a hierarchical ASM for real-time tracking of non-rigid objects. For tracking an object we used ASM for estimating object contour possibly with occlusion. Moreover, to reduce the processing time we used hierarchical approach for real-time tacking. In the next frame we estimated the initial feature point by using Kalman filter. We also added block matching algorithm for increasing accuracy of the estimation. The proposed hierarchical, prediction-based approach was proven to out perform the exiting non-hierarchical, non-prediction methods.

• Proceedings of the KAIS Fall Conference
• /
• 2006.05a
• /
• pp.513-516
• /
• 2006

인터넷의 발달로 인터넷 사용자는 기하급수적으로 증가하게 되었으며, 인터넷을 기반으로 하는 수많은 응용프로그램들이 개발되고 있다. 인터넷상에는 수많은 사이트(site)들이 존재하며 방문자들의 주목을 받기 위하여 여러 가지 기법을 선보이고 있다. 그러나 컴퓨터상의 정적인 2차원 평면하에서는 현실감 및 입체감을 경험하는 것이 한계가 있다. 따라서 플래시(flash)와 같은 플러그인(plug-in) 및 동영상을 도입하여 동적인 컨텐츠를 제공하는 사례가 늘고 있으며 한편으로 최근 가상현실(Virtual Reality) 기법을 이용한 사이트들이 점차 증가하고 있는 추세이다. 가상현실은 컴퓨터가 제공하는 3차원의 컴퓨터 그래픽 기술을 이용하여 사용자와 온라인으로 상호대화를 하는 기법이라고 간단히 정의할 수 있다[2,3]. 가상현실을 이용하여 3차원 실시간 구현 기술을 웹에 적용시킴으로서 3차원 공간에서 현실감을 느낄 수 있게 함과 동시에 입체적인 정보를 사용자에게 제공할 수 있게 하는 기법들이 속속 선보이게 되었다. 현재 다양한 인터넷 기반 3차원 가상 현실 기술이 각각 서로 다른 기술 및 특징들을 가지고 나와 있다. 3차원 가상 공간을 구현한다. 선택한 물체에 사진 이미지기반 방식과 3차원 모델링 방식을 모두 적용하여 보다 현실감 있고 모든 방향으로의 접근이 가능하도록 하며. 또한 3차원 사운드 및 동영상도 함께 제공하며 가상 공간과 인간의 실질적 교감을 현실화 시키는 인터페이스를 제시하는 데에 연구의 목적이 있다.