• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.2
• /
• pp.1-8
• /
• 2001

In this paper, we propose an algorithm which estimates the displacements and velocities of objects in the soccer field from the soccer image sequences. Assuming the time interval of an object movement is given, we transform the object positions into those in the soccer field model and compute the distance and the velocity. When four corresponding pairs of the feature points, such as the crossing points of the lines in the soccer field, exist and three of them are not on a line, we transform the object positions in the soccer image into those in the soccer field by using the perspective displacement field model. In addition, when the soccer image has less than four feature points, we first transform the object positions into those in the image which has more than four feature points, and then transform the positions into those in the soccer field again. To find the coordinate transformation between two images, we estimate the panning and zooming for consecutive images in the sequence. In the experimental results, we quantitatively evaluated the estimation accuracy by applying our algorithm to the synthetic. soccer image sequences generated by graphic tools, and applied it to the real soccer image sequences for broadcasting to show its usefulness.

• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.420-438
• /
• 2004

Artificially or naturally contained texts in the natural images have significant and detailed information about the scenes. If we develop a method that can extract and recognize those texts in real-time, the method can be applied to many important applications. In this paper, we suggest a new method that extracts the text areas in the natural images using the low-level image features of color continuity. gray-level variation and color valiance and that verifies the extracted candidate regions by using the high-level text feature such as stroke. And the two level features are combined hierarchically. The color continuity is used since most of the characters in the same text lesion have the same color, and the gray-level variation is used since the text strokes are distinctive in their gray-values to the background. Also, the color variance is used since the text strokes are distinctive in their gray-values to the background, and this value is more sensitive than the gray-level variations. The text level stroke features are extracted using a multi-resolution wavelet transforms on the local image areas and the feature vectors are input to a SVM(Support Vector Machine) classifier for the verification. We have tested the proposed method using various kinds of the natural images and have confirmed that the extraction rates are very high even in complex background images.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.1 s.307
• /
• pp.55-66
• /
• 2006

We propose a progressive image retrieval method based on an efficient combination of multiresolution color and torture features in wavelet transform domain. As a color feature, color autocorrelogram of the hue and saturation components is chosen. As texture features, BDIP and BVLC moments of the value component are chosen. For the selected features, we obtain multiresolution feature vectors which are extracted from all decomposition levels in wavelet domain. The multiresolution feature vectors of the color and texture features are efficiently combined by the normalization depending on their dimensions and standard deviation vector, respectively, vector components of the features are efficiently quantized in consideration of their storage space, and computational complexity in similarity computation is reduced by using progressive retrieval strategy. Experimental results show that the proposed method yields average $15\%$ better performance in precision vs. recall and average 0.2 in ANMRR than the methods using color histogram color autocorrelogram SCD, CSD, wavelet moments, EHD, BDIP and BVLC moments, and combination of color histogram and wavelet moments, respectively. Specially, the proposed method shows an excellent performance over the other methods in image DBs contained images of various resolutions.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.561-571
• /
• 2020

Seven techniques widely used in the geodetic transformations have been reviewed and compared to figure out their theoretical characteristics. A series of numerical tests were performed about four data sets. This was followed by result analyses in terms of transformation residuals and accuracies together with some hypothesis testings based on the student-t distribution to confirm the statistical significance of the techniques. In the case of the transformation between the geodetic frames implemented in the same system, no statistical significance was revealed in the results of the 3D transformation techniques, even if the testing area becomes large as the Asia-Oceania continent. Among the 2D transformations, it was possible for the NTv2 grid modeling technique to deliver improved transformation accuracy. Finally, it was possible from the results analyzed in this study to propose the Helmert transformation to geodetic control points and the NTv2 technique to the 2D spatial data transformation of the geodetic systems.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.4
• /
• pp.727-732
• /
• 2012

This paper presents an approach to classify normal and arrhythmia from the MIT-BIH Arrhythmia Database using Discrete Cosine Transform(DCT), Discrete Wavelet Transform(DWT) and neural network. In the first step, Discrete Cosine Transform is used to obtain the representative 15 coefficients for input features of neural network. In the second step, Discrete Wavelet Transform are used to extract maximum value, minimum value, mean value, variance, and standard deviation of detail coefficients. Neural network classifies normal and arrhythmia beats using 55 numbers of input features, and then the accuracy rate is 98.8%.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.348-351
• /
• 2004

In this paper, we propose the face recognition method using Harr wavelet transform and 2D PCA. While previous PCA computed the covariance matrix by using one dimensional vectors, 2D PCA computed the covarinace matrix by using direct two dimensional image and extracted feature vector by solving eigenvalue problem. To gain the face image having the low dimension and robust property, the proposed method uses wavelet transformation. We apply the LL band image data to 2D PCA for face recognition. The experimental results indicate that our method improves recognition rate than 2D PCA into original image.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.137-140
• /
• 2003

캐리커처의 일반적인 의미는 어떤 사람이나 사물의 특징을 추출하여 익살스럽게 풍자한 그림이나 글이다. 다시 말해, 캐리커처는 사람의 얼굴에서 특징을 잡아 과장하거나 왜곡하여 그린 데생이라고 한다. 컴퓨터를 이용한 기존의 캐리커처 제작방법으로는, 입력 이미지 좌표의 통계적인 차이값을 이용하는 PICASSO System 방법[1], 제작자의 애매한 느낌을 퍼지 논리를 이용하여 표현하는 방법, 이미지를 와핑하는 방법, 여러 단계의 벡터 필드 변환을 이용하는 방법등이 연구되어 왔다. 본 논문에서는 실시간 또는 준비된 영상을 입력으로 받아 저장한 후, 네 단계의 과정으로 처리한 후 최종적으로 캐리커처된 이미지를 생성하게 된다. 각 단계별 처리 내용으로는 첫번째 단계에서는 영상에서 얼굴을 검출하고 두번째 단계에서는 특정 얼굴부위의 기하학적 정보를 좌표값으로 추출한다. 세번째 단계에서는 전 단계에서 얻은 좌표값으로 로컬 와핑 기법을 이용하여 영상을 변환한다. 네 번째 단계에서는 변형된 영상으로 퍼지 논리를 이용하여 보다 개선된 윤곽선 이미지로 변환하여 캐리커처 이미지를 얻는다. 본 논문에서는 영상 인식, 변환 및 윤곽선 검출 및 둥의 여러 가지 영상 처리 기법을 이용하여 기존의 캐리커처 제작 방식보다 간단하고, 복잡한 연산 과정이 없는 캐리커처 제작 시스템을 구현하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.2
• /
• pp.112-123
• /
• 1990

This paper presents a vertex-detecting of Hanguel patterns using nested contour shape. Inputed binary character patterns are transformed by distance transformation method and make a new file of transferred data by analysis of charactersitcs. A new vertex-detecting algorithm for recognizing Hanguel patterns using the two data files is proposed. This algorithm is able to reduce the projecting parts of Hanguel pattern, separate the connecting parts between different strokes, set the code number by transformed value of coorked features. It makes the output of results in order to apply the Hanguel recognition.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.221-232
• /
• 2012

The double-density discrete wavelet transform(DWT) is an improvement upon the critically sampled DWT with important additional properties. It employs one scaling function and two distinct wavelets, which are designed to be offset from one another by one half. And it is overcomplete by a factor of two. Also, this transformation is nearly shift-invariant. But there is room for improvement because not all of the wavelets are directional. That is, although the double-density DWT utilizes more wavelets, some lack a dominant spatial orientation, which prevents them from being able to isolate those directions. Proposed method is a DWT that combines the double-density DWT and quincunx sampling, each of which has its own characteristics and advantages. Especially, the quincunx sampling treats the different directions more homogeneously. As a result, since proposed method can generate sub-images of multiple degrees rotated versions, this method provides an improved performance in image processing fields.

• Journal of Broadcast Engineering
• /
• v.13 no.5
• /
• pp.707-718
• /
• 2008

We derive a modified version of the cubic convolution scaler to enlarge or reduce the size of digital image with arbitrary ratio. To enhance the edge information of the scaled image and to obtain a high-quality scaled image, the proposed scaler is applied along the direction of an edge. Since interpolation along the direction of an edge has to process nonuniformly sampled data, the kernel of the cubic convolution scaler is modified to interpolate the data. The proposed scaling scheme can be used to resize pictures in various formats in a transcoding system that transforms a bit stream compressed at one bit rate into one compressed at another bit rate. In many applications, such as transcoders, the resolution conversion is very important for changing the image size while maintaining high quality of the scaled image. We show experimental results that demonstrate the effectiveness of the proposed interpolation method. The proposed scheme provides clearer edges, without artifacts, in the resized image than do conventional schemes. The algorithm exhibits significant improvement in the minimization of information loss when compared with the conventional interpolation algorithms.