• Journal of the Korea Computer Industry Society
• /
• v.10 no.5
• /
• pp.227-234
• /
• 2009

The Paper introduces a new technique for block matching motion estimation. since the temporal correlation of a animation sequence between the motion vector of current block and the motion vector of previous block. In this paper, we propose the scene change detection algorithm for block matching using the temporal correlation of the animation sequence and the center-biased property of motion vectors. The proposed algorithm determines the location of a better starting point for the search of an exact motion vector using the point of the smallest SAD(sum of absolute difference) value by the predicted motion vector from the same block of the previous frame and the predictor candidate point on each search region. Simulation results show that the PSNR values are improved as high as 9~32% in terms of average number of search point per motion vector estimation and improved about 0.06~0.21dB on an average except the FS(full search) algorithm.

• The Journal of the Acoustical Society of Korea
• /
• v.33 no.6
• /
• pp.400-406
• /
• 2014

This paper describes a robust watermark decoding model using a SVM(Support Vector Machine). First, the embedding process is performed inversely for a watermarked signal. And then the watermark is extracted using the proposed model. For SVM training of the proposed model, data are generated that are watermarks extracted from sounds containing watermarks by four different embedding schemes. BER(Bit Error Rate) values of the data are utilized to determine a threshold value employed to create training set. To evaluate the robustness, 14 attacks selected in StirMark, SMDI and STEP2000 benchmarking are applied. Consequently, the proposed model outperformed previous method in PSNR(Peak Signal to Noise Ratio) and BER. It is noticeable that the proposed method achieves BER 1% below in the case of PSNR greater than 10 dB.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.195-201
• /
• 2015

For median filtering (MF) detection in altered digital images, this paper presents a new feature vector that is formed from autoregressive (AR) coefficients via an AR model of the gradients between the neighboring row and column lines in an image. Subsequently, the defined 10-D feature vector is trained in a support vector machine (SVM) for MF detection among forged images. The MF classification is compared to the median filter residual (MFR) scheme that had the same 10-D feature vector. In the experiment, three kinds of test items are area under receiver operating characteristic (ROC) curve (AUC), classification ratio, and minimal average decision error. The performance is excellent for unaltered (ORI) or once-altered images, such as $3{\times}3$ average filtering (AVE3), QF=90 JPEG (JPG90), 90% down, and 110% up to scale (DN0.9 and Up1.1) images, versus $3{\times}3$ and $5{\times}5$ median filtering (MF3 and MF5, respectively) and MF3 and MF5 composite images (MF35). When the forged image was post-altered with AVE3, DN0.9, UP1.1 and JPG70 after MF3, MF5 and MF35, the performance of the proposed scheme is lower than the MFR scheme. In particular, the feature vector in this paper has a superior classification ratio compared to AVE3. However, in the measured performances with unaltered, once-altered and post-altered images versus MF3, MF5 and MF35, the resultant AUC by 'sensitivity' (TP: true positive rate) and '1-specificity' (FN: false negative rate) is achieved closer to 1. Thus, it is confirmed that the grade evaluation of the proposed scheme can be rated as 'Excellent (A)'.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.11C
• /
• pp.940-947
• /
• 2010

Motion Compensated Frame Interpolation(MCFI) has been used to reduce motion jerkiness for dynamic scenes and motion blurriness for LCD-panel display as post processing for high quality display. However, MCFI that directly uses the motion information often suffers from annoying artifacts such as blockiness, ghost effects, and deformed structures. So in this paper, we propose a novel edge-based adaptively weighted vector median filter as post-processing. At first, the proposed method generates an edge direction map through a sobel mask and a weighted maximum frequent filter. And then, outlier MVs are removed by average of angle difference and replaced by a median MV of $3{\times}3$ window. Finally, weighted vector median filter adjusts the weighting values based on edge direction derived from spatial coherence between the edge direction continuity and motion vector. The results show that the performance of PSNR and SSIM are higher up to 0.5 ~ 1 dB and 0.4 ~ 0.8 %, respectively.

• Journal of Broadcast Engineering
• /
• v.12 no.6
• /
• pp.565-573
• /
• 2007

In this paper, we propose a method to select motion vector predictor by considering prediction structure of a multi view content for coding efficiency of multi view coding which is being standardized in JVT. Motion vector of a different tendency is happened while carrying out temporal and view reference prediction of multi-view video coding. Also, due to the phenomena of motion vectors being searched in both temporal and view order, the motion vectors do not agree with each other resulting a decline in coding efficiency. This paper is about how the motion vector predictor are selected with information of prediction structure. By using the proposed method, a compression ratio of the proposed method in multi-view video coding is increased, and finally $0.03{\sim}0.1$ dB PSNR(Peak Signal-to-Noise Ratio) improvement was obtained compared with the case of JMVM 3.6 method.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.127-146
• /
• 2022

Recently, as word embedding has shown excellent performance in various tasks of deep learning-based natural language processing, researches on the advancement and application of word, sentence, and document embedding are being actively conducted. Among them, cross-language transfer, which enables semantic exchange between different languages, is growing simultaneously with the development of embedding models. Academia's interests in vector alignment are growing with the expectation that it can be applied to various embedding-based analysis. In particular, vector alignment is expected to be applied to mapping between specialized domains and generalized domains. In other words, it is expected that it will be possible to map the vocabulary of specialized fields such as R&D, medicine, and law into the space of the pre-trained language model learned with huge volume of general-purpose documents, or provide a clue for mapping vocabulary between mutually different specialized fields. However, since linear-based vector alignment which has been mainly studied in academia basically assumes statistical linearity, it tends to simplify the vector space. This essentially assumes that different types of vector spaces are geometrically similar, which yields a limitation that it causes inevitable distortion in the alignment process. To overcome this limitation, we propose a deep learning-based vector alignment methodology that effectively learns the nonlinearity of data. The proposed methodology consists of sequential learning of a skip-connected autoencoder and a regression model to align the specialized word embedding expressed in each space to the general embedding space. Finally, through the inference of the two trained models, the specialized vocabulary can be aligned in the general space. To verify the performance of the proposed methodology, an experiment was performed on a total of 77,578 documents in the field of 'health care' among national R&D tasks performed from 2011 to 2020. As a result, it was confirmed that the proposed methodology showed superior performance in terms of cosine similarity compared to the existing linear vector alignment.

• The Bulletin of The Korean Astronomical Society
• /
• v.22
• /
• pp.12.1-12.1
• /
• 1997

• Animal cells and systems
• /
• v.8
• /
• pp.50-50
• /
• 2004

• The Mathematical Education
• /
• v.22 no.2
• /
• pp.41-44
• /
• 1984

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.177-180
• /
• 2005

Three dimensional shaded images are standard visualization method for CAD models on the computer screen. Therefore, much of the effort in the visualization of CAD models has been focused on how conveniently and realistically CAD models can be displayed on the screen. However, shaded 3D CAD data images captured from the screen may not be suitable for some application areas. Technical document, either in the paper or electronic form, can more clearly describe the shape and annotate parts of the model by using projected 2D line drawing format viewed from a user defined view direction. This paper describes an efficient method for generating such a 2D line drawing data in the vector format. The algorithm is composed of silhouette line detection, hidden line removal and cleaning processes.