• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4835-4848
• /
• 2020

The recent expansion of the digital content market is increasing the technical demand for various facial image transformations within the virtual environment. The recent image translation technology enables changes between various domains. However, current image-to-image translation techniques do not provide stable performance through unsupervised learning, especially for shape learning in the face transition field. This is because the face is a highly sensitive feature, and the quality of the resulting image is significantly affected, especially if the transitions in the eyes, nose, and mouth are not effectively performed. We herein propose a new unsupervised method that can transform an in-wild face image into another face style through radical transformation. Specifically, the proposed method applies two face-specific feature loss functions for a generative adversarial network. The proposed technique shows that stable domain conversion to other domains is possible while maintaining the image characteristics in the eyes, nose, and mouth.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.6
• /
• pp.90-98
• /
• 1996

In this paper we have proposed the sign language transformation system for deaf based on a morpheme analysis. The proposed system extracts phoneme components and connection informations of the input character sequence by using a morpheme analysis. And then the sign image obtained by component analysis is correctly and automatically generated through the sign image database. For the effective sign language transformation, the language description dictionary which consists of a morpheme analysis part for analysis of input character sequence and sign language description part for reference of sign language pattern is costructed. To avoid the duplicating sign language pattern, the pattern is classified a basic, a compound and a similar sign word. The computer simulation shows the usefulness of the proposed system.

• Journal of Korea Multimedia Society
• /
• v.20 no.6
• /
• pp.969-977
• /
• 2017

Through Rene Girard's theory of triangle of the desire, this research investigates the mimetic nature of desire as shown in the main character of the movie The Servant. This paper analyzes the structural transformation of desire in the character, which is revealed by the process of reinterpretation via the medium change and convergence from Chunhyangjeon, a classic oral novel in Korea, to The Servant, a movie created by director Dae-woo Kim in 2010. The Servant is a meaningful research subject as the transformation of the inner desire of the character is accomplished by boldly designating Bangja, who is supposed to be a minor character, as the protagonist. In particular, Rene Girard's argument on the indirectness of desire in the theory of triangle of the desire helps understand the point where the character' inner desire, which naturally occurred in the existing narrative, transforms into the mimetic desire by an intermediary. This indirectness of the mimetic desire of the main character suggests a similarity with modern men's vanity which is offered by the capitalist era. Through this, the modern meaning of the mimetic aspect of desire as revealed by the transformation from the movie The Servant to Chunhyangjeon can be understood.

• Journal of the Korean Society of Radiology
• /
• v.11 no.4
• /
• pp.241-246
• /
• 2017

The existing fractal compression method is effective in generating an artificial shape by approximating its partial regions to a domain block by re-dividing the whole image into a domain region and dividing it into several domain blocks, but it is difficult to implement a computer. In this study, it is difficult to approximate a complex block such as a large-sized block and an affine transformation because a large amount of calculation is required in searching for a combination of similar blocks through a transformation, so a large amount of coding time is required.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.4
• /
• pp.293-304
• /
• 2022

In this study, to analyze the effect of buildings on the image co-registration performance, co-registration results are compared according to the presence or absence of matching points extracted from buildings. To remove the matching points extracted from buildings, a building mask generated by extracting building objects from the digital topographic map was used. In addition, matching points extraction performance and image co-registration accuracy were analyzed according to the magnitude of the convergence angle. Image co-registration results were compared by applying the affine and piecewise linear transformation models, respectively. According to the experimental results, the affine transformation model showed an overall improvement in accuracy after removing the matching points extracted from buildings. On the other hand, the piecewise linear transformation model improved the accuracy at the checkpoints including the surrounding buildings, but the accuracy improvement was not significant at checkpoints in the flat area without the existence of buildings. In addition, when the piecewise linear transformation model was applied, stable accuracy of less than 2 pixels was derived from images with a convergence angle of 20° or less.

• Proceedings of the IEEK Conference
• /
• 2001.06d
• /
• pp.227-230
• /
• 2001

In this paper, We present a 3D image data for ocular refina. This 3D display techniques are used voxel(cuboid) projection. Voxel is 3D reconstruction method of the pixel. In this paper, 3D image display system is constructed under PC environment and programed based on modular programming by using Visual C++. The hole procedures are composed of data preparation, 3D Display over transformation and scaling.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2454-2457
• /
• 1998

In this paper, we interconnected the wavelet transformation and ADPCM to improve the image compression ratio and reduce the loss of information in the reconstructed image. Simulation shows the promising results.

• Journal of KIISE:Software and Applications
• /
• v.30 no.1_2
• /
• pp.153-163
• /
• 2003

In this paper, we propose a new technique of image based rendering(IBR) for the pose transformation of a face by using only a frontal face image and its mesh without a three-dimensional model. To substitute the 3D geometric model, first, we make up a standard mesh set of a certain person for several face sides ; front. left, right, half-left and half-right sides. For the given person, we compose only the frontal mesh of the frontal face image to be transformed. The other mesh is automatically generated based on the standard mesh set. And then, the frontal face image is geometrically transformed to give different view by using Invertible Meshwarp Algorithm, which is improved to tolerate the overlap or inversion of neighbor vertexes in the mesh. The same warping algorithm is used to generate the opening or closing effect of both eyes and a mouth. To evaluate the transformation performance, we capture dynamic images from 10 persons rotating their heads horizontally. And we measure the location error of 14 main features between the corresponding original and transformed facial images. That is, the average difference is calculated between the distances from the center of both eyes to each feature point for the corresponding original and transformed images. As a result, the average error in feature location is about 7.0% of the distance from the center of both eyes to the center of a mouth.

• Journal of Biomedical Engineering Research
• /
• v.31 no.2
• /
• pp.114-122
• /
• 2010

This paper presents a method that registers a lymphoscintigraphy to the real image captured by a CMOS camera, which helps surgeons to easily and precisely detect sentinel lymph nodes for sentinel lymph node biopsy in breast cancer patients. The proposed method consists of two steps: pre-matching and image registration. In the first step, we localize fiducial markers in a lymphoscintigraphy and a real image of a four quadrant bar phantom by using image processing techniques, and then determines perspective transformation parameters by matching with the corresponding marker points. In the second step, we register a lymphoscintigraphy to a real images of patients by using the perspective transformation of pre-matching. To examine the accuracy of the proposed method, we conducted an experiment with a chest mock-up with radioactive markers. As a result, the euclidean distance between corresponding markers was less than 3mm. In conclusion, the present method can be used to accurately align lymphoscintigraphy and real images of patients without attached markers to patients, and then provide useful anatomical information on sentinel lymph node biopsy.

• Proceedings of the Korea Contents Association Conference
• /
• 2003.11a
• /
• pp.120-123
• /
• 2003

In this paper, a digital watermarking scheme whichis effective in protecting a copyright of video image under an image transformation and impulse noise is proposed. The proposing scheme is to use a coded watermark that insert the personal ID of copyrighter. The recovery ability is improved by the coded watermark. Also the coded watermark is abel to trace the illegal distributors. Binary image is used as watermark image, the value of PSNR and recovered rates of watermark are obtained in order to confirm the required invisibility and robustness in watermark system. The experimental results show that image quality is less degraded as the PSNR of 98.21 ㏈. It is also observed that excellent watermark recovery is achieved under the image transformation and impulse noise.