• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.379-387
• /
• 2015

In recent years, copyright violations from illegal copying and distribution of e-comic contents have become an important issue. Fingerprinting techniques have been emerged to provide a fast and reliable identification method of identifying e-comic contents. When illegally scanned or camera captured comic contents are distributed, they suffer from distortions. So the fingerprint differs from the original version. This paper presents a restoration framework for correcting geometric distortions in distorted comics to improve the comic content identification.

• Journal of Korea Game Society
• /
• v.10 no.1
• /
• pp.157-165
• /
• 2010

This paper presents a novel real-time rendering algorithm based on spherical coordinate system of the object using convex hull. While OpenGL rendering pipeline touches all vertices of an object, the proposed method takes account the only visible vertices by examining the visible triangles of the object. In order to determine the visible areas of the object in its spherical coordinate representation, the proposed method uses 3D geometric relation of 6 plane equations of the camera frustum and the bounding sphere of the object. In addition, we compute the convex hull of the object and its maximum side factors for hidden surface removal. Simulation results showed that the quality of result image is almost same compared to original image and rendering performance is greatly improved.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1191-1194
• /
• 2022

인터넷의 발전으로 수많은 이미지와 비디오를 손쉽게 이용할 수 있게 되었다. 이미지와 비디오 데이터의 양이 기하급수적으로 증가함에 따라, JPEG, HEVC, VVC 등 이미지와 비디오를 효율적으로 저장하기 위한 부호화 기술들이 등장했다. 최근에는 인공신경망을 활용한 학습 기반 모델이 발전함에 따라, 이를 활용한 이미지 및 비디오 압축 기술에 관한 연구가 빠르게 진행되고 있다. NNIC (Neural Network based Image Coding)는 이러한 학습 가능한 인공신경망 기반 이미지 부호화 기술을 의미한다. 본 논문에서는 NNIC 모델과 인공신경망 기반의 초해상화(Super Resolution) 모델을 합동훈련하여 기존 NNIC 모델보다 더 높은 성능을 보일 수 있는 방법을 제시한다. 먼저 NNIC 인코더(Encoder)에 이미지를 입력하기 전 다운 스케일링(Down Scaling)으로 쌍삼차보간법을 사용하여 이미지의 화소를 줄인 후 부호화(Encoding)한다. NNIC 디코더(Decoder)를 통해 부호화된 이미지를 복호화(Decoding)하고 업 스케일링으로 초해상화를 통해 복호화된 이미지를 원본 이미지로 복원한다. 이때 NNIC 모델과 초해상화 모델을 합동훈련한다. 결과적으로 낮은 비트량에서 더 높은 성능을 볼 수 있는 가능성을 보았다. 또한 합동훈련을 함으로써 전체 성능의 향상을 보아 학습 시간을 늘리고, 압축 잡음을 위한 초해상화 모델을 사용한다면 기존의 NNIC 보다 나은 성능을 보일 수 있는 가능성을 시사한다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.3 s.309
• /
• pp.67-75
• /
• 2006

Facial expressions exhibit not only facial feature motions, but also subtle changes in illumination and appearance. Since it is difficult to generate realistic facial expressions by using only geometric deformations, detailed features such as textures should also be deformed to achieve more realistic expression. The existing methods such as the expression ratio image have drawbacks, in that detailed changes of complexion by lighting can not be generated properly. In this paper, we propose a nonlinear model for skin color change and a model-based synthesis method for facial expression that can apply realistic expression details under different lighting conditions. The proposed method is composed of the following three steps; automatic extraction of facial features using active appearance model and geometric deformation of expression using warping, generation of facial expression using a model for nonlinear skin color change, and synthesis of original face with generated expression using a blending ratio that is computed by the Euclidean distance transform. Experimental results show that the proposed method generate realistic facial expressions under various lighting conditions.

• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.899-907
• /
• 2022

Purpose: Although many studies on seismic fragility analysis of general bridges have been conducted using machine learning methods, studies on curved bridge structures are insignificant. Therefore, the purpose of this study is to analyze the seismic fragility of bridges with I-shaped curved girders based on the machine learning method considering the material property and geometric uncertainties. Method: Material properties and pier height were considered as uncertainty parameters. Parameters were sampled using the Latin hypercube technique and time history analysis was performed considering the seismic uncertainty. Machine learning data was created by applying artificial neural network and response surface analysis method to the original data. Finally, earthquake fragility analysis was performed using original data and learning data. Result: Parameters were sampled using the Latin hypercube technique, and a total of 160 time history analyzes were performed considering the uncertainty of the earthquake. The analysis result and the predicted value obtained through machine learning were compared, and the coefficient of determination was compared to compare the similarity between the two values. The coefficient of determination of the response surface method was 0.737, which was relatively similar to the observed value. The seismic fragility curve also showed that the predicted value through the response surface method was similar to the observed value. Conclusion: In this study, when the observed value through the finite element analysis and the predicted value through the machine learning method were compared, it was found that the response surface method predicted a result similar to the observed value. However, both machine learning methods were found to underestimate the observed values.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.17 no.6
• /
• pp.131-142
• /
• 2007

In this paper, semi-fragile watermarking algorithm was proposed for the application to RP(Rapid Prototyping) system. In the case of the perceptual change or distortion of the original one, the prototype product will be affected from the process because the RP system requires the high precision measure. Therefore, the geometrical transformations like translation, rotation and scaling, the mesh order change and the file format change are used in the RP system because they do not change the basic shapes of the 3D models, but, the decimation and the smoothing are not used because they change the models. The proposed algorithm which is called semi-fragile watermarking is robust against to these kinds of manipulations which preserve the original shapes because it considers the limitations of the RP system, but fragile against to the other manipulations which change the original shapes. This algorithm does not change the model shapes after embedding the watermark information, that is, there is no shape difference between the original model and the watermarked model. so, it will be useful to authenticate the data integrity and hide the information in the field of mechanical engineering which requires the high precision measure.

• Journal of Korea Multimedia Society
• /
• v.4 no.3
• /
• pp.247-256
• /
• 2001

Digital watermarking is a copyright protection technique for digital images which embed a code into the digital data so the data is marked. Watermarking techniques previously deal with on-line digital data and have been developed to withstand digital attacks such image processing, compression and geometric transformation. In this paper we propose a novel method of embedding watermarks in printed images. In the proposed algorithm, watermark is embedded in a dithered binary image by comparing the $2\times{2}$ blocks of the counting array is the number of 1 (WHITE) in the $16\times{16}$ blocks of the dithered binary image with predefined reference block pattern, which is generated by watermark values. The proposed algorithm is able to provide more information at a watermark because the proposed algorithm use both '1'and '0' as watermark values. The watermark information is detected by comparing the watermark which is reconstructed from the image which is embedded watermark with the original watermark which is embedded in a binary image. The performance of the proposed algorithm is compared with that of the conventional watermark embedding algorithm for printed images by detecting watermark for scan images.

• Journal of the Korea Computer Graphics Society
• /
• v.20 no.1
• /
• pp.13-19
• /
• 2014

In this paper, we introduce a real-time method to render a 3D scene using image-based lighting. Previous approaches for image-based lighting focused on diffuse reflection and mirror-like specular reflection. In this paper, we provide a simple preprocessing approach to efficiently approximate Phong reflection model, which has been used for computer graphics applications for several decades. For diffuse reflection, we generate a texture map for diffuse reflection by integrating the source image in preprocessing step, similarly to the previous approaches. We adopt the similar idea to produce a set of specular reflection maps for various material shininess. By doing this, we can render a dynamic scene without high computational complexity or numerous texture map access.

• Journal of Korea Multimedia Society
• /
• v.8 no.11
• /
• pp.1510-1519
• /
• 2005

We proposed a digital watermarking method that it is possible to identify the copyright because the watermark is detected in the first print-scan and to protect a forgery because the watermark is not detected in the second print-scan. The proposed algorithm uses LPM and DFT transform for the robustness to the distortion of pixel value and geometrical distortion. This methods could improve watermark detection performance and image quality by selecting maximum sampling radius in LPM transform. After analyzing the characteristics of print-scan process, we inserted the watermark in the experimentally selected frequency bands that survives robustly to the first print-scan and is not detected in the second print-scan, using the characteristic of relatively large distortion in high frequency bands of DFT As the experimental result, the original proof is possible because average similarity degree 5.13 is more than the critical value 4.0 in the first print-scan. And the detection of forgery image is also possible because average similarity degree 2.76 is less than the critical value 4.0 in the second print-scan.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.339-342
• /
• 2017

Geometric transform of an image is used to image correction. Ridid-Body, Simlilary transform, etc, many correction methods are exist in computer vision. Image warping is used to correction for image with perspective. To image warping I extracted 4 feature point about warping position. But It is difficult to extract 4 points accurately and warping result with these point is occurs error over 3 or 4 pixel at warping position. So I used template matching to extract 4 points correctly and selected repeatedly 2 points of 4 points because to confirm result correctly. positions of 2 points are changed in near of 3 by 3 pixel and warped each change. So I selected optimal 4 points with a error of less than 1 pixel and finally, warped image using optimal points. For this way is possible to obtain optimum result.