• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.241-243
• /
• 2010

Previous approaches to the 2D to 3D conversion problem require heavy computation or considerable amount of user input. In this paper, we propose a rather simple method in estimating the depth map from a single image using a monocular depth cue: haze. Using the haze imaging model, we obtain the distance information and estimate a reliable depth map from a single scenery image. Using the depth map, we also suggest an algorithm that converts the single image to 3D stereoscopic images. We determine a disparity value for each pixel from the original 'left' image and generate a corresponding 'right' image. Results show that the algorithm gives well refined depth maps despite the simplicity of the approach.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.10
• /
• pp.1-7
• /
• 1997

This paper proposes a new real-time 2-D convolver filter architecture wihtout using any multiplier. To meet the massive amount of computations for real-time image processing, several commercial 2-D convolver chips have many multipliers occupying large VLSI area. Te proposed architecture using only one shift-and-accumulator can reduce the chip size by more than 70% of commercial 2-D convolver filter chips and can meet the real-time image processing srequirement, i.e., the standard of CCIR601. In addition, the proposed chip can be used for not only 2-D image processing but also 1-D signal processing and has bood scalability for higher speed applications. We have simulated the architecture by using VHDL models and have performed logic synthesis. We used the samsung SOG cell library (KG60K) and verified completely function and timing simulations. The implemented filter chip consists of only 3,893 gates, operates at 125 MHz and can meet the real-time image processing requirement, that is, 720*480 pixels per frame and 30 frames per second (10.4 mpixels/second).

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.1-14
• /
• 2024

While text-to-image models have made remarkable progress in image synthesis, certain models, particularly generative diffusion models, have exhibited a noticeable bias to- wards generating images related to the culture of some developing countries. This paper introduces an empirical investigation aimed at mitigating the bias of image generative model. We achieve this by incorporating symbols representing Saudi culture into a stable diffusion model using the Dreambooth technique. CLIP score metric is used to assess the outcomes in this study. This paper also explores the impact of varying parameters for instance the quantity of training images and the learning rate. The findings reveal a substantial reduction in bias-related concerns and propose an innovative metric for evaluating cultural relevance.

• The Journal of the Korea Contents Association
• /
• v.14 no.2
• /
• pp.1-9
• /
• 2014

Image inpainting is the widely used technique to restore a damaged region or to fill a hole in an image. The exemplar-based technique effectively generates new texture by copying colour values of the most correlated patch in the source into the empty region of the current patch. In traditional exemplar-based synthesis, the patch correlation is computed using only the already filled pixels of the current patch. Thus, by ignoring the correlation between the hole regions of the two patches, an undesirable patch which is highly correlated with the current patch in the already filled area but considerably dissimilar in the area to be filled can be selected, which results in bad texture propagation. To avoid such problems, a new exemplar-based inpainting method using patch extrapolation is proposed. The empty part of the current patch is extrapolated beforehand, and then the complete patch is used for finding its exemplar. Experimental results show that the proposed method provides more natural synthesis results than the conventional ones.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.5
• /
• pp.487-492
• /
• 2018

Recently, various applications for image processing have been ported to the mobile environment due to the expansion of the image shooting on the mobile device. However, in the case of extracting the image foreground, which is one of the most important functions of image synthesis, is difficult since it needs complex calculation. In this paper, we propose an video synthesis technique that can divide images captured by mobile devices into foreground / background and combine them in real time on target images. Considering the characteristics of mobile shooting, our system can extract automatically foreground of input video that contains weak motion when shooting. Using SIMD and GPGPU-based acceleration algorithms, SD-quality images can be processed on mobile in real time.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.45-54
• /
• 2022

Image depth estimation is a technology that is the basis of various image analysis. As analysis methods using deep learning models emerge, studies using deep learning in image depth estimation are being actively conducted. Currently, most deep learning-based depth estimation models are being trained with clean and ideal images. However, due to the lack of data on adverse conditions such as haze or fog, the depth estimation may not work well in such an environment. It is hard to sufficiently secure an image in these environments, and in particular, obtaining non-homogeneous haze data is a very difficult problem. In order to solve this problem, in this study, we propose a method of synthesizing non-homogeneous haze images and a learning method for a monocular depth estimation deep learning model using this method. Considering that haze mainly occurs outdoors, datasets mainly containing outdoor images are constructed. Experiment results show that the model with the proposed method is good at estimating depth in both synthesized and real haze data.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.465-472
• /
• 2022

In this paper, the style synthesis network is trained to generate style-synthesized video through the style synthesis through training Stylegan and the video synthesis network for video synthesis. In order to improve the point that the gaze or expression does not transfer stably, 3D face restoration technology is applied to control important features such as the pose, gaze, and expression of the head using 3D face information. In addition, by training the discriminators for the dynamics, mouth shape, image, and gaze of the Head2head network, it is possible to create a stable style synthesis video that maintains more probabilities and consistency. Using the FaceForensic dataset and the MetFace dataset, it was confirmed that the performance was increased by converting one video into another video while maintaining the consistent movement of the target face, and generating natural data through video synthesis using 3D face information from the source video's face.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.3
• /
• pp.113-121
• /
• 2013

In this paper, we propose a sub-pixel rendering algorithm using learning-based 2D FIR filters. The proposed algorithm consists of two stages: the learning and synthesis stages. At the learning stage, we produce the low-resolution synthesis information derived from a sufficient number of high/low resolution block pairs, and store the synthesis information into a so-called dictionary. At the synthesis stage, the best candidate block corresponding to each input high-resolution block is found in the dictionary. Next, we can finally obtain the low-resolution image by synthesizing the low-resolution block using the selected 2D FIR filter on a sub-pixel basis. On the other hand, we additionally enhance the sharpness of the output image by using pre-emphasis considering RGB stripe pattern of display. The simulation results show that the proposed algorithm can provide significantly sharper results than conventional down-sampling methods, without blur effects and aliasing.

• Journal of the Institute of Convergence Signal Processing
• /
• v.8 no.4
• /
• pp.285-292
• /
• 2007

SoC which deploys software modules as well as hardware IPs on a single chip is a major revolution taking place in the implementation of a system design, and high-level synthesis is an important process of SoC design methodology. Recently, SPARK parallelizing high-level synthesis software tool has been developed. It takes a behavioral ANSI-C code as an input, schedules it using code motion and various code transformations, and then finally generates synthesizable RTL VHDL code. Although SPARK employs various loop transformation algorithms, the synthesis results generated by SPARK are not acceptable for basic signal and image processing algorithms with nested loop. In this paper we propose a SoC platform with an application-specific PLD targeting local operations which are feature of many loop algorithms used in signal and image processing, and demonstrate design process which maps behavioral specification with nested loops written in a high-level language (ANSI-C) onto 2D systolic array. Finally the derived systolic array is implemented on the proposed application-specific PLD of SoC platform.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.127-130
• /
• 2022

This paper is a study on singing voice synthesis modeling using a generator loss function, which analyzes various factors that may occur when applying BEGAN among deep learning algorithms optimized for image generation to Audio domain. and we conduct experiments to derive optimal quality. In this paper, we focused the problem that the L1 loss proposed in the BEGAN-based models degrades the meaning of hyperparameter the gamma(𝛾) which was defined to control the diversity and quality of generated audio samples. In experiments we show that our proposed method and finding the optimal values through tuning, it can contribute to the improvement of the quality of the singing synthesis product.