Se-hyeok Park
Samsung
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Se-hyeok Park.
ieee global conference on consumer electronics | 2012
Hyun-Seung Lee; Seung-Goo Kim; Ji-Hwan Kim; Se-hyeok Park; Cheul-hee Hahm
In this paper, we propose self-synthesis based super-resolution algorithm for natural images. The proposed method analyzes the property of the natural image and focuses on the self-similarity of natural objects. Structure and texture components are extracted from the self-image and synthesized on the interpolated image with matching weights to restore the self-similarity of interpolated image. Then, the synthesized image is compensated with MAP estimator to prevent artifacts. Experimental results show that the proposed method gives more natural texture in terms of human perception.
IEEE Transactions on Consumer Electronics | 2012
Sooyeon Lee; Youngshin Kwak; Youn Jin Kim; Se-hyeok Park; Jae-Hyun Kim
The YCbCr color space is widely used in image processing techniques. The preference for YCbCr is due to the rough correspondence between the YCbCr components and visual attributes. However, image contrast decreases as the chroma value increases owing to the nonorthogonality between YCbCr components. In this study, a contrast-preserved chroma enhancement algorithm using YCbCr signals is proposed by predicting the amounts of luma change needed to compensate for the lightness change induced by chroma enhancement. Numerical and psychophysical experimental results show that the proposed algorithm can effectively enhance the perceived image chroma and details.
international conference on consumer electronics berlin | 2012
Gi Yeong Gim; Youn Jin Kim; Tae Gyoung Ahn; Se-hyeok Park
In this paper, we propose a novel method reducing motion artifacts in horizontal scrolling text (HST) area which has been frequently occurred during frame rate conversion (FRC) processing. The proposed method takes place in the following two steps: HST area detection and motion vector (MV) correction. The most dominant MV in each horizontal line is referred to as a block line motion vector (BLMV) and its direction and magnitude are used to detect HST regions. MVs in the HST regions are corrected in order to suppress the motion artifacts. It is advantageous to improve the performance of various motion-based image processing applications such as FRC. Its merits and performance in motion artifact reduction could be verified through a set of visual experiments.
ieee global conference on consumer electronics | 2014
Seok Bong Yoo; Kyuha Choi; Se-hyeok Park; Jong Beom Ra
Even though super-resolution is a promising technique, it can cause unwanted increase of compression noises, if it is applied to an image coded with a low bit-rate. To solve this problem, we propose an integrated framework to reduce compression noises and to recover high-frequency components of a coded low-resolution image. The framework effectively combines two patch-based algorithms, a patch-matching-based 3-D filtering algorithm and an example-based super-resolution algorithm, based on the combination of 3-D transform coefficients. Experimental results demonstrate that the proposed framework successfully improves the resolution while alleviating compression noises in the images coded with low bit-rates.
international conference on consumer electronics | 2012
Seung-Ho Park; Tae Gyoung Ahn; Se-hyeok Park; Jae-Hyun Kim
We introduce an advanced local fallback algorithm that is sensible of an object boundary. In previous studies, local vector smoothness (LVS) was used to determine the local fallback ratio. However, LVS in a properly interpolated object boundary results in unnecessary motion. Our local fallback algorithm application is sensible of the moving object boundary and occlusion though spatial and temporal analysis of motion vector reliability.
ieee global conference on consumer electronics | 2012
Hyun-Seung Lee; Ji-Hwan Kim; Se-hyeok Park; Cheul-hee Hahm
Recently, sub-pixel rendered filter is often used as a post processing of graphic contents to reduce the jagging artifacts in displays. However, in a printing system, sub-pixel filtered image yields blurring and jagging artifacts due to the difference of displaying method. In order to prevent artifacts, new edge enhancement method is proposed. Edge region of an image is processed by an adaptive intensity mapping function to reduce the mid-range of intensities that make jagging artifacts in half-toning. Then, a color replacement function is applied to reduce the color fringe artifacts. Experimental results show that the proposed algorithm improves the quality of printed sub-pixel rendered image.
Archive | 2013
Byungseok Min; Yong Kim; Eun-Hyun Kim; Jong-man Kim; Jong-Ho Kim; Se-hyeok Park; Jeong-hoon Park; Hyun-Hee Park; Min-Woo Lee; Ji-Young Yi
Archive | 2012
Gun-Shik Shin; Se-hyeok Park; Jong-hyun Park; Chang-su Han
Archive | 2013
Seung-Gu Kim; Se-hyeok Park; Tae-gyoung Ahn
Archive | 2013
Seung-Gu Kim; Tae Gyoung Ahn; Se-hyeok Park