Dictionary and Structural Similarity-based Compression Artifact Reduction in DCT-coded Images

Soowoong Jeong,Yong-Ho Kim,Seok-Han Lee,Ho-Geun Song,Tae-Eun Kim,Sangkeun Lee 중앙대학교 영상콘텐츠융합연구소 2015 TechArt :Journal of Arts and Imaging Science Vol.2 No.3

We present an example and a structural similarity-based scheme to remove artifacts associated with block-based compression schemes. The proposed framework is designed to remove the compression artifacts on the basis of the training sets from the original and their compressed patches across block boundaries. For the data-learning phase, an image is first compressed using various strength levels. Next, each block boundary caused by the compression process is modeled and categorized into classes using a simple classifier. Then, we optimize the classes on the basis of the least mean square optimization approach. By contrast, for the artifact-removal phase, we classify a given block boundary into one of the classes, obtain the filter coefficients from the selected class, and apply these coefficients on two given blocks to remove the artifacts. In particular, the structural-similarity measurement is made only around the edges to effectively preserve the high-frequency image contents. The main advantages of the proposed algorithm are the following: (1) it is an efficient approach using only a fixed number of coefficients to remove blocking artifacts, (2) it requires no prior information on the blocking noise, and (3) it preserves the original image structure using structural similarity. To evaluate the proposed scheme, several state-of-the art approaches are described and compared in terms of peak signal-to-noise ratio, quality metric, and processing time.

강한 에지성분과 방향 히스토그램을 이용한 효과적 영상검색

정수웅(Soowoong Jeong),김용호(Yong-Ho Kim),이상근(Sangkeun Lee) 대한전자공학회 2010 대한전자공학회 학술대회 Vol.2010 No.6

The content based image retrieval has been widely used for the feature information of color, texture, and shape. In this paper, the way of the image retrieval which features the edge orientation histogram using the WLPF(Weighted Low-Pass Filter) is proposed in oder to use the feature information of image effectively. The image retrieval is performed after apply WLPF for image to remove the weak edges which is not involved in the shape information of images and to preserve the strong edges as the shape information of images. Therefore, the proposed algorithm can be used as a useful tool for the image retrieval that requires high efficiency in many fields including the complex background image and too many weak edges in the image.

Fast MOG (Mixture of Gaussian) Algorithm based on Predicting Model Parameters

Yongho Kim,Soowoong Jeong,Jeongsu Oh,Sangkeun Lee 중앙대학교 영상콘텐츠융합연구소 2015 TechArt :Journal of Arts and Imaging Science Vol.2 No.1

Variable calculation at all pixels in a mixture of Gaussians (MOG) is a major obstacle for applications related to background removal. This paper presents a fast MOG algorithm based on partial parameter prediction. The proposed algorithm is applied to a limited number of pixels in order to reduce computational costs while maintaining conventional performance, and the parameter prediction is conducted using only the previous values and simple constant subtractions. Experiment results show that the predicted parameters almost match, in terms of pixel-to-pixel comparisons, to the exactly computed parameters in order to determine a proper model. In particular, the fast algorithm can save more than 37% of the model’s parameter computations while retaining 99.89% and 96.62% image and object-unit accuracies, respectively. Furthermore, it is verified that the pixels of the lost object do not affect the MOG algorithms. Therefore, we believe that it can be a useful tool for fast application development based on MOG algorithms.

Fast dehazing based on dark channel approximation

Guisik Kim,Soowoong Jeong,Sangkeun Lee 대한전자공학회 2015 ITC-CSCC :International Technical Conference on Ci Vol.2015 No.6

Efficient naturalness restoration for non-uniform illumination images

Yonghun Shin,Soowoong Jeong,Sangkeun Lee IET 2015 IET image processing Vol.9 No.8

<P>This study presents a novel image-naturalness restoration for the purpose of achieving better image quality with respect to the human visual system. Specifically, the authors suppress the artefacts around edges using image gradient components. They also appropriately enhance the image brightness using an adaptive gamma correction. In particular, they simply create a mapping curve to adjust the contrast, and then perform contrast enhancement. Experimental results demonstrate that the proposed algorithm outperforms other state-of-the-art algorithms in terms of subjective and objective quality measures, and even computational speed. Therefore they believe that the proposed approach can be a useful tool to improve the visual quality of images under non-uniform illumination.</P>

Efficient Image Transformation and Camera Registration for the Multi-Projector Image Calibration

Seokhan Lee,Soowoong Jeong,Haneul Yu,Guisik Kim,Hanoung Kwak,Eunju Kang,Sangkeun Lee 중앙대학교 영상콘텐츠융합연구소 2016 TechArt :Journal of Arts and Imaging Science Vol.3 No.1

Camera calibration is one of the essential techniques in the 3D computer vision field. Through calibration, the distortion problem can be solved with registration and by acquiring the intrinsic and extrinsic parameters of the camera. In this study, we use and develop more realistic contents through color information and image quality that is obtained by projecting multi-view images without distortion. These images are projected from a multi-projector to a screen. The proposed method solves the distortion problem that occurs when projecting an image to a screen using multi-projector projection. The no distortion reference image is built and projected by a multi-projector onto a screen with registration of the distortion target image and reference image by estimating the homography that shows the relationship between the reference image and distorted target image. In the experimental results, the images projected by the multi-projector are better than those projected by a single projector with respect to resolution and color. Further, the test environment consists of server/client and it can be projected without any distortion to a screen, regardless of the number of projectors.

Improved Circulant Structure with Kernel Tracker using Correlation Kernel based on Wavelet Feature

Guisik Kim,Soowoong Jeong,Sangkeun Lee 중앙대학교 영상콘텐츠융합연구소 2016 TechArt :Journal of Arts and Imaging Science Vol.3 No.2

Visual object tracking has many applications related to computer vision. Recently, correlation filter based trackers have been ranked as the highest performers in this field. However, handling chronic problems such as occlusion, deformation, and scale variations is difficult with such trackers. These problems are solved by many other researches that employ other features and improve an appearance update. In this paper, we propose an improved CSK (Circulant Structure with Kernel) tracker using object feature decomposition in the wavelet domain. Specifically, a newly created correlation kernel is generated from different filter-banks reflecting the visual properties of a given object, and it is stable and robust to the environmental variations. Experimental results demonstrate that the proposed scheme outperforms the conventional CSK tracker in terms of center location error by 59% on an average for 100 sequences. Therefore, we believe that the proposed tracker can be useful for robust object tracking in occlusion.

Colorful Multi-Exposure Fusion with Guided Filtering based Fusion Method

Changho Song,Soowoong Jeong,Sangkeun Lee 중앙대학교 영상콘텐츠융합연구소 2016 TechArt :Journal of Arts and Imaging Science Vol.3 No.4

Multi-exposure fusion(MEF) are techniques to obtain the high dynamic range. One of MEF methods, guided filtering-based fusion(GFF) has good performance for preserving details of original images. However, GFF method considers only details, which causes a problem of missing color information. To solve this problem, we proposed a saliency map-based approach for considering both detail and color information. The experimental results show that the proposed method can provide better color quality than the existing methods.

Single Image Enhancement Using Inter-channel Correlation

Kim, Jin,Jeong, Soowoong,Kim, Yong-Ho,Lee, Sangkeun The Institute of Electronics and Information Engin 2013 IEIE Transactions on Smart Processing & Computing Vol.2 No.3

This paper proposes a new approach for enhancing digital images based on red channel information, which has the most analogous characteristics to invisible infrared rays. Specifically, a red channel in RGB space is used to analyze the image contents and improve the visual quality of the input images but it can cause unexpected problems, such as the over-enhancement of reddish input images. To resolve this problem, inter-channel correlations between the color channels were derived, and the weighting parameters for visually pleasant image fusion were estimated. Applying the parameters resulted in significant brightness as well as improvement in the dark and bright regions. Furthermore, simple contrast and color corrections were used to maintain the original contrast level and color tone. The main advantages of the proposed algorithm are 1) it can improve a given image considerably with a simple inter-channel correlation, 2) it can obtain a similar effect of using an extra infrared image, and 3) it is faster than other algorithms compared without artifacts including halo effects. The experimental results showed that the proposed approach could produce better natural images than the existing enhancement algorithms. Therefore, the proposed scheme can be a useful tool for improving the image quality in consumer imaging devices, such as compact cameras.

Efficient Document Image Binarization

Kiju Lee,Soowoong Jeong,Jeong-su Oh,Jong-soo Choi,Sangkeun Lee 중앙대학교 영상콘텐츠융합연구소 2014 TechArt :Journal of Arts and Imaging Science Vol.1 No.4

In this paper, we present an efficient and adaptive method for document image binarization using degraded images. Our contributions lead to improvements in both the binarization quality and speed. The vertical and horizontal strokes of Korean and Chinese characters are detected adaptively using a local means for accurate binarization. A down-sampled integral image is employed to quickly compute the local means. The proposed method can deal with various degradations owing to shadows, non-uniform illumination, low contrast, and high levels of signal-dependent noise. The experimental results show that the proposed method is about 11- to 424-times faster than existing algorithms and provides better quality results. Therefore, the proposed efficient document binarization algorithm can be a useful tool in fast documentation and optical character recognition.