• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.1
• /
• pp.63-71
• /
• 2003

This paper describes a color image segmentation algorithm based on region merging using hue difference as a restrictive condition. The proposed algorithm using mathematical morphology and a modified watershed algorithm does over-segmentation in the RGB space to preserve contour information of regions. Then, the segmentation result of color image is acquired by repeated region merging using hue differences as a restrictive condition. This stems from human visual system based on hue, saturation, and intensity. Hue difference between two regions is used as a restrictive condition for region merging because it becomes more important factor than color difference if intensity is not low. Simulation results show that the proposed color image segmentation algorithm provides efficient segmentation results with the predefined number of regions for various color images.

• Journal of Broadcast Engineering
• /
• v.17 no.4
• /
• pp.565-571
• /
• 2012

During depth data acquisition and transmission, the quality of depth maps is usually degraded by physical noise and coding error. In this paper, a new joint bilateral filter based on the common distance transform is presented to enhance the low-quality depth map. The proposed method determines the amount of exploitable color data according to distance transform values of depth and color pixels. Consequently, the proposed filter minimizes noise in the depth map while suppressing visual artifacts of joint bilateral filtering. Experimental results show that our method outperforms other conventional methods in terms of noise reduction and visual artifact suppression.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.609-614
• /
• 2009

The purpose of this paper is to design the metal object detection system for drive inside protection. To do this, we propose the algorithm for designing the color filter that can detect the metal object using fuzzy theory and the algorithm for detecting area of the driver's face using fuzzy skin color filter. Also, by using the proposed algorithm, we propose the algorithm for detecting the metallic object candidate regions. And, the metallic object color filter is then applied to find the candidate regions. Finally, we show the effectiveness and feasibility of the proposed method through some experiments.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.110-116
• /
• 2017

This paper presents an effective demosaicking algorithm for color filter array (CFA) images acquired from single-sensor devices based on directional interpolation and nonlocal properties of the image. We interpolate the G channel considering diagonal directions as well as horizontal and vertical directions, using a small number of pixels to reflect local properties of the image. Then, we overcome image degradations, such as zipper effects near edges and false colors, by applying nonlocal means (NLM) filtering to the interpolated pixels. R and B channels are reproduced by using directional interpolation with information of the reconstructed G channel and NLM filtering. Experimental results for various McMaster images with high saturation and color changes show that the proposed algorithm accomplishes high PSNR compared with conventional methods. Moreover, the proposed method demonstrates better subjective quality compared with existing methods in terms of reduction of quality degradation, like false colors, and preservation of the image structures, such as edges and textures.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.741-747
• /
• 2012

In this paper, we propose a fast and robust framework for detecting and tracking multiple targets. The proposed system includes two modules: object detection module and object tracking module. In the detection module, we preprocess the input images frame by frame, such as gray and binarization. Next after extracting the foreground object from the input images, morphology technology is used to reduce noises in foreground images. We also use a block-based histogram analysis method to distinguish human and other objects. In the tracking module, color-based tracking algorithm and Kalman filter are used. After converting the RGB images into HSV images, the color-based tracking algorithm to track the multiple targets is used. Also, Kalman filter is proposed to track the object and to judge the occlusion of different objects. Finally, we show the effectiveness and the applicability of the proposed method through experiments.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.1-10
• /
• 2010

In this paper, we propose a novel way of combining color demosaicing and the auto white balance (AWB) method, which are important parts of image processing. Performance of the AWB is generally affected by demosaicing results because most AWB algorithms are performed posterior to color demosaicing. In order to increase the performance and efficiency of the AWB algorithm, the color constancy problem is considered during the color demosaicing step. Initial estimates of the directional luminance and chrominance values are defined for estimating edge direction and calculating the AWB gain. We propose a modified edge-based AWB method that used a pre-defined achromatic region. The estimation of edge direction is performed region adaptively by using the local statistics of the initial estimates of the luminance and chrominance information. The proposed method shows significant improvements in terms of visual and numerical criteria when compared to conventional methods.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.11a
• /
• pp.92-93
• /
• 2016

정확한 변위정보를 추정하기 위해 다양한 비용 값 계산함수 또는 비용 값 합산 방법들이 개발되었다. 본 논문에서는 비용 값 계산을 위해 좌, 우영상의 기울기와 SAD(Sum of Absolute Differences)를 이용하며 비용 값 합산을 위해 가이드 영상 필터링을 사용한다. 가이드 영상 필터링은 가이드 영상의 종류에 따라 필터링결과가 크게 변하게 되는데, 스테레오 정합에 사용된 원본 입력 영상을 가이드 영상으로 사용할 경우 정확한 화소 값을 가지고 있기 때문에 경계영역을 보존하며 필터링 수행이 가능하다. 하지만 가이드 필터링은 가이드 영상으로부터 미리 지정해준 이웃한 화소와의 거리와 색상차이의 분산 값만을 고려하여 필터링을 수행하기 때문에 설정 변수 값에 매우 의존적인 특성을 갖는다. 가이드 필터링 과정에서 변수에 대한 의존성을 낮추고 경계영역의 정확도를 높이기 위해 우선 평활화 필터를 이용하여 경계영역을 추출한다. 원본 입력영상을 사용하여 경계영역을 추출할 경우 객체 내부의 많은 텍스처 영역의 정보까지 추출되지만, 평활화 필터를 이용할 경우 정확한 경계 영역의 정보만을 추출 할 수 있다. 추출된 경계영역에 대해서만 높은 가중치를 사용한 뒤 기존의 가이드 영상 필터링과 혼합하여 최종 비용 값을 합산한다. 제안한 방법을 사용하여 경계영역의 정확도가 향상된 최종 변위 지도를 획득할 수 있었다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.71-79
• /
• 2011

The objective of the imaging pipeline is to transform the original scene into a display image that appear similar, Generally, gamma adjustment or histogram-based method is modified to improve the contrast and detail. However, this is insufficient as the intensity and the chromaticity of illumination vary with geometric position. Thus, MSR (Multi-Scale Retinex) has been proposed. the MSR is based on a channel-independent logarithm, and it is dependent on the scale of the Gaussian filter, which varies according to input image. Therefore, after correcting the color, image quality degradations, such as halo, graying-out, and dominated color, may occur. Accordingly, this paper presents a novel color correction method using a modified image formation model in which the image is divided into three components such as global illumination, local illumination, and reflectance. The global illumination is obtained through Gaussian filtering of the original image, and the local illumination is estimated by using JND-based adaptive filter. Thereafter, the reflectance is estimated by dividing the original image by the estimated global and the local illumination to remove the influence of the illumination effects. The output image is obtained based on sRGB color representation. The experiment results show that the proposed method yields better performance of color correction over the conventional methods.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.10-13
• /
• 2012

본 논문은 가상 직물 착용을 위한 직조 패턴 제거 필터의 성능 분석에 관한 것이다. 명도 차분 맵을 이용한 가상 직물 착용 시스템은 의류 형상 영역의 명도 차분 맵을 이용하여 조명과 음영 특성을 추출할 시, 의류 형상 영역의 색상에는 무관하지만 의류 모델의 직조 패턴에는 영향을 받는다. 본 논문에서는 바이래터럴 필터(bilateral filter)와 측지 형태학 필터(geodesic morphological filter)에 기반하여 모델 의류 영역의 직조 패턴을 제거하는 방법을 소개하고 그 성능을 분석함에 목적이 있다. 가상 직물 착용 시스템에 직조 패턴 제거 필터를 채택할 경우, 최대한 모델 영상의 직조 패턴에 무관하게 직물 원단의 디자인이 의복의 외관에 미치는 영향을 시뮬레이션할 수 있음에 따라 직물 디자이너의 창작활동을 도와줄 수 있다. 또한 온라인상에서 직물 원단이나 의류를 거래할 시에 구매자로 하여금 모델 영상의 직조패턴에 종속되지 않은 상태에서 의사결정을 할 수 있도록 지원해 B2B 또는 B2C 전자상거래 행위를 촉진할 수 있다.

• Journal of the Korea Convergence Society
• /
• v.8 no.8
• /
• pp.33-40
• /
• 2017

In this paper, we propose a text extraction method by pattern analysis on contour for effective text detection in image. Text extraction algorithms using edge based methods show good performance in images with simple backgrounds, The images of complex background has a poor performance shortcomings. The proposed method simplifies the color of the image by using K-means clustering in the preprocessing process to detect the character region in the image. Enhance the boundaries of the object through the High pass filter to improve the inaccuracy of the boundary of the object in the color simplification process. Then, by using the difference between the expansion and erosion of the morphology technique, the edges of the object is detected, and the character candidate region is discriminated by analyzing the pattern of the contour portion of the acquired region to remove the unnecessary region (picture, background). As a final result, we have shown that the characters included in the candidate character region are extracted by removing unnecessary regions.