• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.5
• /
• pp.231-240
• /
• 2015

Medical imagery require to protect the privacy with preserving the quality of the original contents. Therefore, reversible watermarking is a solution for this purpose. Previous researches have focused on general imagery and achieved high capacity and high quality. However, they raise a distortion over entire image and hence are not applicable to medical imagery which require to preserve the quality of the objects. In this paper, we propose a novel reversible watermarking for medical imagery, which preserve the quality of the objects and achieves high capacity. First, object and background region is segmented and then predicted error histogram-based reversible watermarking is applied for each region. For the efficient watermark embedding with small distortion in the object region, the embedding level at object region is set as low while the embedding level at background region is set as high. In experiments, the proposed algorithm is compared with the previous predicted error histogram-based algorithm in aspects of embedding capacity and perceptual quality. Results support that the proposed algorithm performs well over the previous algorithm.

• The KIPS Transactions:PartB
• /
• v.12B no.5 s.101
• /
• pp.587-594
• /
• 2005

This paper proposes a multi-level thresholding method for image segmentation using fuzzy clustering algorithm in transition region. Most of threshold-based image segmentation methods determine thresholds based on the histogram distribution of a given image. Therefore, the methods have difficulty in determining thresholds for real-image, which has a complex and undistinguished distribution, and demand much computational time and memory size. To solve these problems, we determine thresholds for real-image using fuzzy clustering algorithm after extracting transition region consisting of essential and important components in image. Transition region is extracted based on Inか entropy, which is robust to noise and is well-known as a tool that describes image information. And fuzzy clustering algorithm can determine optimal thresholds for real-image and be easily extended to multi-level thresholding. The experimental results demonstrate the effectiveness of the proposed method for performance.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.6
• /
• pp.705-716
• /
• 2002

This paper proposes a method which visualizes MRI head data in 3 dimensions with direct volume rendering. Though surface rendering is usually used for MRI data visualization, it has some limits of displaying little speckles because it loses the information of the speckles in the surfaces while acquiring the information. Direct volume rendering has ability of displaying little speckles, but it doesn't treat MRI data because of the data features of MRI. In this paper, we try to visualize MRI head data in 3 dimensions as follows. First, we separate the brain region from the head region of MRI head data, next increase the pixel level of the brain region, then combine the brain region with the increased pixel level and the head region without brain region, last visualizes the combined MRI head data with direct volume rendering. We segment the brain region from head region based on histogram threshold, morphology operations and snakes algorithm. The proposed segmentation method shows 91~95% similarity with a hand segmentation. The method rather clearly visualizes the organs of the head in 3 dimensions.

• International journal of advanced smart convergence
• /
• v.8 no.1
• /
• pp.24-34
• /
• 2019

In this research, a practical deep learning framework to differentiate the lesions and nodules in breast acquired with ultrasound imaging has been proposed. 7408 ultrasound breast images of 5151 patient cases were collected. All cases were biopsy proven and lesions were semi-automatically segmented. To compensate for the shift caused in the segmentation, the boundaries of each lesion were drawn using Fully Convolutional Networks(FCN) segmentation method based on the radiologist's specified point. The data set consists of 4254 benign and 3154 malignant lesions. In 7408 ultrasound breast images, the number of training images is 6579, and the number of test images is 829. The margin between the boundary of each lesion and the boundary of the image itself varied for training image augmentation. The training images were augmented by varying the margin between the boundary of each lesion and the boundary of the image itself. The images were processed through histogram equalization, image cropping, and margin augmentation. The networks trained on the data with augmentation and the data without augmentation all had AUC over 0.95. The network exhibited about 90% accuracy, 0.86 sensitivity and 0.95 specificity. Although the proposed framework still requires to point to the location of the target ROI with the help of radiologists, the result of the suggested framework showed promising results. It supports human radiologist to give successful performance and helps to create a fluent diagnostic workflow that meets the fundamental purpose of CADx.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.8
• /
• pp.1373-1379
• /
• 2006

Moving object extraction is one of key research topics for various video services. In this study, a new moving object extraction algorithm is introduced to extract objects using block motion vectors in video data. To do this, 1) a maximum a posteriori probability and Gibbs random field are used to obtain real block motion vectors,2) a 2-D histogram technique is used to determine a global motion, 3) additionally, a block segmentation is fellowed. In the computer simulation results, the proposed technique shows a good performance.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.3
• /
• pp.33-40
• /
• 2018

In this paper, we propose a method to effectively split the adjacent baggage that is moving on high speed conveyor of airport. The proposed method calculate the Angle Histogram(AH) that inspects background pixels within radius r based on the center point of the adjacent baggage. After that, the adjacent baggage is segmented by finding split angles at the AH. We also improved the split quality of adjoining baggage by repeatedly correcting the center point to correctly split adjacent baggage of asymmetric size. And the calculation time of AH is reduced about 1/3 by using the symmetry property of the circle. Experiments have shown that 93% of all adjacent baggage images are correctly segmented and the proposed method is effective.

• Annual Conference of KIPS
• /
• 2005.11a
• /
• pp.189-192
• /
• 2005

비디오 분할의 목적은 같은 내용들을 가지는 프레임들의 순서를 표현하는 각 샷의 비디오 순서 분할을 위한 것이다. 그리고 색인에 대한 각 샷으로부터 키 프레임을 선택한다. 존재하는 비디오 분할 방법들은 2가지 그룹들로 분류될 수 있다. 먼저 경계값이 할당되어야만 하는 샷 전환 검출(SCD) 접근과 클러스터 수의 사전 지식이 요구되는 클러스터 접근이다. 본 논문에서는 컬러-$x^2$명도 히스토그램 기반 FCM(fuzzy c-means) 클러스터링 알고리즘을 사용하는 비디오 분할 방법을 제안하였다. 이 알고리즘은 앞에서 기술한 2가지 접근의 혼합이다. 그리고 이것은 두 가지 접근들의 결점을 극복하도록 설계 되었다. 실험 결과들은 컬러-$x^2$명도 히스토그램 기반 FCM 클러스링 알고리즘이 강건하고 비디오 시퀀스들의 다양한 형태들에 응용할 수 있다고 제안한다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.4
• /
• pp.304-308
• /
• 2001

The increase of video data makes the demand of efficient retrieval, storing, and browsing technologies necessary. In this paper, a video segmentation method (scene change detection method, or shot boundary detection method) for the development of such systems is proposed. For abrupt cut detection, inter-frame similarities are computed using luminance and edge histograms and a cut is declared when the similarities are under th predetermined threshold values. A gradual scene change detection is based on the similarities between the current frame and the previous shot boundary frame. A correlation method is used to obtain universal threshold values, which are applied to various video data. Experimental results show that propose method provides 90% precision and 98% recall rates for abrupt cut, and 59% precision and 79% recall rates for gradual change.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2002.06a
• /
• pp.316-322
• /
• 2002

본 연구에서는 고정된 카메라로부터 입력되는 영상열에서 이동 물체를 신뢰성있게 분리하기 위해 형태 정보를 이용한 확장 방법을 제안한다. 영역 분리의 핵심은 배경으로부터 주위 잡음 영역과 무관하게 이동 물체 영역을 분리하는 기술이라고 볼 수 있다. 제안된 방법은 초기 이동 물체가 존재하지 않는 영상을 참고 영상(reference image)으로 하여 입력 영상(input image)과의 차영상(subtraction image)을 구하고, 차영상의 히스토그램(histogram)에서 배경잡음 모델링(modeling)을 통해 배경잡음을 제거한다. 그리고 배경잡음이 제거된 차영상에서 국부 최대값들(local maxima)을 이용해 후보 초기 영역을 선정한 후, 이 영역을 기반으로 영역의 형태정보를 이용하여 영역을 선별적으로 확장하면서 결합하는 방법을 사용하였다. 제안된 방법을 실제 상황에서 얻은 다양한 영상열에 적용한 결과, 기존의 영역 분리 방법보다 주위 잡음과 무관하게 이동 물체를 분리할 수 있음을 확인할 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.703-705
• /
• 2005

본 논문에서는 기울기 크기 기반의 3차원 영역확장 알고리즘을 사용하여 small animal PET(Positron Emission Tomography) 영상으로부터 종양을 분할하는 연구를 수행하였다. 픽셀 값의 범위가 다양하고 저해상도의 특성을 갖는 PET영상으로부터 대상영역을 정확하게 분할하기 위해서 전처리(preprocessing)과정으로 영상 픽셀값의 분포를 펼쳐줌으로써 영상의 가시화를 높이는 히스토그램 스트레칭(histogram stretching) 기법을 적용하고 대상영역과 픽셀값이 유사한 인접영역과의 경계를 찾기 위해 가우시안의 1차 미분 함수를 사용하여 계산된 기울기 크기(gradient magnitude) 기반의 3차원 영역확장(region growing) 알고리즘을 제안한다. 제안한 알고리즘은 영역확장의 결과에 가장 큰 영향을 미치는 적절한 동질성 기준의 선택으로 대상영역의 분할을 성공적으로 수행하여 일반적인 영역확장의 단점을 보완하였다.