• 한국통신학회:학술대회논문집
• /
• 한국통신학회 1993년도 추계종합학술발표회 논문집
• /
• pp.351-354
• /
• 1993

• 대한의용생체공학회:의공학회지
• /
• 제8권2호
• /
• pp.118-122
• /
• 1987

The medical image processing system is intended for a diverse set of users in the medical Imaging Parts. This system consists of a 640 Kbyte IBM-PC/AT with 30 Mbyte hard disk, special purpose image processor with video input devices and display monitor. Image may be recorded and processed in real time at sampling rate up to 10 MHz. This system provides a wide range of image enhancement processing facilities via a menu-driven software packages. These facilities include point by point processing, image averaging, convolution filter and subtraction.

• Investigative Magnetic Resonance Imaging
• /
• 제22권2호
• /
• pp.102-109
• /
• 2018

Purpose: The purpose of this study is to compare the performance of the T1 3D subtraction technique and the conventional 2D dynamic contrast enhancement (DCE) technique in diagnosing Cushing's disease. Materials and Methods: Twelve patients with clinically and biochemically proven Cushing's disease were included in the study. In addition, 23 patients with a Rathke's cleft cyst (RCC) diagnosed on an MRI with normal pituitary hormone levels were included as a control, to prevent non-blinded positive results. Postcontrast T1 3D fast spin echo (FSE) images were acquired after DCE images in 3T MRI and image subtraction of pre- and postcontrast T1 3D FSE images were performed. Inter-observer agreement, interpretation time, multiobserver receiver operating characteristic (ROC), and net benefit analyses were performed to compare 2D DCE and T1 3D subtraction techniques. Results: Inter-observer agreement for a visual scale of contrast enhancement was poor in DCE (${\kappa}=0.57$) and good in T1 3D subtraction images (${\kappa}=0.75$). The time taken for determining contrast-enhancement in pituitary lesions was significantly shorter in the T1 3D subtraction images compared to the DCE sequence (P < 0.05). ROC values demonstrated increased reader confidence range with T1 3D subtraction images (95% confidence interval [CI]: 0.94-1.00) compared with DCE (95% CI: 0.70-0.92) (P < 0.01). The net benefit effect of T1 3D subtraction images over DCE was 0.34 (95% CI: 0.12-0.56). For Cushing's disease, both reviewers misclassified one case as a nonenhancing lesion on the DCE images, while no cases were misclassified on T1 3D subtraction images. Conclusion: The T1 3D subtraction technique shows superior performance for determining the presence of enhancement on pituitary lesions compared with conventional DCE techniques, which may aid in diagnosing Cushing's disease.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.63-66
• /
• 2009

Automatic segmentation of foreground from background in video sequences has attracted lots of attention in computer vision. This paper proposes a novel framework for the background subtraction that the foreground is segmented from the background by directly subtracting a background image from each frame. Most previous works focus on the extraction of more reliable seeds with threshold, because the errors are occurred by noise, weak color difference and so on. Our method has good segmentations from the approximate seeds by using the Random Walks with Restart (RWR). Experimental results with live videos demonstrate the relevance and accuracy of our algorithm.

• 한국멀티미디어학회논문지
• /
• 제12권10호
• /
• pp.1418-1426
• /
• 2009

주어진 배경 이미지로부터 전경 객체를 분리하는 것을 목표로 하는 배경 차분화 기법에 관한 많은 연구가 있어 왔다. 최근에 발표된 몇 가지 통계 기반 배경 차분화 기법들은 동적인 환경에서 동작할 수 있을 정도로 안정된 성능을 보이는 것으로 보고되고 있다. 그러나 이들 기법은 일반적으로 매우 많은 계산 자원을 요구하며, 객체의 명확한 윤곽을 획득하는데 있어서는 아직 어려움이 있다. 본 논문에서는 점진적으로 변화하는 배경을 모델링하기 위해 복잡한 통계 기법을 적용하는 대신 간단한 이동-평균 기법을 사용한다. 또한 픽셀별로 할당되는 다중의 임계치 대신 유전자 학습에 의해 최적화되는 하나의 전역적 임계치를 사용한다. 유전자 학습을 위해 새로운 적합도 함수를 정의하여 학습하고 이를 이용하여 이미지의 분할 결과들을 평가한다. 본 논문의 시스템은 웹 카메라가 장착된 개인용 컴퓨터에서 구현하였으며, 실사 이미지들에 대한 실험 결과에 의하면 기존의 가우시안 믹스쳐 방식보다 우수한 성능을 보이는 것으로 나타났다.

• Imaging Science in Dentistry
• /
• 제46권1호
• /
• pp.17-24
• /
• 2016

Purposes: This study employed a posteriori registration and subtraction of radiographic images to quantify the apical root resorption in maxillary permanent central incisors after orthodontic treatment, and assessed whether the external apical root resorption (EARR) was related to a range of parameters involved in the treatment. Materials and Methods: A sample of 79 patients (mean age, $13.5{\pm}2.2years$) with no history of trauma or endodontic treatment of the maxillary permanent central incisors was selected. Periapical radiographs taken before and after orthodontic treatment were digitized and imported to the Regeemy software. Based on an analysis of the post-treatment radiographs, the length of the incisors was measured using Image J software. The mean EARR was described in pixels and relative root resorption (%). The patient's age and gender, tooth extraction, use of elastics, and treatment duration were evaluated to identify possible correlations with EARR. Results: The mean EARR observed was $15.44{\pm}12.1pixels$ (5.1% resorption). No differences in the mean EARR were observed according to patient characteristics (gender, age) or treatment parameters (use of elastics, treatment duration). The only parameter that influenced the mean EARR of a patient was the need for tooth extraction. Conclusion: A posteriori registration and subtraction of periapical radiographs was a suitable method to quantify EARR after orthodontic treatment, and the need for tooth extraction increased the extent of root resorption after orthodontic treatment.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.159-161
• /
• 2004

Many motion object detection algorithms rely on the process of background subtraction, an important technique that is used for detecting changes from a model of the background scene. This paper propose a novel method to update the background model image of a visual surveillance system which is not stationary. In order to do this, we use a background model based on statistical qualities of monitored images and another background model that excluded motions. By comparing each changed area computed from the two background model images and current monitored image, the areas that will be updated are decided.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2008년도 학술대회 1부
• /
• pp.623-628
• /
• 2008

본 논문에서는 비전 기반 게임 인터페이스를 위한 배경영역으로부터 전경영역을 추출하기 위해 빠르고 강건한 새로운 방법을 소개한다. Background Subtraction 방법은 추적하고자 하는 이미지의 특징을 추출하기 전에 필수적으로 거쳐야 하는 전처리 과정이다. 이를 위해 본 논문에서는 이미지를 지역 셀로 나누어 가우시안 커널이 적용된 Local Histogram을 계산하고 히스토그램의 Bhattacharyya 거리를 계산하여 전경확률을 결정한다. 이처럼 지역적 히스토그램에 기반한 방법은 급격한 조명변화나 잡음 또는 작은 배경오브젝트의 움직임에 부분적으로 강간함을 보인다. 히스토그램을 계산하는데에서 Multi-Scaled Integral Histogram을 사용하여 잡음을 억제하면서 계산의 속도를 높였다.

• 디지털산업정보학회논문지
• /
• 제9권2호
• /
• pp.17-22
• /
• 2013

In this paper, we propose a concrete crack detection method using shape properties. It is based on morphology algorithm and crack features. We assume that an input image is contaminated by various noises. Thus, we use a morphology operator and extract patterns of crack. It segments cracks and background using opening and closing operations. Morphology based segmentation is better than existing integration methods using subtraction in detecting a crack it has small width. Also, it is robust to noisy environment. The proposed algorithm classifies the segmented image into crack and background using shape properties of crack. This method calculates values of properties such as the number of pixels and the maximum length of the segmented region. Also, pixel counts of clusters are considered. We decide whether the segmented region belongs to cracks according to those data. Experimental results show that our proposed crack detection method has better results than those by existing detection methods.

• 전자공학회논문지D
• /
• 제34D권7호
• /
• pp.88-96
• /
• 1997

As the need of automatized system has been increased recently together with the development of industrial and military technologies, the adaptive real-time target detection technologies that can be embedded on vehicles, planes, ships, robots and so on, are hgihly demanded. Accordingly, this paper proposes a novel approach to detect and segment the moving targets using the binary phase extraction joint transform correlator (BPEJTC), the advanced image subtraction filter and convex hull processing. The BPEJTC which was used as a target detection unit mainly for target tracking compensating the camera movement. The target region has been detected by processing the successful three frames using the advanced image subtraction filter, and has become more accurate by applying the developed convex hull filter. As shown by some experimental results, it is expected that the proposed approaches for compensation of the camera movement and segmentationof of target region, can be used for th emissile guiddance, aero surveillance, automatic inspectin system as well as the target detection unit of automatic target recognition system that request adaptive real-time processing.