• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.301-302
• /
• 2013

본 논문에서는 초음파 영상에서 퍼지 C-Means 클러스터링을 이용한 양자화 기법을 제안한다. 제안된 방법은 초음파 영상에서 나타난 명암도를 이용하여 n개의 그룹으로 클러스터링한다. 그리고 각 클러스터의 중심 값을 기준으로 정렬한 뒤, 각 그룹에 지정된 색상을 요부 초음파 영상에서 나타낸다. 본 논문에서 제안하는 기법을 적용한 요부 초음파 영상과 일반적으로 자주 이용되는 히스토그램 기반 양자화 기법을 적용한 요부 초음파 영상을 비교하였을 때, 본 논문에서 제안하는 퍼지 C-Means 클러스터링을 이용한 양자화를 적용한 영상이 근육 내의 지방을 분석하는데 효과적인 것을 확인할 수 있었다.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.8
• /
• pp.27-31
• /
• 2013

In this paper, we propose a new quantization method using fuzzy C-means clustering(FCM) for lumbar ultrasound image recognition. Unlike usual histogram based quantization, our method first classifies regions into 10 clusters and sorts them by the central value of each cluster. Those clusters are represented with different colors. This method is efficient to handle lumbar ultrasound image since in this part of human body, the brightness values are distributed to doubly skewed histogram in general thus the usual histogram based quantization is not strong to extract different areas. Experiment conducted with 15 real lumbar images verified the efficacy of proposed method.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.5
• /
• pp.29-32
• /
• 2012

In this paper, we propose a novel method to extract muscle area from lumbar ultrasonographic image. The muscle area resided in lumbar area can be defined as the area between thoracic vertebra and subcutaneous fat area. A modified 4-directional contour tracing algorithm is designed to detect the boundaries and candidate areas are extracted and verified by the morphological characteristics of lumbar area. The experiment using 392 lumbar images verifies that the proposed method is sufficiently effective by showing over 94% accuracy in extraction.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2010.07a
• /
• pp.413-416
• /
• 2010

본 논문에서는 요부 영상에서 근육을 추출하는 방법을 제안한다. 제안된 방법은 초음파 영상에서 왜곡이 존재하지 않는 영역을 측정 할 근육 영역을 설정한 후, 초기 초음파 영상에서 불필요한 잡음을 제거하고 Ends-in Search Stretching 기법을 적용하여 근육 영역의 명암 대비를 강조한다. 그리고 형태학적 특징을 이용하여 등뼈 영역과 피하지방을 분리한 후, 4 방향 윤곽선 추적 알고리즘을 적용하여 피하지방의 하단 부분을 추출한다. 또한 최대 및 최소 명암도를 조정하여 얻어진 등뼈의 후보 영역에서 형태학적 특징을 이용하여 잡음을 제거하고 최종적으로 등뼈 영역을 추출한다. 추출된 등뼈 영역에 대해 피하지방층과 등뼈 사이를 근육의 두께로 측정한다. 본 연구에서 제안된 방법을 요부의 초음파 영상에 적용하여 근육 영역을 추출한 결과, 제안된 방법이 초음파 영상에서 근육 영역들의 두께를 측정하는데 기존의 근육 측정 방법보다 효과적인 것을 확인 할 수 있었다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.1-3
• /
• 2012

본 논문에서는 요부 초음파 영상에서 다열근의 두께를 자동으로 측정하는 방법을 제안한다. 기존의 방법에서는 Valley Search 알고리즘을 적용하여 측정 기준 객체를 추출하고 다열근의 두께를 측정하였으나, 다열근의 형태학적 위치 정보를 반영하지 않았기 때문에 잘못된 측정 기준 객체를 추출하는 단점이 있다. 따라서 본 논문에서는 중앙 객체 탐색 알고리즘을 적용하여 측정 기준 객체를 추출하고 다열근의 두께를 자동으로 측정하는 방법을 제안한다. 제안된 방법을 획득한 요부 초음파 영상을 대상으로 실험한 결과, 기존의 방법보다 효율적으로 측정 기준 객체를 추출하고 다열근의 두께를 기존의 방법보다 정확히 측정하는 것을 확인할 수 있었다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.55-60
• /
• 2011

In this paper, we propose a new method for extracting muscles from lumbar images. The proposed method sets areas without distortions with field expert's assistance as areas of measuring interest and removing noises from initial ultrasonic videos. Then, the method emphasizes the brightness contrast with Ends-in search stretching algorithm and separate thoracic vertebra from subcutaneous fat area using morphological characteristics. 4-directions contour tracing algorithm is applied to extract the bottom of subcutaneous fat area. Extracting thoracic vertebra area requires noise removal and morphological characteristics as well among candidate areas obtained by controlling min-max brightness. The thickness of muscles is then defined as the length between subcutaneous fat area and extracted thoracic vertebra. The experiment which consists of 368 image analysis verifies that the proposed method is more effective in measuring the thickness of muscles than before.

• Korean Journal of Applied Biomechanics
• /
• v.19 no.4
• /
• pp.689-696
• /
• 2009

This study was conducted to examine the effects of the lumbar stabilization exercise (LSE) on fall prevention in elderly females (n = 21) by measuring changes in the isometric strength, multifidus, transverse abdominis muscle thickness, and posture stability index. The strength of isometric contraction was measured by the 3-D Pegasus system ; the thickness of the multifidus and transverse abdominis were measured by using Sonoace 6000C, and the posture stability index was measured using a computerized Biodex Balance System SD apparatus analysis. These results lead us to the conclusion that flexion and extension, left rotation on strength of isometric contraction, and thickness of the transverse abdominis (when released) statically increased. Overall, the anterior/posterior and medial/lateral elements in the posture stability index statically decreased, Consequently, the LSE should the prevent falls in elderly females.

• The Journal of the Korea Contents Association
• /
• v.11 no.4
• /
• pp.235-243
• /
• 2011

The purpose of the study was to examine the thickness of the trunk muscles ie. external obliques (EO), transversus abdominis (TrA), and multifidus and the trunk endurance strength in order to determine any relationship between the presence or absence of low back pain (LBP) and the size of trunk muscles. Data were obtained from 50 subjects, aged between 19-29 years. Participants had no experience of spinal problems that had resulted in a restriction of normal activity or time-off work and no current spinal symptoms. Measurements of muscle thickness of the trunk muscles were collected at rest, contraction and 15 seconds of post contraction during endurance strength tests. Background information was obtained followed all physical measures. Subjects were divided into two groups based on their experience of LBP. In draw-in maneuver, increasing the thickness of TrA was observed in all participants while EO was decreased at contraction in group 1 and increase in group 2. Only subjects in the group 2 had TrA increased during the flexion endurance test. In the side-bridge endurance test, the thickness of the right TrA was also observed differently between groups. Therefore, the results of the study may suggest that a function of specific muscle should be addressed for training persons with LBP.