최근에 광간섭 단층촬영은 생물학적 조직을 비 침습적으로 이미지를 얻는데 많이 사용되고 있다. 그러나, 광간섭 단층촬영은 노이즈 때문에 해석하는데 아직까지는 어려움을 갖고 있다. 본 논문에서는 인체와 토끼의 연골 이미지들의 이미지에서 잡음을 제거하는 다양한 영상처리 기술을 적용해 보았다. 또한 광간섭 단층촬영으로 얻은 이미지들을 영상 분할 방법을 통해 얻고자 하는 부위를 구별 하였으며 대부분의 이미지들이 영상분할 알고리즘에 적합함을 볼 수 있었다. 그리고, 광간섭 단층영상에 적합한 영상분할 방법을 선택한 후 영상을 재구성 하였다. 광간섭 단층촬영은 작은 깊이와 거리에 제한을 가지고 있기 때문에 영상처리장치에 단점을 가지고 있다. 광간섭 이미지가 매우 작은 공간에서 이루어 짐으로 같은 지역의 영상을 재구성 하기는 어려운 점이 있다. 그래서, 광간섭 단층영상 재구성을 할 때 좋은 매칭 알고리즘 방법이 필요하다. 본 논문에서는 챔퍼 매칭 알고리즘을 사용하여 재구성 하였다. 본 연구에서는 OCT 연골 이미지를 얻어 노이즈 제거, 영상 분할, 3D 광간섭 단층 영상을 재구성 할 수 있었다.
최근에 광간섭 단층촬영은 생물학적 조직을 비 침습적으로 이미지를 얻는데 많이 사용되고 있다. 그러나, 광간섭 단층촬영은 노이즈 때문에 해석하는데 아직까지는 어려움을 갖고 있다. 본 논문에서는 인체와 토끼의 연골 이미지들의 이미지에서 잡음을 제거하는 다양한 영상처리 기술을 적용해 보았다. 또한 광간섭 단층촬영으로 얻은 이미지들을 영상 분할 방법을 통해 얻고자 하는 부위를 구별 하였으며 대부분의 이미지들이 영상분할 알고리즘에 적합함을 볼 수 있었다. 그리고, 광간섭 단층영상에 적합한 영상분할 방법을 선택한 후 영상을 재구성 하였다. 광간섭 단층촬영은 작은 깊이와 거리에 제한을 가지고 있기 때문에 영상처리장치에 단점을 가지고 있다. 광간섭 이미지가 매우 작은 공간에서 이루어 짐으로 같은 지역의 영상을 재구성 하기는 어려운 점이 있다. 그래서, 광간섭 단층영상 재구성을 할 때 좋은 매칭 알고리즘 방법이 필요하다. 본 논문에서는 챔퍼 매칭 알고리즘을 사용하여 재구성 하였다. 본 연구에서는 OCT 연골 이미지를 얻어 노이즈 제거, 영상 분할, 3D 광간섭 단층 영상을 재구성 할 수 있었다.
Recently, optical coherence tomography (OCT) has demonstrated considerable promise for the noninvasive assessment of biological tissues. However, OCT images difficult to analyze due to speckle noise. In this paper, we tested various image processing techniques for speckle removal of human and rabbit...
Recently, optical coherence tomography (OCT) has demonstrated considerable promise for the noninvasive assessment of biological tissues. However, OCT images difficult to analyze due to speckle noise. In this paper, we tested various image processing techniques for speckle removal of human and rabbit cartilage OCT images. Also, we distinguished the images which get with methods of image segmentation for OCT images, and found the most suitable method for segmenting an image. And, we selected image segmentation suitable for OCT before image reconstruction. OCT was a weak point to system design and image processing. It was a limit owing to measure small a distance and depth size. So, good edge matching algorithms are important for image reconstruction. This paper presents such an algorithm, the chamfer matching algorithm. It is made of background for 3D image reconstruction. The purpose of this paper is to describe good image processing techniques for speckle removal, image segmentation, and the 3D reconstruction of cartilage OCT images.
Recently, optical coherence tomography (OCT) has demonstrated considerable promise for the noninvasive assessment of biological tissues. However, OCT images difficult to analyze due to speckle noise. In this paper, we tested various image processing techniques for speckle removal of human and rabbit cartilage OCT images. Also, we distinguished the images which get with methods of image segmentation for OCT images, and found the most suitable method for segmenting an image. And, we selected image segmentation suitable for OCT before image reconstruction. OCT was a weak point to system design and image processing. It was a limit owing to measure small a distance and depth size. So, good edge matching algorithms are important for image reconstruction. This paper presents such an algorithm, the chamfer matching algorithm. It is made of background for 3D image reconstruction. The purpose of this paper is to describe good image processing techniques for speckle removal, image segmentation, and the 3D reconstruction of cartilage OCT images.
* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.
문제 정의
The goal of this research most is to develop image processing where is suitable from OCT.
제안 방법
The mutual information technique is a volume-based registration method, and was derived for use with a communication channel. The scale factor was calculated using the voxel size information before the matching process, and six transform parameters (rotation in x, y, z and translation in x, y, z) were considered in this study. The registration tool was designed considering the accuracy and effectiveness of the registration process.
In this study, we used OCT images to observe the structure of human and rabbit cartilages. Before MRI was available, CT scans were used for medical imaging.
In this study, we per formed image segmentation using a region growing method and a thresholding method algorithm. Also, we prepared a foundation for the composition of 3-D images by using a chamfer matching algorithm to match images. We thus obtained the possibility of reconstituting a 3D image by improving on the method used for the OCT images.
An automatic image registration method was presented in this paper. The proposed system includes pre-processing, 2D segmentation, 3D registration, fusion, and rendering sub-systems for multi-modal OCT images.
대상 데이터
OCT and SD (spectral domain)-OCT setup. The components of the system are: a superluminescent diode source (SLD), single mode fiber (SMF).
이론/모형
This image segmentation worked well to divide the part that we wanted. The algorithm employs an edge detection method, thresholding method, region growing method, and watershed method. We used both an edge detection algorithm method and a thresholding algorithm method and segmented human and rabbit cartilage images.
We knew that using a method with more than two algorithms would be more effective for segmentation than the commonly used method for the human and rabbit cartilage images. In this study, we per formed image segmentation using a region growing method and a thresholding method algorithm. Also, we prepared a foundation for the composition of 3-D images by using a chamfer matching algorithm to match images.
Ho DS, Kim BM, Shin K, Hwang ID: Evaluation of a chip LED sensor module at 770 nm for fat thickness measurement of optical tissue phantoms and human body tissue. JKPS 51:1663-1667 (2007)
Rogowska J, Brezinski M: Image processing techniques for noise removal, enhancement and segmentation of cartilage OCT images. Phys Med Biol 47:641-655 (2002)
Tobias OJ, Seara R, Soares FAP: Automatic image segmentation using fuzzy sets. Proceedings of the 38th Midwest Symposium on Circuits and Systems 2:921-924 (1995)
Eom SG, Chang SC, Ahn BH: Watershed-based region merging using conflicting regions, Proceedings 2002 International Conference on Image Processing 2:II781-784 (2002)
Abdelsayed S, Ionescu D, Goodenough D: Matching and registration method for remote sensing images, Proceedings of the international geoscience and remote sensing symposium IGARSS'95, Florence, Italy, 1029-1031 (1995)
Alhichri HS, Kamel M: Virtual circles: a new set of features for fast image registration. P.A.Lett 24:1181-1190 (2003)
Cheung KW, Yeung DY, Chin RT: A bayesian framework for deformable pattern recognition with application to handwritten character recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 20:1382-1388 (1998)
Borgefors G: An improved version of the chamfer matching algorithm, In 7th Int. Conf, Pattern Recognition, Montreal, P.Q., Canada, 1175-1177 (1984)
Ho DS, Lee HK, Suh TS: Feature extraction and image segmentation of mechanical structures from human medical images. Korean Journal of Medical Physics 15:112-119 (2004)
Song JY, Nah BS, Suh TS: The application of chanfer matching algorithm to the reeor analysis of a treatment field between a cimulation image and a portal image. Korean Journal of Medical Physics 14:189-195 (2003)
※ AI-Helper는 부적절한 답변을 할 수 있습니다.