DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Yoon, Young-Gyu | - |
dc.contributor.advisor | 윤영규 | - |
dc.contributor.author | Kang, Woosuk | - |
dc.date.accessioned | 2022-04-27T19:31:27Z | - |
dc.date.available | 2022-04-27T19:31:27Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948674&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/296025 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2021.2,[ii, 26 p. :] | - |
dc.description.abstract | Image segmentation is one of the most important tasks in medical image analysis and is the starting point to understand how brain functions. Recently studies have been focused on supervised deep segmentation algorithms, but in the brain image domain, sufficient pixel-level label data are hard to obtain. In this paper, focusing on the color information of Brainbow data where each neurons are stained into different colors, and address the problem with unsupervised instance segmentation, presenting b-Net, a more powerful architecture for Brainbow image instance segmentation. Our architecture is a 3D encoder-decoder network where it properly function as auto-encoder through sparsity constraint, where encoder produces a k-way pixel-wise prediction, providing meaningful segmentation results in the ProExM Brainbow neuron segmentation. Here encoder is also trained to function as CRF, utilizing the label consistency for segmentation. It is shown that the proposed model can provide proper segmentation for each neuron. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Brainbow▼aUnsupervised Segmentation▼aAutoencoder▼aSparsity Constraint▼aCRF▼a3D | - |
dc.subject | 브레인보우▼a비지도학습▼a오토인코더▼a희소성 제약▼a조건부 무작위장▼a3차원 | - |
dc.title | b-Net: a 3D neural network for unsupervised instance segmentation of brainbow | - |
dc.title.alternative | 비넷: 비지도학습 브레인보우 객체 분할을 위한 3차원 인공신경망 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 강우석 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.