relation: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/2651/ title: Features Detection from Industrial Noisy 3D CT Data for Reverse Engineering creator: Ma Thi, Chau creator: Park, Chang-soo creator: Suthunyatanakit, Kittichai creator: Oh, Min-jae creator: Kim, Tae-wan creator: Kang, Myung-joo creator: Bui, The Duy subject: Information Technology (IT) description: To detect features are significantly important for reconstructing a model in reverse engineering. In general, it is too difficult to find the features from the original industrial 3D CT data because the data have many noises. So it is necessary to reduce the noises for detecting features. This paper proposes a new method for detecting corner features and edge features from noisy 3D CT scanned data. First, we applied the level set method[18] to CT scanned image in order to segment the data. Next, in order to reduce noises, we exploited nonlocal means method[19] to the segmented surface. This helps to detect the edges and corners more accurately. Finally, corners and sharp edges are detected and extracted from the boundary of the shape. The corners are detected based on Sobel-like mask convolution processing with a marching cube. The sharp edges are detected based on Canny-like mask convolution with SUSAN method[13], which is for noises removal. In the paper, the result of detecting both features is presented. date: 2012 type: Conference or Workshop Item type: PeerReviewed identifier: Ma Thi, Chau and Park, Chang-soo and Suthunyatanakit, Kittichai and Oh, Min-jae and Kim, Tae-wan and Kang, Myung-joo and Bui, The Duy (2012) Features Detection from Industrial Noisy 3D CT Data for Reverse Engineering. In: Multimedia, Computer Graphics and Broadcasting.