|
A Web-based on-machine mould matching and measurement system based on CAD/CAM/CAI integration
CHOI Jin-hwa, JEON Byung-cheol, KIM Gun-hee, SHIN Bong-cheol, LEE Honghee, CHO Myeong-woo, SEONG Eun-je, PARK Dong-sam
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2006, 7(9): 1474-1481.
https://doi.org/10.1631/jzus.2006.A1474
The purpose of this study is to develop a Web-based on-machine mould identification and measurement system. The Web-based mould identification system matches obtained vision information with CAD database. Developed Web-based system is to exchange messages between a server and a client by making of ActiveX control, and the result of mould identification is shown on Web-browser at remote site. For effective feature classification and extraction, the signature method is used to make meaningful information from obtained image data. For on-machine measurement of the matched mould, inspection database is constructed from CAD database using developed inspection planning methods. The results are simulated and analyzed using developed system to verify the effectiveness of the proposed methods.
|
|
Texture classification based on EMD and FFT
XIONG Chang-zhen, XU Jun-yi, ZOU Jian-cheng, QI Dong-xu
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2006, 7(9): 1516-1521.
https://doi.org/10.1631/jzus.2006.A1516
Empirical mode decomposition (EMD) is an adaptive and approximately orthogonal filtering process that reflects human’s visual mechanism of differentiating textures. In this paper, we present a modified 2D EMD algorithm using the FastRBF and an appropriate number of iterations in the shifting process (SP), then apply it to texture classification. Rotation-invariant texture feature vectors are extracted using auto-registration and circular regions of magnitude spectra of 2D fast Fourier transform (FFT). In the experiments, we employ a Bayesion classifier to classify a set of 15 distinct natural textures selected from the Brodatz album. The experimental results, based on different testing datasets for images with different orientations, show the effectiveness of the proposed classification scheme.
|
|
A new fast algorithm for computing the distance between two disjoint convex polygons based on Voronoi diagram
YANG Cheng-lei, QI Meng, MENG Xiang-xu, LI Xue-qing, WANG Jia-ye
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2006, 7(9): 1522-1529.
https://doi.org/10.1631/jzus.2006.A1522
Computing the distance between two convex polygons is often a basic step to the algorithms of collision detection and path planning. Now, the lowest time complexity algorithm takes O(logm+logn) time to compute the minimum distance between two disjoint convex polygons P and Q, where n and m are the number of the polygons’ edges respectively. This paper discusses the location relations of outer Voronoi diagrams of two disjoint convex polygons P and Q, and presents a new O(logm+logn) algorithm to compute the minimum distance between P and Q. The algorithm is simple and easy to implement, and does not need any preprocessing and extra data structures.
|
8 articles
|