Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/106515
Title: A pellet sphericity measure system based on dual active contour models
Authors: Shi, D.-M.
Heng, P.W.S. 
Chen, F.
Keywords: Dual active contour model
Image processing
Pharmaceutical manufacturing
Sphericity
Issue Date: 2003
Source: Shi, D.-M.,Heng, P.W.S.,Chen, F. (2003). A pellet sphericity measure system based on dual active contour models. International Conference on Machine Learning and Cybernetics 5 : 2781-2784. ScholarBank@NUS Repository.
Abstract: The spherical granules play very important role in pharmaceutical manufacturing, since spheroids are ideal for coating as their shape allows for the application of a uniform layer of coating material. There are many factors affecting the pellet sphericity in shperonization process, such as the starting materials, spheronization speed, residence time, etc. A satisfactory sphericity measure can indicate how to adjust the starting materials and the operating variables. In this paper, edge detection is employed to obtain a pellet image boundary robustly and then calculate the pellet sphericity. Active contour models, also termed as snakes by the nature of their evolution are a sophisticated approach to contour extraction. Conventional snakes suffer difficulty in appropriate choice of an initial contour and values of parameters. The dual active contour models can relieve this problem by combining with a local shape model to improve the parameterization. This methodology has been applied to our sphericity measure system.
Source Title: International Conference on Machine Learning and Cybernetics
URI: http://scholarbank.nus.edu.sg/handle/10635/106515
ISBN: 0780378652
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

31
checked on Feb 17, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.