Premium
Neural network approach to image reconstruction from projections
Author(s) -
Wang Yuanmei
Publication year - 1998
Publication title -
international journal of imaging systems and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.359
H-Index - 47
eISSN - 1098-1098
pISSN - 0899-9457
DOI - 10.1002/(sici)1098-1098(1998)9:5<381::aid-ima8>3.0.co;2-6
Subject(s) - computer science , artificial neural network , convolution (computer science) , microcomputer , iterative reconstruction , image (mathematics) , image processing , algorithm , artificial intelligence , telecommunications , chip
In this article, we formulate the image reconstruction problem in terms of a multicriteria optimization‐based neural network model, and study its performance. The value of neural network as a computational device is to be shown. We also demonstrate the efficiency of our implementation of neural net processing and compare its performance with respect to the convolution‐backprojection reconstruction techniques based on computer‐generated noisy projections. The method presented here has the particular ability to solve ill‐posed reconstruction problems. The algorithm described was implemented on a serial PC/Intel 586 microcomputer, but was cast in a form which is ideally suited for parallel processing. © 1998 John Wiley & Sons, Inc. Int J Imaging Syst Technol, 9, 381–387, 1998