30 October 2009 Automatic contour extraction for multiple objects based on Schroedinger transform of image
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 749545 (2009) https://doi.org/10.1117/12.829020
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
Abstract
Analytical and numerical solutions of the Schroedinger Equation which was satisfied by the propagator P(b, a) , including all the paths contribution, are discussed. The definition of Schrödinger transform of image is first proposed. Exterior and interior of objects are obtained from Schroedinger transforms of original image and its inverse image. Using the bruteforce algorithm, sets of exterior and interior points are thinned. By finding pairs of exterior and interior points with the smallest distance between them, contours of multiple objects are extracted. Some experiments with simulated and real images are given.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Liantang Lou, Liantang Lou, Ling Lu, Ling Lu, Wenliang Gao, Wenliang Gao, Lingling Li, Lingling Li, Zhongliang Fu, Zhongliang Fu, } "Automatic contour extraction for multiple objects based on Schroedinger transform of image", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 749545 (30 October 2009); doi: 10.1117/12.829020; https://doi.org/10.1117/12.829020
PROCEEDINGS
6 PAGES


SHARE
Back to Top