A hierarchical system is proposed by using simulated annealing for the detection of lines, circles, ellipses, and hyperbolas in image. The hierarchical detection procedures are type by type and pattern by pattern. The equation of ellipse and hyperbola is defined under translation and rotation. The distance from all points to all patterns is defined as the error. Also we use the minimum error to determine the number of patterns. The proposed simulated annealing parameter detection system can search a set of parameter vectors for the global minimal error. In the experiments, using the hierarchical system, the result of the detection of a large number of simulated image patterns is better than that of using the synchronous system. In the seismic experiments, both of two systems can well detect line of direct wave and hyperbola of reflection wave in the simulated one-shot seismogram and the real seismic data, but the hierarchical system can converge faster. The results of seismic pattern detection can improve seismic interpretation and further seismic data processing.
[1]
Alan F. Murray,et al.
International Joint Conference on Neural Networks
,
1993
.
[2]
N. Metropolis,et al.
Equation of State Calculations by Fast Computing Machines
,
1953,
Resonance.
[3]
Jayanta Basak,et al.
Hough transform network: learning conoidal structures in a connectionist framework
,
2002,
IEEE Trans. Neural Networks.
[4]
Kou-Yuan Huang,et al.
Simulated Annealing for Pattern Detection and Seismic Application
,
2007,
IJCNN.
[5]
C. D. Gelatt,et al.
Optimization by Simulated Annealing
,
1983,
Science.
[6]
Kou-Yuan Huang,et al.
Image processing of seismograms: (a) Hough transformation for the detection of seismic patterns; (b) thinning processing in the seismogram
,
1985,
Pattern Recognit..