Filtern
Dokumenttyp
- Vortrag (3)
- Beitrag zu einem Tagungsband (2)
- Beitrag zu einem Sammelband (1)
- Dissertation (1)
Referierte Publikation
- nein (7)
Schlagworte
- Bayesian network (1)
- CDHMM (1)
- CT (1)
- Crack detection (1)
- Curve detection (1)
- DR (1)
- Detection in noisy images (1)
- Digitale Detektoren (1)
- Dynamic programming (1)
- Grenzen der Bildqualität (1)
Eingeladener Vortrag
- nein (3)
A new algorithm for detection of longitudinal crack-like indications in radiographic images is developed in this work. Conventional local detection techniques give unsatisfactory results for this task due to the low signal to noise ratio (SNR ~ 1) of crack-like indications in radiographic images. The usage of global features of crack-like indications provides the necessary noise resistance, but this is connected with prohibitive computational complexities of detection and difficulties in a formal description of the indication shape. Conventionally, the excessive computational complexity of the solution is reduced by usage of heuristics. The heuristics to be used, are selected on a trial and error basis, are problem dependent and do not guarantee the optimal solution. Not following this way is a distinctive feature of the algorithm developed here. Instead, a global characteristic of crack-like indication (the estimation function) is used, whose maximum in the space of all possible positions, lengths and shapes can be found exactly, i.e. without any heuristics. The proposed estimation function is defined as a sum of a posteriori information gains about hypothesis of indication presence in each point along the whole hypothetical indication. The gain in the information about hypothesis of indication presence results from the analysis of the underlying image in the local area. Such an estimation function is theoretically justified and exhibits a desirable behaviour on changing signals. The developed algorithm is implemented in the C++ programming language and testet on synthetic as well as on real images. It delivers good results (high correct detection rate by given false alarm rate) which are comparable to the performance of trained human inspectors.
Recent developments for automatic detection of crack indications in welding
seams are presented addressing the task from a probabilistic point of view.
This work improves the algorithm developed several years ago. The distinctive
feature of these algorithms is a translation of the task of detection into an
optimisation task in such a way, that the the maximum of a scoring function in
the space of all possible positions, lengths and shapes can be found exactly and
computationally effective. The progress of the new algorithm presented here
consists in the replacement of the discrete (binary) model of crack indications
(i.e. defect present vs. defect absent) previously used with a continuous grey
value model and the development of a new scoring function. The restriction
of the noise model to additive Gaussian allowed the utilisation of conjugate
priors for the posterior probability estimation in a computationally effective
way too. Results of experimental evaluation of the developed algorithm are
presented.