16065 2007 eng 1 16 (Poster P1) conferenceobject Lyon, France 0 -- -- -- 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. DIR 2007 - International Symposium on Digital Industrial Radiology and Computed Tomography (Proceedings) 18024 http://www.ndt.net/article/dir2007/papers/p1.pdf Sonderstandort: Publica-Schrank DIR 2007 - International Symposium on Digital industrial Radiology and Computed Tomography Lyon, France 2007-06-25 2007-06-27 0 Oleksandr Alekseychuk Uwe Zscherpel eng uncontrolled Industrial radiographic testing eng uncontrolled Crack detection eng uncontrolled Curve detection eng uncontrolled Detection in noisy images eng uncontrolled Bayesian network eng uncontrolled HMM eng uncontrolled CDHMM eng uncontrolled Dynamic programming eng uncontrolled Kalman filter Physisches Exemplar in der Bibliothek der BAM vorhanden ("Hardcopy Access") Graue Literatur