Automated surface-anomaly detection using machine learning has become an interesting and promising area of research, with a very high and direct impact on the application domain of visual inspection. Deep-learning methods have become the most suitable approaches for this task. They allow the inspection system to learn to detect the surface anomaly by simply showing it a number of exemplar images. This paper presents a segmentation-based deep-learning architecture that is designed for the detection and segmentation of surface anomalies and is demonstrated on a specific domain of surface-crack detection. The design of the architecture enables the model to be trained using a small number of samples, which is an important requirement for practical applications. The proposed model is compared with the related deep-learning methods, including the state-ofthe-art commercial software, showing that the proposed approach outperforms the related methods on the specific domain of surface-crack detection. The large number of experiments also shed light on the required precision of the annotation, the number of required training samples and on the required computational cost. Experiments are performed on a newly created dataset based on a real-world quality control case and demonstrates that the proposed approach is able to learn on a small number of defected surfaces, using only approximately 25-30 defective training samples, instead of hundreds or thousands, which is usually the case in deeplearning applications. This makes the deep-learning method practical for use in industry where the number of available defective samples is limited. The dataset is also made publicly available to encourage the development and evaluation of new methods for surface-defect detection.

Earth-and space-based observations provide synergistic information for space mission encounters by providing data over longer timescales, at different wavelengths and using techniques that are impossible with an in situ flyby. We report here such observations in support of the EPOXI spacecraft flyby of comet 103P/Hartley 2. The nucleus is small and dark, and exhibited a very rapidly changing rotation period. Prior to the onset of activity, the period

No abstract

No abstract

A new semiempirical model called FRANG for calculation of fragment emission angles in light and heavy ion fragmentation reactions was developed. Contributions from both central and peripheral collisions were investigated, where fragmentation occurs due to nuclear and Coulomb interaction, respectively. For central collisions the reaction was described by a two step abrasion-ablation model, where collision parameters were determined from a simple geometrical model. The fragment emission angles were calculated using a parametrization of longitudinal momentum loss and transverse momentum uptake in the collision of projectile and target atom. For peripheral collisions the Coulomb excitation of nucleon vibration resonances and subsequent decay into fragments was taken into account. Fragment emission angles were calculated from deflection in the electric field and from the amplitude of vibrations in excited nuclear states. The modeled emission angles were in accordance with the experimental values for most projectile-target systems examined and compared. It was established that the model very well reproduces the experimental results in the energy region Ͻ200 MeV/ nucleon, despite its simplicity, and can be successfully employed in several applications. The model is estimated to be valid in the energy range from a few 10 MeV/ nucleon up to few 100 MeV/ nucleon.