No abstract

No abstract

In the present paper we propose a method for fast segmentation of ultrasound data. It is based on setting up a model depending on user input. We apply a matching scheme in order to obtain initial contours for 2D segmentation of several cross-sections of the organ by a discrete dynamic contour. Further, we set up an active image which drives the deformation of the dynamic contour. The active image comprises both iexiuml information based on image data as well as spatial information which we derive from the inital contour. We design the active image according to user input and image quality to aid the segmentation task.

No abstract

We investigated optimal implementation strategies for industrial inspection systems aiming to detect cracks on ground steel billets’ surfaces by combining state-of-the-art AI-based methods and classical computational imaging techniques. In 2D texture images, the interesting patterns of surface irregularities are often surrounded by visual clutter, which is to be ignored, e.g., grinding patterns. Even neural networks struggle to reliably distinguish between actual surface disruptions and irrelevant background patterns. Consequently, the image acquisition procedure already has to be optimised to the specific application. In our case, we use photometric stereo (PS) imaging to generate 3D surface models of steel billets using multiple illumination units. However, we demonstrate that the neural networks, especially in high-speed scenarios, still suffer from recognition deficiencies when using raw photometric stereo camera data, and are unable to generalise to new billets and image acquisition conditions. Only the additional application of adequate state-of-the-art image processing algorithms guarantees the best results in both aspects. The neural networks benefit when appropriate image acquisition methods together with image processing algorithms emphasise relevant surface structures and reduce overall pattern variation. Our proposed combined strategy shows a 9.25% better detection rate on validation data and is 14.7% better on test data, displaying the best generalisation.