Neural netwok based X-ray tomography for fast inspection of apples on a conveyor belt system

The throughput of an inline computed tomography (CT) based inspection system depends on the speed of its image reconstruction algorithm. Filtered back projection (FBP) provides fast reconstructions, but requires many high quality radiographs from all angles to obtain accurate reconstructions. This is not achievable in an inline environment. Iterative reconstruction methods yield adequate reconstructions from limited, but they are slow. Recently a new reconstruction algorithm was introduced [1] that can handle limited data and is very fast: the neural network FBP (NN-FBP). In this work, we introduce a neural network (NN) based Hilbert transform FBP (NN-hFBP) for inline inspection. This method reconstructs images with a filter-based Hilbert transform FBP method. The filters are application specific and trained by a neural network. Comparison of the NN-hFBP and conventional reconstruction methods applied to inline fan-beam X-ray data of apples shows that the NN-hFBP yields high quality images in a short reconstruction time.