Vertical‐horizontal‐context‐based high numerical precision synthesis of masked line‐scan X‐ray image

Abstract

Material identification based on R_value (Transparency natural logarithm ratio of low‐energy to high‐energy.) of line‐scan dual‐energy X‐ray transmission (DE‐XRT) has a good prospect for industrial application. Unfortunately, the DE‐XRT signals before attenuation within the material range cannot be directly measured, whereas their precision has essential effect on R_value. Therefore, a vertical‐horizontal‐context‐based signal synthesis method was proposed to rebuilt incomplete/masked image, which takes the filtered signals outside the material range as the reference context, and takes into account the vertical (forward/column/Y) and horizontal (scanning/row/X) anisotropy. The vertical is a time series with continuity of signal trend; the horizontal is a spatial characteristic with the fluctuation synchronization within the same row signals. The vertical curves are synthesized one by one, thus extending to the whole surface. The special rigorous synthesis evaluations of curve synthesis difference and surface synthesis difference were also proposed. Experimental results show that the tow evaluations are both only around 0.0007, and it only takes 35 ms to complete the surface synthesis of 119 × 119 pixels on the CPU with 3.4 GHz main frequency. This high numerical precision can match the similarly filtered signals after attenuation so as to improve the accuracy of R_value. And this, together with calculation real‐time, can promote the application of industrial inline material identification.