RESUMEN
Deflectometry has been widely used to detect defects on specular surfaces. However, it is still very challenging to detect defects on semispecular or diffuse surfaces because of the low contrast and low signal-to-noise ratio. To address this challenge, we proposed a phase-modulation combined method for accurate defect detection. Based on the phase and modulation of captured fringes, a dual-branch convolutional neural network is employed to simultaneously extract geometric and photometric features from the phase-shifting pattern sequence and modulation, which improves the defect detection performance significantly. Compared to state-of-the-art methods, we believe the results demonstrated the proposed method's effectiveness and capability to reduce false positives.
RESUMEN
Inter-reflection removal is vital for complex-scene reconstruction. However, most methods assume that the tested surface is a diffuse, and are limited to removal of inter-reflection caused only by diffuse reflections. For all kinds of inter-reflections caused by diffuse and specular reflections, a micro-frequency shifting (MFS) projection technique is presented. Because the modulation variation with frequency in inter-reflection regions is larger than that of other regions, we use the MFS technique to detect inter-reflections, where patterns with specifically designed frequency-shifts and base frequencies are projected. Inter-reflections are detected through large variations in modulation, and removed using a regional-projection technique. Experimental results validate the effectiveness for diffuse and specular inter-reflection removal.