Approach to Identification of Changes from Local Surface Normal Analysis of RTI Data in Application to Cultural Heritage

Identification of changes from cultural heritage (CH) surfaces incor- porates several factors like noise from the surface, error from the acquisition system, and alignment of the two phases of information in a one-time frame. In the post-processing pipeline for change iden- tification, the alignment always generates a bias in calculating the changes. This work proposes a pipeline for processing the surface normal calculated from a simulated Reflectance Transformation Imaging (RTI) acquisition. In this work, we have proposed a normal distribution analysis of the neighboring pixels to give more confi- dence to the change detection method. To claim the ground truth of the segmentation method based on a normal distribution, we have decided to work on the simulated RTI acquisitions. This will help us eliminate the mentioned errors and noises and check their validity. We have considered a visual inspection of the normal distribution of the neighboring pixels and set several parameters to group the several behaviors of the surface changes. From the segmentation, a semi-quantitative change calculation is also possible based on the segmented pixel count in each surface stage. The considered parameters were normalized to make the method independent of the acquisition parameters such as camera and light positions and magnification.