An Invariant Tangent-Angle Descriptor and a Band U-Net for 2D Fragment Adjacency Prediction

Key points

• We improved the two-stage architecture proposed in Beaulac's thesis, in which a rotation-equivariant Siamese convolutional neural network scores pairs of local image windows along the two contours of two fragments.1
• The scores are gathered in an adjacency matrix in which a ResNet detects the partial anti-diagonal band that reveals the adjacency of two fragments.1
• In the current work, we keep the pipeline and replace the local score by a comparison of tangent-angle profiles of contour windows, making it, by construction, invariant to fragment rotation and agnostic to the selected contour-starting point.1
• Furthermore, under the PairingNet pair-searching protocol conditions, our learned descriptor obtains a Recall@10 of 0.82 on the real set against 0.56 from the best model of the original paper.1

Sources (1)

• [1]An Invariant Tangent-Angle Descriptor and a Band U-Net for 2D Fragment Adjacency Prediction
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 05:14 AM

  This paper addresses the prediction of adjacency between pairs of 2D fragments based on their contours.

  We improved the two-stage architecture proposed in Beaulac's thesis, in which a rotation-equivariant Siamese convolutional neural network scores pairs of local image windows along the two contours of two fragments.

Extractive summary: sentences quoted from the sources.