Rotation Invariance in Floor Plan Digitization using Zernike Moments
This addresses the challenge of converting scanned floor plans into machine-readable formats for further use, though it appears incremental as it builds on existing region adjacency graph methods.
The paper tackles the problem of digitizing rotated floor plan images by proposing an end-to-end pipeline that improves rotation invariance in region adjacency graph feature extraction, resulting in enhanced F1 score and IoU on rotated data.
Nowadays, a lot of old floor plans exist in printed form or are stored as scanned raster images. Slight rotations or shifts may occur during scanning. Bringing floor plans of this form into a machine readable form to enable further use, still poses a problem. Therefore, we propose an end-to-end pipeline that pre-processes the image and leverages a novel approach to create a region adjacency graph (RAG) from the pre-processed image and predict its nodes. By incorporating normalization steps into the RAG feature extraction, we significantly improved the rotation invariance of the RAG feature calculation. Moreover, applying our method leads to an improved F1 score and IoU on rotated data. Furthermore, we proposed a wall splitting algorithm for partitioning walls into segments associated with the corresponding rooms.