A novel CNN method for the accurate spatial data recovery from digital images. (2023)

• Record Type: Journal Article
• Authors: Murugan, G.; Moyal, Vishal; Nandankar, Praful; Pandithurai, O.; John Pimo, Er.S.
• Is Part Of: Materials today. Volume 80:Part 3(2023)
• Page Start: 1706
• Page End: 1712
• Publication Date: 2023
• Subjects: R-CNN -- Machine learning -- Digital images; Materials science -- Congresses -- Periodicals; 620.1
• DOI: 10.1016/j.matpr.2021.05.351
• Languages: English
• ISSNs: 2214-7853

Abstract

Abstract: The parsing of floorplans has been an issue for a long time in automated document processing and with algorithmic methods until recent years. This problem has also improved output with the emergence of convolutionary neural networks (CNN). The job here is to obtain spatial and geometrical data from floorplans as accurately as possible. The aim of this project is to extract the most information from a floor plan image around instance segmentation models like Cascade Mask R-CNN. A new style of key point CNN is being implemented to supplement the segmentation to find correct corner positions. Then the resulting segmentation is combined in a post-processing stage. With a mean IoU of 72.7 percent versus 57.5 percent, the resulting segmentation scores surpass the existing baseline of the CubiCasa5k floorplan data base. Moreover, for almost every class, the mean IoU for each class is increased. Cascade Mask R-CNN has also been shown to be better suited to this role than Mask R-CNN.