Autoencoder-based part clustering for part-in-whole retrieval of CAD models. (June 2019)

• Record Type: Journal Article
• Authors: Muraleedharan, Lakshmi Priya; Kannan, Shyam Sundar; Muthuganapathy, Ramanathan
• Is Part Of: Computers & graphics. Volume 81(2019)
• Page Start: 41
• Page End: 51
• Publication Date: 2019-06
• Subjects: Segmentation -- Part-based -- CAD mesh model -- Hyperbolic points -- Autoencoder -- Unsupervised part clustering; Computer graphics -- Periodicals; 006.6
• DOI: 10.1016/j.cag.2019.03.016
• Languages: English
• ISSNs: 0097-8493

Abstract

Highlights: A non-parametric algorithm for segmentation of CAD mesh models. Segmentation algorithm has been shown to perform well for noisy CAD models. Proposed a novel Feature description based on Gauss map of the segments. Proposed an Autoencoder-based approach for clustering of segments. Extensive comparative studies demonstrates that our algorithm is comparable or better than other existing methods. Graphical abstract: Abstract: Part-in-whole retrieval (PWR) is an important problem in the field of computer-aided design (CAD) with applications in design reuse, feature recognition and suppression and so on. Initially, we present a non-parametric (and hence threshold independent) algorithm for segmenting CAD models (represented as meshes) which does not require any user intervention. As there is no labelled segmented dataset available for part clustering, we propose the use of autoencoders, one of the approaches used in deep networks along with hierarchical clustering. The features for autoencoder is derived from the Gauss map of the segments. The autoencoder network is then trained and validated using a hierarchical clustering-based approach that generates a dictionary of labels for each segment. PWR is then done by testing a query model with the network that retrieves models having the query as their subset. Comparison of the segmentation algorithm with the state-of-the-art approaches indicate that it performs better or on par. The algorithm was also tested for noisy models. Results of the part clustering and PWR are also presented for models from a CAD dataset along with the discussions.