Curvature Augmented Deep Learning For 3D Object Recognition
Keywords
3D Object Recognition; Computational Geometry; Convolutional Neural Networks; Deep Learning
Abstract
This paper presents a new method to incorporate shape information into convolutional neural network (CNN)s for 3D object recognition. Voxel CNNs have been very successful with the task of 3D object recognition. However, continuous shape information that is useful for recognition is often lost in their conversion to a voxel representation. We propose a single dimensional feature that can be applied to voxel CNNs. This paper presents a novel rotation-invariant feature based on mean curvature that improves shape recognition for voxel CNNs. We augment the recent voxel CNN Octnet architecture with our feature and demonstrate a 1 % overall accuracy increase on the ModelNet 10 dataset.
Publication Date
8-29-2018
Publication Title
Proceedings - International Conference on Image Processing, ICIP
Number of Pages
3648-3652
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICIP.2018.8451487
Copyright Status
Unknown
Socpus ID
85062898142 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85062898142
STARS Citation
Braeger, Sarah and Foroosh, Hassan, "Curvature Augmented Deep Learning For 3D Object Recognition" (2018). Scopus Export 2015-2019. 10056.
https://stars.library.ucf.edu/scopus2015/10056