Abstract
3D shape recognition becomes necessary due to the popularity of 3D data resources. This paper aims to introduce the new method, hybrid deep learning network convolution neural network–support vector machine (CNN–SVM), for 3D recognition. The vertices of the 3D mesh are interpolated to be converted into Point Clouds; those Point Clouds are rotated for 3D data augmentation. We obtain and store the 2D projection of this 3D augmentation data in a 32 × 32 × 12 matrix, the input data of CNN–SVM. An eight-layer CNN is used as the algorithm for feature extraction, then SVM is applied for classifying feature extraction. Two big datasets, ModelNet40 and ModelNet10, of the 3D model are used for model validation. Based on our numerical experimental results, CNN–SVM is more accurate and efficient than other methods. The proposed method is 13.48% more accurate than the PointNet method in ModelNet10 and 8.5% more precise than 3D ShapeNets for ModelNet40. The proposed method works with both the 3D model in the augmented/virtual reality system and in the 3D Point Clouds, an output of the LIDAR sensor in autonomously driving cars.
Highlights
The 3D shapes recognition problem has been studied over a long period in the computer age with many applications in real life, such as robotics, autonomous driving, augmented/mixed reality, and so on
Our experiments will work on the ModelNet dataset, including ModelNet10 and ModelNet40
Our experiments will work on the ModelNet dataset, including ModelNet10 and ModelNet40 [16]
Summary
The 3D shapes recognition problem has been studied over a long period in the computer age with many applications in real life, such as robotics, autonomous driving, augmented/mixed reality, and so on. Many remarkable achievements in 2D object recognition have been made subsequently by the strong learning capability of a convolution neural network (CNN) and large-scale training datasets. Unlike conventional 2D images, there is a limit in the progress of 3D shape recognition [1]. The reason is that a 2D manifolds’ representation of 3D models is not similar to the representation of 2D images. The 3D models’ representation as 2D manifolds are not similar to 2D images representation, and a standard method to store the information of 3D geometrical shapes has not been developed [2]. It seems hard to select deep learning techniques directly for 3D shape recognition. Presentations obtained for 3D shapes have significantly affected the performance of shape recognition
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
