Learning and Recognition of Primitive Threedimensional Shapes using Solid Angles

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2019 by IJETT Journal
Volume-67 Issue-12
Year of Publication : 2019
Authors : Satoshi Kodama, Kota Endo
DOI :  10.14445/22315381/IJETT-V67I12P212

Citation 

MLA Style: Satoshi Kodama, Kota Endo "Learning and Recognition of Primitive Threedimensional Shapes using Solid Angles" International Journal of Engineering Trends and Technology 67.12 (2019):74-82.

APA Style:Satoshi Kodama, Kota Endo. Learning and Recognition of Primitive Threedimensional Shapes using Solid Angles  International Journal of Engineering Trends and Technology, 67(12),74-82.

Abstract
Unlike two-dimensional shapes, recognition of three-dimensional shapes has various backgrounds depending on the viewpoint and rotation of the object; thus, shape recognition using machine learning techniques is very difficult. Generally, the black box nature of deep learning is problematic from an accountability perspective. Therefore, in this paper, we propose a method to evaluate the similarity for learning by focusing on polygons that make up a threedimensional shape and the solid angle for them. The value and pattern of the three-dimensional angle differ for each object shape; thus, by classifying based on the results of the proposed method, it is possible to perform learning and shape recognition. In this study, we verified the effectiveness of learning using three-dimensional angles and shape recognition by creating multiple primitive shapes as samples. In addition, we verified for threedimensional shape deformed part of the threedimensional primitive shape. As a result, using the solid angle, it was confirmed that can be effectively determined for three-dimensional primitive shapes.

Reference

[1] Min Liu, Fupin Yao, Chiho Choi, Ayan Sinha, Karthik Ramani, "Deep Learning 3D Shapes Using Alt-az Anisotropic 2-Sphere Convolution," 7th International Conference on Learning Representations, 2019.
[2] AI Scholar, https://ai-scholar.tech/treatise/deeplearning-3d- 36/, 2018.
[3] Daeyun Shin, Charless C. Fowlkes, Derek Hoiem, "Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction," Conference on Computer Vision and Pattern Recognition 2018, DOI: 10.1109/CVPR.2018.00323, 2018.
[4] David Griffiths, Jan Boehm, "A Review on Deep Learning Techniques for 3D Sensed Data Classification," Remote Sensing, 11(12), 1499, DOI: 10.3390/rs11121499, 2019.
[5] Katja Auernhammer, Ramin Tavakoli Kolagari, Markus Zoppelt, "Attacks on Machine Learning: Lurking Danger for Accountability," Conference on Artificial Intelligence 2019 (AAAI-19), 2019.
[6] Naveed Akhtar, Ajmal Mian, "Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey," in IEEE Access, vol. 6, pp. 14410-14430, DOI: 10.1109/ACCESS.2018.2807385, 2018.
[7] Tom Slee, "Algorithmic Accountability: The Other Side of Machine Learning," SAP SuccessFactors, https://www.successfactors.com/resources/knowledgehub/ algorithmic-accountability-the-other-side-of-machinelearning. html, 2019.
[8] Michael Fullan, Joanne Quinn, Joanne McEachen, "Deep Learning: Engage the World Change the World," Corwin, ISBN-10: 1506368581, 2017.
[9] Raju Gudhe, "Point Cloud Data for Deep Learning (Part_01)," https://medium.com/@graju1401/point-clouddata- for-deep-learning-part-01-ecc1445b3728, Medium, 2018.
[10] Daniel Maturana, Sebastian Scherer, "VoxNet: A 3D Convolutional Neural Network for real-time object recognition," 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 922-928, DOI: 10.1109/IROS.2015.7353481, 2015.
[11] Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, Jianxiong Xiao, ?3D ShapeNets: A Deep Representation for Volumetric Shapes,? IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR.2015.7298801, 2015.
[12] Nima Sedaghat, Mohammadreza Zolfaghari, Ehsan Amiri, Thomas Brox, "Orientation-boosted Voxel Nets for 3D Object Recognition," Proceedings of the British Machine Vision Conference (BMVC), DOI :10.5244/c.31.97, 2017.
[13] Jun Mitani, Hiromasa Suzuki, Hiroshi Uno: "Computer Aided Design for Origamic Architecture Models with Voxel Data Structure," IPSJ Journal Vol.44, No. 5, pp.1372-1379, 2003.
[14] Masanobu Nagase, Shuichi Akizuki, Manabu Hashimoto, "Extraction of 3-D Feature Point for effect in Object Recognition based on Local Shape Distinctiveness," Information Processing Society of Japan, IPSJ SIG Technical Report, Vol. 2013, No. 26, 2013.
[15] Hang Su, Subhransu Maji, Evangelos Kalogerakis, Erik Learned-Miller, "Multi-view Convolutional Neural Networks for 3D Shape Recognition," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 945-953, DOI: 10.1109/ICCV.2015.114, 2015.
[16] Haoxuan You, Yifan Feng, Rongrong Ji, Yue Gao, "PVNet: A Joint Convolutional Network of Point Cloud and Multi- View for 3D Shape Recognition," Proceedings of the 26th ACM international conference on Multimedia, pp. 1310- 1318, DOI: 10.1145/3240508.3240702, 2018.
[17] Nakayama Atsushi, Kawakatsu Daisuke, Kobori Ken-ichi, Kutsuwa Toshirou, "A checking method for a point inside a polyhedron in grasping an object of VR," The 48th National Convention of Information Processing Society of Japan (IPSJ), 2, 297–298, 1994.
[18] Satoshi Kodama, "Effectiveness of inside/outside determination in relation to 3D non-convex shapes using CUDA," The Imaging Science Journal, Vol. 66(7), pp. 409-418, DOI: 10.1080/13682199.2018.1497251, 2018.
[19] Satoshi Kodama, Yuka Ozeki, Rei Nakagawa, "Internal and External Analysis Considering the Layers of Threedimensional Shapes Using CUDA," International Journal of Computer Trends and Technology (IJCTT), Vol. 67(6), DOI: 10.14445/22312803/IJCTT-V67I6P101, 2019.
[20] C. Wayne Brown, "Volume / Surfaces," Learn WebGL, http://learnwebgl.brown37.net/model_data/model_volume. html, 2016.
[21] Justin A. Jensen, Robert P. Burton, "Fourveo: Integration of 4D animation into conventional 3D animation workflows," Computer Animation and Virtual Worlds, Vol. 29 (3-4), DOI: 10.1002/cav.1816, 2018.

Keywords
Shape recognition, Shape learning, Pattern recognition, Shape Registration, Solid angle.