An analysis of viewpoint dependency in three-dimensional object recognition using support vector machines

2005 ◽  
Vol 37 (1) ◽  
pp. 105-115
Author(s):  
Taichi Hayasaka ◽  
Shigeki Nakauchi ◽  
Shiro Usui
Keyword(s):  
Object Recognition ◽  
Support Vector Machines ◽  
Three Dimensional ◽  
Support Vector ◽  
Vector Machines ◽  
Dimensional Object

Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines

2009 ◽  
Vol 119 (1-2) ◽  
pp. 32-38 ◽  
Author(s):  
Paula Martiskainen ◽  
Mikko Järvinen ◽  
Jukka-Pekka Skön ◽  
Jarkko Tiirikainen ◽  
Mikko Kolehmainen ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Support Vector Machines ◽  
Three Dimensional ◽  
Behaviour Pattern ◽  
Support Vector ◽  
Vector Machines

scholarly journals Application of Improved Three-Dimensional Kernel Approach to Prediction of Protein Structural Class

2013 ◽  
Vol 2013 ◽  
pp. 1-8
Author(s):  
Xu Liu ◽  
Yuchao Zhang ◽  
Hua Yang ◽  
Lisheng Wang ◽  
Shuaibing Liu
Keyword(s):  
Support Vector Machines ◽  
Three Dimensional ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Structural Class ◽  
Protein Structural Class ◽  
Complementary Role ◽  
Vector Machines ◽  
Kernel Approach ◽  
Leave One Out

Kernel methods, such as kernel PCA, kernel PLS, and support vector machines, are widely known machine learning techniques in biology, medicine, chemistry, and material science. Based on nonlinear mapping and Coulomb function, two 3D kernel approaches were improved and applied to predictions of the four protein tertiary structural classes of domains (all-α, all-β,α/β, andα + β) and five membrane protein types with satisfactory results. In a benchmark test, the performances of improved 3D kernel approach were compared with those of neural networks, support vector machines, and ensemble algorithm. Demonstration through leave-one-out cross-validation on working datasets constructed by investigators indicated that new kernel approaches outperformed other predictors. It has not escaped our notice that 3D kernel approaches may hold a high potential for improving the quality in predicting the other protein features as well. Or at the very least, it will play a complementary role to many of the existing algorithms in this regard.

scholarly journals Object Recognition System-on-Chip Using the Support Vector Machines

2005 ◽  
Vol 2005 (7) ◽  
Author(s):  
Roberto Reyna-Rojas ◽  
Dominique Houzet ◽  
Daniela Dragomirescu ◽  
Florent Carlier ◽  
Salim Ouadjaout
Keyword(s):  
Object Recognition ◽  
Support Vector Machines ◽  
Recognition System ◽  
System On Chip ◽  
Support Vector ◽  
Vector Machines ◽  
On Chip

scholarly journals The Recognition Of Partially Occluded Objects with Support Vector Machines, Convolutional Neural Networks and Deep Belief Networks

2014 ◽  
Vol 4 (1) ◽  
pp. 5-19 ◽  
Author(s):  
Joseph Lin Chu ◽  
Adam Krzyźak
Keyword(s):  
Neural Networks ◽  
Object Recognition ◽  
Support Vector Machines ◽  
Convolutional Neural Networks ◽  
Recognition Task ◽  
Generative Models ◽  
Deep Belief Network ◽  
Support Vector ◽  
Belief Network ◽  
Vector Machines

Abstract Biologically inspired artificial neural networks have been widely used for machine learning tasks such as object recognition. Deep architectures, such as the Convolutional Neural Network, and the Deep Belief Network have recently been implemented successfully for object recognition tasks. We conduct experiments to test the hypothesis that certain primarily generative models such as the Deep Belief Network should perform better on the occluded object recognition task than purely discriminative models such as Convolutional Neural Networks and Support Vector Machines. When the generative models are run in a partially discriminative manner, the data does not support the hypothesis. It is also found that the implementation of Gaussian visible units in a Deep Belief Network trained on occluded image data allows it to also learn to effectively classify non-occluded images

Sign in / Sign up

Export Citation Format

Share Document