TY  - JOUR
T1  - Convolutional Neural Network Training for Robotic Applications in
3D Environments
AU - Jimenez, M.Robinson AU - Aviles, S.Oscar AU - Ovalle, Diana M. 
JO  - Research Journal of Applied Sciences
VL  - 13
IS  - 1
SP  - 41
EP  - 46
PY  - 2018
DA  - 2001/08/19
SN  - 1815-932x
DO  - rjasci.2018.41.46
UR  - https://makhillpublications.co/view-article.php?doi=rjasci.2018.41.46
KW  - Convolutional neural network
KW  -robotic applications
KW  -3D environment
KW  -characteristics
KW  -dynamic
KW  -information
AB  - This study presents two training schemes of three deep convolutional neural network architectures
applied to object recognition, based on the depth information supplied for a 3D camera. For this case, the depth
information allows to make the set of training images of each network, its architecture and its characteristics,
generating a dynamic recognition application by variation of the image capture point. The best scheme is
selected to add a weighting layer with saturationn for obtain a final architecture that recognize objects to
different distances with a 91.69% success that mean a maximum error of 8.31%.
ER  -