The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Embora estudos anteriores utilizando redes neurais artificiais tenham sido ativamente aplicados ao reconhecimento de formas de objetos, pouca atenção tem sido dada ao reconhecimento de elementos espaciais (por exemplo, posição, rotação e tamanho). No presente estudo, uma rede neural associativa de rotação e espalhamento de tamanho (rede RS-SAN) é proposta e a eficácia da rede RS-SAN na orientação de objetos (rotação), reconhecimento de tamanho e forma é mostrada. A rede RS-SAN presta atenção ao fato de que o sistema de reconhecimento espacial no cérebro (córtex parietal) está envolvido tanto no reconhecimento espacial (por exemplo, posição, rotação e tamanho) quanto no reconhecimento da forma de um objeto. A rede RS-SAN utiliza espalhamento espacial por camadas de espalhamento, aprendizagem inversa generalizada e métodos de vetores populacionais para o reconhecimento do objeto. A informação da orientação e tamanho do objeto é espalhada por camadas duplas de espalhamento que possuem características de sintonia semelhantes às dos neurônios de discriminação espacial (por exemplo, neurônios de orientação de eixo e neurônios de discriminação de tamanho) no córtex parietal. A rede RS-SAN reconhece simultaneamente o tamanho do objeto independentemente da sua orientação e forma, a orientação independentemente do seu tamanho e forma, e a forma independentemente do seu tamanho e orientação.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Kiyomi NAKAMURA, Shingo MIYAMOTO, "Rotation, Size and Shape Recognition by a Spreading Associative Neural Network" in IEICE TRANSACTIONS on Information,
vol. E84-D, no. 8, pp. 1075-1084, August 2001, doi: .
Abstract: Although previous studies using artificial neural networks have been actively applied to object shape recognition, little attention has been paid to the recognition of spatial elements (e.g. position, rotation and size). In the present study, a rotation and size spreading associative neural network (RS-SAN net) is proposed and the efficacy of the RS-SAN net in object orientation (rotation), size and shape recognition is shown. The RS-SAN net pays attention to the fact that the spatial recognition system in the brain (parietal cortex) is involved in both the spatial (e.g. position, rotation and size) and shape recognition of an object. The RS-SAN net uses spatial spreading by spreading layers, generalized inverse learning and population vector methods for the recognition of the object. The information of the object orientation and size is spread by double spreading layers which have similar tuning characteristics to spatial discrimination neurons (e.g. axis orientation neurons and size discrimination neurons) in the parietal cortex. The RS-SAN net simultaneously recognizes the size of the object irrespective of its orientation and shape, the orientation irrespective of its size and shape, and the shape irrespective of its size and orientation.
URL: https://global.ieice.org/en_transactions/information/10.1587/e84-d_8_1075/_p
Copiar
@ARTICLE{e84-d_8_1075,
author={Kiyomi NAKAMURA, Shingo MIYAMOTO, },
journal={IEICE TRANSACTIONS on Information},
title={Rotation, Size and Shape Recognition by a Spreading Associative Neural Network},
year={2001},
volume={E84-D},
number={8},
pages={1075-1084},
abstract={Although previous studies using artificial neural networks have been actively applied to object shape recognition, little attention has been paid to the recognition of spatial elements (e.g. position, rotation and size). In the present study, a rotation and size spreading associative neural network (RS-SAN net) is proposed and the efficacy of the RS-SAN net in object orientation (rotation), size and shape recognition is shown. The RS-SAN net pays attention to the fact that the spatial recognition system in the brain (parietal cortex) is involved in both the spatial (e.g. position, rotation and size) and shape recognition of an object. The RS-SAN net uses spatial spreading by spreading layers, generalized inverse learning and population vector methods for the recognition of the object. The information of the object orientation and size is spread by double spreading layers which have similar tuning characteristics to spatial discrimination neurons (e.g. axis orientation neurons and size discrimination neurons) in the parietal cortex. The RS-SAN net simultaneously recognizes the size of the object irrespective of its orientation and shape, the orientation irrespective of its size and shape, and the shape irrespective of its size and orientation.},
keywords={},
doi={},
ISSN={},
month={August},}
Copiar
TY - JOUR
TI - Rotation, Size and Shape Recognition by a Spreading Associative Neural Network
T2 - IEICE TRANSACTIONS on Information
SP - 1075
EP - 1084
AU - Kiyomi NAKAMURA
AU - Shingo MIYAMOTO
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E84-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2001
AB - Although previous studies using artificial neural networks have been actively applied to object shape recognition, little attention has been paid to the recognition of spatial elements (e.g. position, rotation and size). In the present study, a rotation and size spreading associative neural network (RS-SAN net) is proposed and the efficacy of the RS-SAN net in object orientation (rotation), size and shape recognition is shown. The RS-SAN net pays attention to the fact that the spatial recognition system in the brain (parietal cortex) is involved in both the spatial (e.g. position, rotation and size) and shape recognition of an object. The RS-SAN net uses spatial spreading by spreading layers, generalized inverse learning and population vector methods for the recognition of the object. The information of the object orientation and size is spread by double spreading layers which have similar tuning characteristics to spatial discrimination neurons (e.g. axis orientation neurons and size discrimination neurons) in the parietal cortex. The RS-SAN net simultaneously recognizes the size of the object irrespective of its orientation and shape, the orientation irrespective of its size and shape, and the shape irrespective of its size and orientation.
ER -