TY - GEN
T1 - Image retrieval system capable of learning the user's sensibility using neural networks
AU - Kageyama, Y.
AU - Saito, H.
PY - 1997
Y1 - 1997
N2 - With the advent of the multimedia era, the need to retrieve the image that a user wants from a lot of images is an important issue. In this paper, we propose an interactive image retrieval system which employs backpropagation neural networks using the words that represent the user's sensibility, in order to deal with the user's ambiguous queries. When an user inputs the words, this system sets the synapse of the network which represents both the user and the words and displays candidate images according to the output values of the neural network. The user evaluates the similarity of the image that he/she wants to get until the system displays the optimal images and produces the set of teach signals according to the user's evaluation. After training the network, the system displays new candidate images. The inputs of the neural network are image features which have one-to-one correspondence with images in the databases. We implemented this system on Sun SPARC station, and show that the system could improve the candidate images each time an user evaluate them.
AB - With the advent of the multimedia era, the need to retrieve the image that a user wants from a lot of images is an important issue. In this paper, we propose an interactive image retrieval system which employs backpropagation neural networks using the words that represent the user's sensibility, in order to deal with the user's ambiguous queries. When an user inputs the words, this system sets the synapse of the network which represents both the user and the words and displays candidate images according to the output values of the neural network. The user evaluates the similarity of the image that he/she wants to get until the system displays the optimal images and produces the set of teach signals according to the user's evaluation. After training the network, the system displays new candidate images. The inputs of the neural network are image features which have one-to-one correspondence with images in the databases. We implemented this system on Sun SPARC station, and show that the system could improve the candidate images each time an user evaluate them.
UR - http://www.scopus.com/inward/record.url?scp=0030702536&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0030702536&partnerID=8YFLogxK
U2 - 10.1109/ICNN.1997.614126
DO - 10.1109/ICNN.1997.614126
M3 - Conference contribution
AN - SCOPUS:0030702536
SN - 0780341228
SN - 9780780341227
T3 - IEEE International Conference on Neural Networks - Conference Proceedings
SP - 1563
EP - 1567
BT - 1997 IEEE International Conference on Neural Networks, ICNN 1997
T2 - 1997 IEEE International Conference on Neural Networks, ICNN 1997
Y2 - 9 June 1997 through 12 June 1997
ER -