TY - GEN
T1 - Object recognition using multi-layer Hopfield neural network
AU - Young, Susan S.
AU - Scott, Peter D.
AU - Nasrabadi, Nasser M.
PY - 1994
Y1 - 1994
N2 - An object recognition approach based on concurrent coarse-and-fine matching using a multi-layer Hopfield neural network is presented. The proposed network consists of several cascaded single layer Hopfield networks, each encoding object features at a distinct resolution, with bidirectional interconnections linking adjacent layers. The interconnection weights between nodes associating adjacent layers are structured to favor node pairs for which model translation and rotation, when viewed at the two corresponding resolutions, are consistent. This inter-layer feedback feature of the algorithm reinforces the usual intra-layer matching process in conventional single layer Hopfield nets in order to compute the model-object match which is most consistent across several resolution levels. The performance of the algorithm is demonstrated in cases of images containing single and multiple occluded objects. These results are compared with recognition results obtained using a single layer Hopfield network.
AB - An object recognition approach based on concurrent coarse-and-fine matching using a multi-layer Hopfield neural network is presented. The proposed network consists of several cascaded single layer Hopfield networks, each encoding object features at a distinct resolution, with bidirectional interconnections linking adjacent layers. The interconnection weights between nodes associating adjacent layers are structured to favor node pairs for which model translation and rotation, when viewed at the two corresponding resolutions, are consistent. This inter-layer feedback feature of the algorithm reinforces the usual intra-layer matching process in conventional single layer Hopfield nets in order to compute the model-object match which is most consistent across several resolution levels. The performance of the algorithm is demonstrated in cases of images containing single and multiple occluded objects. These results are compared with recognition results obtained using a single layer Hopfield network.
UR - https://www.scopus.com/pages/publications/0027932011
U2 - 10.1109/cvpr.1994.323860
DO - 10.1109/cvpr.1994.323860
M3 - Conference contribution
AN - SCOPUS:0027932011
SN - 0818658274
SN - 9780818658273
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 417
EP - 422
BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PB - Publ by IEEE
T2 - Proceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Y2 - 21 June 1994 through 23 June 1994
ER -