Use of top-down signals for restoring partly occluded patterns
Use of top-down signals for restoring partly occluded patterns
复制标题
使用自上而下的信号来恢复部分被遮挡的图案
DOI：
10.1109/ijcnn.2002.1005435
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
K. Fukushima
中科院分区：
文献类型：
--
作者：
K. Fukushima
提出了一种能够修复部分遮挡模式缺失部分的神经网络模型。它是一个多层递阶神经网络，其中视觉信息通过自下而上和自上而下的信号相互作用来处理。如果模型不熟悉部分遮挡的图案，模型会尝试通过外推图案的未遮挡部分的轮廓来重建原始形状。如果模型已经学习了图案，则模型会识别它，并尝试使用学习到的有关图案形状的信息来完成形状。该模型不使用简单的模板匹配方法。它甚至可以接受学习模式的变形版本。
Proposes a neural network model that has the ability to repair the missing portions of partly occluded patterns. It is a multi-layered hierarchical neural network, in which visual information is processed by interaction of bottom-up and top-down signals. If a partly occluded pattern is unfamiliar to the model, the model tries to reconstruct the original shape by extrapolating the contours of the unoccluded part of the pattern. If the pattern has already been learned by the model, the model recognizes it and tries to complete the shape using the learned information on the shape of the pattern. The model does not use a simple template matching method. It can accept even deformed versions of learned patterns.