Health Imaging Res. Lab., Eastman Kodak Co., Rochester, NY.
IEEE Trans Image Process. 1997;6(3):357-72. doi: 10.1109/83.557336.
An object recognition approach based on concurrent coarse-and-fine matching using a multilayer 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 interlayer feedback feature of the algorithm reinforces the usual intralayer matching process in the conventional single-layer Hopfield network in order to compute the most consistent model-object match across several resolution levels. The performance of the algorithm is demonstrated for test images containing single objects, and multiple occluded objects. These results are compared with recognition results obtained using a single-layer Hopfield network.
提出了一种基于多层霍普菲尔德神经网络的并行粗-精匹配的目标识别方法。所提出的网络由几个级联的单层霍普菲尔德网络组成，每个网络在不同的分辨率下对目标特征进行编码，并且相邻层之间存在双向连接。连接相邻层的节点的互连权重被构造为有利于当在两个对应分辨率下观察时模型平移和旋转一致的节点对。该算法的这种层间反馈特征增强了传统单层霍普菲尔德网络中的常规层内匹配过程，以便在多个分辨率级别上计算最一致的模型-目标匹配。该算法的性能通过包含单个物体和多个遮挡物体的测试图像进行了演示。这些结果与使用单层霍普菲尔德网络获得的识别结果进行了比较。
