Suzuki Kenji
Kurt Rossmann Laboratories for Radiologic Image Research, Department of Radiology, The University of Chicago, 5841 South Maryland Avenue, Chicago, IL 60637, USA.
J Neural Eng. 2004 Dec;1(4):228-37. doi: 10.1088/1741-2560/1/4/006. Epub 2004 Dec 2.
In this paper, a method for determining the receptive field and the structure of hidden layers of a neural filter (NF) was developed and evaluated. With the proposed method, redundant units are removed from input and hidden layers in an NF based on the influence of removal of units on the error between output and teaching images. By performing the removal of units and retraining for recovery of the loss of the removal repeatedly, the receptive field and a reduced structure of hidden layers are determined. Experiments with NFs were performed for acquiring the function of a known filter, for the reduction of noise in natural images and for the reduction of noise in medical image sequences. By use of the proposed method, redundant units were able to be removed from NFs, while the performance of the NFs was maintained. Experimental results suggested that, with the proposed method, a reasonable receptive field for a given image-processing task could be determined, i.e., the receptive field of the NF trained to obtain the function of a filter corresponded to the kernel of the filter, and the receptive fields of the NFs for noise reduction gathered around the object pixels in the input regions of the NFs.
本文开发并评估了一种确定神经滤波器（NF）感受野和隐藏层结构的方法。利用所提出的方法，基于单元去除对输出图像与教学图像之间误差的影响，从NF的输入层和隐藏层中去除冗余单元。通过反复进行单元去除和重新训练以恢复去除造成的损失，确定感受野和隐藏层的简化结构。对NF进行了实验，以获取已知滤波器的功能、降低自然图像中的噪声以及降低医学图像序列中的噪声。通过使用所提出的方法，能够从NF中去除冗余单元，同时保持NF的性能。实验结果表明，利用所提出的方法，可以为给定的图像处理任务确定合理的感受野，即，为获得滤波器功能而训练的NF的感受野对应于滤波器的内核，并且用于降噪的NF的感受野聚集在NF输入区域中的目标像素周围。
