Scale, translation, and rotation invariant orthonormalized optical/optoelectronic neural networks.
Scale, translation, and rotation invariant orthonormalized optical/optoelectronic neural networks.
复制标题
尺度、平移和旋转不变的正交归一化光学/光电神经网络。
DOI：
10.1364/ao.32.007225
复制
发表时间：
1993
期刊：
影响因子：
1.9
通讯作者：
L. R. Patterson
中科院分区：
文献类型：
--
作者：
E. Ghahramani;L. R. Patterson
我们使用方和Hausler [Appl.Opt.29，704-708（1990）]的一维尺度、平移和面内旋转不变变换的高维版本，并结合光学或光电谐振器神经网络中的正交归一化技术。该系统通过计算机模拟测试，使用一些现实的存储和输入图像。类型I（类歧视）和类型II（类歧视）的几种失真类型的虚警率，以及失真图像的个别例子的结果。我们的研究结果表明，二维变换表现出相当低的I型虚警率比一维的。他们还表明，这样的配置是能够识别一组不同的输入与杂乱和嘈杂的背景。
We use a higher-dimensional version of the one-dimensional scale, translation, and in-plane rotation invariant transforms of Fang and Hausler [Appl. Opt. 29, 704-708 (1990)] in conjunction with an orthonormalization technique in an optical or optoelectronic resonator neural network. The system is tested by computer simulations that use a number of realistic stored and input images. Type-I (in-class discrimination) and type-II (out-of-class discrimination) false-alarm rates for several distortion types as well as results for individual examples of distorted images are presented. Our results indicate that the two-dimensional transforms exhibit considerably lower type-I false-alarm rates than the one-dimensional ones. They also show that such a configuration is capable of identifying a set of diverse inputs with cluttered and noisy backgrounds.