Pohit Mausumi
Amity School of Engineering and Technology, Amity University, UP, Sector 125, Noida 201301, India.
Appl Opt. 2010 Aug 1;49(22):4144-51. doi: 10.1364/AO.49.004144.
A multichannel, multilayer feed forward neural network model is proposed for rotation invariant recognition of objects. In the M channel network, each channel consists of a one dimensional slice of the two dimensional (2D) Fourier transform (FT) of the input pattern that connects fully to the weight matrix. Each slice is taken at different angles from the 2D FT of the object. From each channel, only one neuron can fire in the presence of the training object. The output layer sums up the response of the hidden layer neuron and confirms the presence of the object. Rotation invariant recognition from 0 degrees to 360 degrees is obtained even in the case of degraded images.
提出了一种用于物体旋转不变识别的多通道、多层前馈神经网络模型。在M通道网络中，每个通道由输入模式的二维（2D）傅里叶变换（FT）的一维切片组成，该切片与权重矩阵完全连接。每个切片从物体的2D FT中以不同角度获取。在训练物体存在时，每个通道只有一个神经元能够激发。输出层对隐藏层神经元的响应进行求和，并确认物体的存在。即使在图像退化的情况下，也能实现从0度到360度的旋转不变识别。
