COMPLETE DISCRETE 2-D GABOR TRANSFORMS BY NEURAL NETWORKS FOR IMAGE-ANALYSIS AND COMPRESSION
COMPLETE DISCRETE 2-D GABOR TRANSFORMS BY NEURAL NETWORKS FOR IMAGE-ANALYSIS AND COMPRESSION
复制标题
DOI：
10.1109/29.1644
复制
发表时间：
1988-07-01
期刊：
影响因子：
--
通讯作者：
DAUGMAN, JG
中科院分区：
文献类型：
--
作者：
DAUGMAN, JG
一个三层的神经网络被描述为用于将二维离散信号转换为广义非正交的2-D Gabor表示，用于图像分析、分割和压缩。这些变换是联合的空间/光谱表示，它提供了一个完整的图像描述方面的局部窗口的2-D光谱坐标嵌入在全球2-D空间坐标。在本神经网络方法中，基于涉及具有固定权重的两个层和具有可调整权重的一个层的层间相互作用，网络在没有限制条件的情况下找到用于完整的联合2-D Gabor变换的系数。在基于生物学启发的对数极坐标系综的膨胀，旋转和平移的一个单一的底层2-D Gabor小波模板的小波扩展，图像压缩说明与比率高达20：1。同时，本文还介绍了基于完全二维Gabor变换系数聚类的图像分割方法。<>
A three-layered neural network is described for transforming two-dimensional discrete signals into generalized nonorthogonal 2-D Gabor representations for image analysis, segmentation, and compression. These transforms are conjoint spatial/spectral representations, which provide a complete image description in terms of locally windowed 2-D spectral coordinates embedded within global 2-D spatial coordinates. In the present neural network approach, based on interlaminar interactions involving two layers with fixed weights and one layer with adjustable weights, the network finds coefficients for complete conjoint 2-D Gabor transforms without restrictive conditions. In wavelet expansions based on a biologically inspired log-polar ensemble of dilations, rotations, and translations of a single underlying 2-D Gabor wavelet template, image compression is illustrated with ratios up to 20:1. Also demonstrated is image segmentation based on the clustering of coefficients in the complete 2-D Gabor transform.<>