Natural image statistics and efficient coding
Natural image statistics and efficient coding
复制标题
DOI：
10.1088/0954-898x/7/2/014
复制
发表时间：
1996-05-01
影响因子：
7.8
通讯作者：
Field, DJ
中科院分区：
文献类型：
--
作者：
Olshausen, BA;Field, DJ
自然图像包含特征统计量，使它们与纯粹随机的图像区分开来。了解这些特征可以使自然图像更有效地编码。在本文中，我们描述了自然图像中包含的一些结构形式，并展示了这些结构与视觉系统早期阶段神经元的响应特性之间的关系。许多重要的结构形式需要高阶（即线性，成对）统计来表征，这使得基于线性赫布学习或主成分分析的模型不适合为自然图像找到有效的代码。我们认为，一个很好的目标，一个有效的编码的自然场景是最大限度地提高稀疏的表示，我们表明，一个网络，学习稀疏代码的自然场景成功地开发本地化，定向，带通感受野类似于那些在哺乳动物纹状体皮层。
Natural images contain characteristic statistical regularities that set them apart from purely random images. Understanding what these regularities are can enable natural images to be coded more efficiently. In this paper, we describe some of the forms of structure that are contained in natural images, and we show how these are related to the response properties of neurons at early stages of the visual system. Many of the important forms of structure require higher-order (i.e. more than linear, pairwise) statistics to characterize, which makes models based on linear Hebbian learning, or principal components analysis, inappropriate for finding efficient codes for natural images. We suggest that a good objective for an efficient coding of natural scenes is to maximize the sparseness of the representation, and we show that a network that learns sparse codes of natural scenes succeeds in developing localized, oriented, bandpass receptive fields similar to those in the mammalian striate cortex.