arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.02485q-bio.NC
收藏

自然图像中稀疏性的生物启发表征

Biologically-inspired characterization of sparseness in natural images

Laurent U Perrinet

摘要:

自然图像遵循我们的物理(视觉)环境结构所继承的统计数据。特别是,这种结构的一个突出方面是图像可以由相对稀疏的特征描述。我们设计了一个稀疏编码算法的生物启发的架构的初级视觉皮层。我们在这里表明,这种表示的系数表现出重尾分布。对于每个图像,该分布的参数表征稀疏性并且从图像到图像变化。为了研究这种稀疏性的作用,我们设计了一类新的随机纹理刺激,其稀疏性值受我们对自然图像的测量的启发。然后,我们提供了一种方法来合成随机纹理图像与一个给定的统计稀疏匹配的一些给定类的自然图像,并提供其在神经生理学中使用的观点。

英文摘要:

Natural images follow statistics inherited by the structure of our physical (visual) environment. In particular, a prominent facet of this structure is that images can be described by a relatively sparse number of features. We designed a sparse coding algorithm biologically-inspired by the architecture of the primary visual cortex. We show here that coefficients of this representation exhibit a heavy-tailed distribution. For each image, the parameters of this distribution characterize sparseness and vary from image to image. To investigate the role of this sparseness, we designed a new class of random textured stimuli with a controlled sparseness value inspired by our measurements on natural images. Then, we provide with a method to synthesize random textures images with a given statistics for sparseness that matches that of some given class of natural images and provide perspectives for their use in neurophysiology.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑