基于生物视觉通路的目标识别算法

Object recognition algorithm based on biological visual pathway

研究哺乳动物视觉通路的结构和功能,为机器学习提供了广泛的思路。文章对经典稀疏编码和HMAX模型进行改进,建立一种模拟完整视觉通路的算法。用4DGabor金字塔模拟了视觉信息从视网膜到腹侧通路V1区的处理过程;设计一种带稀疏编码性质的非线性滤波器,模拟了信息在V1区到PFC区的多层次处理步骤。实验表明该算法能够符合已知生物模型,达到现有同类先进算法的效果。

. The research on the anatomical and functional connectivity of visual pathway affords a broad way of machine learning. An algorithm to simulate the whole visual pathway is presented based on the improved clas- sic SC and HMAX models. This process can be broken down into two steps： the first is a coding step, which utilizes 4D Gabor pyramid to simulate visual information processing from the retina to the ventral pathway V1 area, and the second is a pooling step, which utilizes a sparse nonlinear filter to simulate multi-level visual in- formation processing from V1 area to PFC area. The experimental results show that this approach tallies with the living model and achieves the result of the state-of-the-art model.