Modeling object recognition in visual cortex using multiple firing k-means and non-negative sparse coding

Modeling object recognition in visual cortex using multiple firing k-means and non-negative sparse coding
复制标题

使用多重激发 k 均值和非负稀疏编码对视觉皮层中的对象识别进行建模

DOI:
10.1016/j.sigpro.2015.08.017
复制
发表时间:
2016-07
期刊:
影响因子:
4.4
通讯作者:
Limiao Deng
Limiao Deng
中科院分区:
工程技术2区
文献类型:
--
作者:
Yanjiang Wang;Limiao Deng

文献摘要

参考文献

被引文献

相似文献

Serre等人开发的HMAX模型模拟了灵长类动物视觉皮层的视觉识别过程。然而,它在模拟V2神经元或更高层次的视觉皮层方面有一定的局限性。我们以一些生物学上合理的方式扩展了该模型,并构建了一个五层计算模型,称为Sparse-HMAX模型。首先,我们使用Gabor滤波器像原始HMAX模型一样描述V1神经元的响应特性,并使用HOG描述符描述C1图像补丁。然后,我们将多个触发均值整合到HMAX模型中来模拟V2神经元的响应,并将非负稀疏编码整合到V4神经元模型中。为了验证我们提出的模型的有效性,我们在三个公共数据库:Caltech101、Caltech256和grazi -01上进行了实验。实验结果表明,与原始HMAX模型相比,稀疏HMAX模型在目标识别精度和处理速度上都有很大的提高。我们提出的方法在识别性能上也可与流行的方法相媲美。
The HMAX model developed by Serre et al. imitates the process of visual recognition in primates’ visual cortex. However, it has some limits in modeling the V2 neurons or higher level of visual cortex. We extend the model in some biologically plausible ways and construct a five-layer computational model, denoted as Sparse-HMAX model. First we use Gabor filters to describe the response properties of V1 neurons as in original HMAX model and describe C1 image patches with HOG descriptors. Then we integrate multiple firingk-means into the HMAX model to emulate the V2 neural responses and non-negative sparse coding to model V4 neurons. To investigate the efficacy of our proposed model, we perform experiments on three public databases: Caltech101, Caltech256 and GRAZ-01. Experimental results demonstrate that Sparse-HMAX model displays great improvements over the original HMAX model both in recognition accuracy and processing speed for object recognition. Our proposed method is also comparable to the prevalent approaches in recognition performance.
使用分层 K 均值模型对 V2 神经元的响应特性进行建模
DOI: 10.1016/j.neucom.2013.07.052
发表时间: 2014-06
期刊: Neurocomputing
影响因子: 6
作者:
Hu, Xiaolin;Zhang, Jianwei;Qi, Peng;Zhang, Bo
通讯作者: Zhang, Bo
DOI: 10.1007/s00138-006-0052-0
发表时间: 2007-04
影响因子: 3.3
作者:
B. Shastri;M. Levine
通讯作者: B. Shastri;M. Levine
DOI: 10.1038/14819
发表时间: 1999-11-01
影响因子: 25
作者:
Riesenhuber, M;Poggio, T
通讯作者: Poggio, T
DOI: 10.1523/jneurosci.4364-03.2004
发表时间: 2004-03-31
影响因子: 5.3
作者:
Ito, M;Komatsu, H
通讯作者: Komatsu, H
DOI: --
发表时间: 1945
影响因子: 14.6
作者:
George Hoberg;Marty Luckert;David Haley;Benjamin Cashore;Michael Howlett;J. Rayner
通讯作者: George Hoberg;Marty Luckert;David Haley;Benjamin Cashore;Michael Howlett;J. Rayner