Object Recognition With an Elastic Net-Regularized Hierarchical MAX Model of the Visual Cortex
Object Recognition With an Elastic Net-Regularized Hierarchical MAX Model of the Visual Cortex
复制标题
DOI：
10.1109/lsp.2016.2582541
复制
发表时间：
2016-06
影响因子：
3.9
通讯作者：
Ali Alameer;Ghazal Ghazaei;P. Degenaar;J. Chambers;K. Nazarpour
中科院分区：
文献类型：
--
作者：
Ali Alameer;Ghazal Ghazaei;P. Degenaar;J. Chambers;K. Nazarpour
人类视觉皮层已经进化到可以有效地识别场景中的物体。 Hierarchical MAX (HMAX) 是一种受视觉皮层启发的物体识别模型，视觉皮层神经元的特征稀疏编码先前被集成到 HMAX 模型中以提高性能。在本研究中，为了进一步提高识别精度，我们开发了一种用于 HMAX 模型的弹性网络正则化字典学习方法。我们将其称为 En-HMAX 模型。通过 En-HMAX 模型，我们可以利用稀疏分组权衡，从而保留相关但信息丰富的特征用于对象分类。结果表明，En-MAX 模型在识别不可见物体方面优于原始 HMAX 模型约 40%，以及 HMAX 模型的两个特殊情况，即最小绝对收缩和选择算子 (LASSO)-HMAX (约 19%) 和 Ridge-HMAX (约 9%) 模型。
The human visual cortex has evolved to determine efficiently objects from within a scene. Hierarchical MAX (HMAX) is an object recognition model which has been inspired by the visual cortex, and sparse coding, which is a characteristic of neurons in the visual cortex, was previously integrated into the HMAX model for improved performance. In this study, in order to further enhance recognition accuracy, we have developed an elastic net-regularized dictionary learning approach for use in the HMAX model. We term this the En-HMAX model. With the En-HMAX model, we can exploit the sparsity-grouping tradeoff, such that correlated but informative features are preserved for object classification. Results show that the En-MAX model outperforms the original HMAX model in recognizing unseen objects by ~40% as well as the two special cases of the HMAX model, i.e., the least absolute shrinkage and selection operator (LASSO)-HMAX (~19%) and Ridge-HMAX (~9%) models.