A New Biologically Motivated Framework for Robust Object Recognition
A New Biologically Motivated Framework for Robust Object Recognition
复制标题
DOI：
10.21236/ada454724
复制
发表时间：
2004-11
期刊：
影响因子：
--
通讯作者：
T. Serre;Lior Wolf;T. Poggio
中科院分区：
文献类型：
--
作者：
T. Serre;Lior Wolf;T. Poggio
摘要：在本文中，我们介绍了一组新的功能强大的对象识别，表现出出色的性能，对各种对象类别，同时能够学习只有少数训练样本。该集合的每个元素是通过在相邻位置和多个方向上组合位置和尺度容限边缘检测器而获得的复杂特征。我们的系统由视觉皮层的定量模型驱动，在来自不同群体的各种对象图像数据集上优于最先进的系统。我们还表明，我们的系统能够从很少的例子中学习，没有先验的类别知识。该方法的成功也为一类前馈模型的大脑皮层物体识别提供了一个可行性证明。最后，我们推测存在一个普遍的过完备的字典的功能，可以处理所有对象类别的识别。
Abstract : In this paper,we introduce a novel set of features for robust object recognition, which exhibits outstanding performances on a variety of object categories while being capable of learning from only a few training examples. Each element of this set is a complex feature obtained by combining position- and scale-tolerant edge-detectors over neighboring positions and multiple orientations. Our system motivated by a quantitative model of visual cortex outperforms state-of-the-art systems on a variety of object image datasets from different groups. We also show that our system is able to learn from very few examples with no prior category knowledge. The success of the approach is also a suggestive plausibility proof for a class of feed-forward models of object recognition in cortex. Finally, we conjecture the existence of a universal overcomplete dictionary of features that could handle the recognition of all object categories.