Edge co-occurrences can account for rapid categorization of natural versus animal images.
Edge co-occurrences can account for rapid categorization of natural versus animal images.
复制标题
DOI：
10.1038/srep11400
复制
发表时间：
2015-06-22
影响因子：
4.6
通讯作者：
Bednar JA
中科院分区：
文献类型：
--
作者：
Perrinet LU;Bednar JA
判断一个视觉场景的语义类别，比如它是否包含动物，通常被认为涉及高水平的大脑联想区。以前的解释需要在不断增加的抽象层次上逐步分析场景，从边缘提取到中级对象识别，然后是对象分类。在这里，我们表明仅统计边缘共现就足以执行粗糙但鲁棒的（平移，缩放和旋转不变）场景分类。我们首先使用尺度空间分析和稀疏编码算法从图像中提取边缘。然后，我们通过计算边缘共现的统计数据来计算不同类别（自然的、人造的或包含动物的）的“关联字段”。这些图像的差异很大，动物图像有更多的弯曲结构。我们表明，这种几何形状本身就足以进行分类，并且人类造成的错误模式与这一过程是一致的。因为这些统计数据可以早在初级视觉皮层测量，所以结果挑战了关于视觉系统中计算流的广泛假设。研究结果还提出了新的图像分类和信号处理算法，利用底层结构和底层语义类别之间的相关性。
Making a judgment about the semantic category of a visual scene, such as whether it contains an animal, is typically assumed to involve high-level associative brain areas. Previous explanations require progressively analyzing the scene hierarchically at increasing levels of abstraction, from edge extraction to mid-level object recognition and then object categorization. Here we show that the statistics of edge co-occurrences alone are sufficient to perform a rough yet robust (translation, scale, and rotation invariant) scene categorization. We first extracted the edges from images using a scale-space analysis coupled with a sparse coding algorithm. We then computed the “association field” for different categories (natural, man-made, or containing an animal) by computing the statistics of edge co-occurrences. These differed strongly, with animal images having more curved configurations. We show that this geometry alone is sufficient for categorization, and that the pattern of errors made by humans is consistent with this procedure. Because these statistics could be measured as early as the primary visual cortex, the results challenge widely held assumptions about the flow of computations in the visual system. The results also suggest new algorithms for image classification and signal processing that exploit correlations between low-level structure and the underlying semantic category.
登录
查看更多内容
DOI：
10.1073/pnas.1105855108
发表时间：
2011-06-14
影响因子：
11.1
作者：
McManus, Justin N. J.;Li, Wu;Gilbert, Charles D.
通讯作者：
Gilbert, Charles D.
影响因子：
--
作者：
Hess, RF;Hayes, A;Field, DJ
通讯作者：
Field, DJ
DOI：
10.1073/pnas.0700622104
发表时间：
2007-04-10
影响因子：
11.1
作者：
Serre, Thomas;Oliva, Aude;Poggio, Tomaso
通讯作者：
Poggio, Tomaso
影响因子：
1.8
作者：
FIELD, DJ;HAYES, A;HESS, RF
通讯作者：
HESS, RF
影响因子：
3.8
作者：
Crouzet SM;Serre T
通讯作者：
Serre T