Automatic learning and extraction of multi-local features
Automatic learning and extraction of multi-local features
复制标题
多局部特征的自动学习和提取
DOI：
10.1109/iccv.2009.5459338
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
Josephine Sullivan
中科院分区：
文献类型：
--
作者：
Oscar M. Danielsson;S. Carlsson;Josephine Sullivan
在本文中，我们介绍了一种新的功能-多本地功能，所以命名为每一个是一个集合的本地功能，如定向边，在一个非常特定的空间安排。多局部特征具有从对象类捕获样本的潜在恒定形状属性的能力。因此，它特别适合于表示和检测视觉类，缺乏独特的局部结构，主要是由他们的全球形状定义。我们提出的算法来自动学习这些功能的集合，以代表一个对象类，从弱标记的训练图像的类，以及程序来有效地检测这些功能在新的图像。多个本地功能的权力证明了通过使用一个简单的投票计划进行对象类别检测的标准数据库中的合奏。尽管其简单性，该方案产生的检测率匹配的最先进的目标检测系统。
In this paper we introduce a new kind of feature - the multi-local feature, so named as each one is a collection of local features, such as oriented edgels, in a very specific spatial arrangement. A multi-local feature has the ability to capture underlying constant shape properties of exemplars from an object class. Thus it is particularly suited to representing and detecting visual classes that lack distinctive local structures and are mainly defined by their global shape. We present algorithms to automatically learn an ensemble of these features to represent an object class from weakly labelled training images of that class, as well as procedures to detect these features efficiently in novel images. The power of multi-local features is demonstrated by using the ensemble in a simple voting scheme to perform object category detection on a standard database. Despite its simplicity, this scheme yields detection rates matching state-of-the-art object detection systems.
DOI：
10.1023/b:visi.0000042934.15159.49
发表时间：
2005-01-01
影响因子：
19.5
作者：
Felzenszwalb, PF;Huttenlocher, DP
通讯作者：
Huttenlocher, DP
以1类整合子为指标的城市河流耐药基因污染评价
DOI：
--
发表时间：
2021
期刊：
影响因子：
--
作者：
L. Lihui;X. Zou;W. Dai;D. Xue;T. Nakamura;A. Wakamiya;K. Marumoto;増田容一，石川将人;長澤杏香，春日郁朗，栗栖太，古米弘明
通讯作者：
長澤杏香，春日郁朗，栗栖太，古米弘明