Automatic Chinese Postal Address Block Location Using Proximity Descriptors and Cooperative Profit Random Forests
Automatic Chinese Postal Address Block Location Using Proximity Descriptors and Cooperative Profit Random Forests
复制标题
DOI：
10.1109/tie.2017.2764866
复制
发表时间：
2018-05
影响因子：
7.7
通讯作者：
Xinghui Dong;Junyu Dong;Huiyu Zhou;Jianyuan Sun;D. Tao
中科院分区：
文献类型：
--
作者：
Xinghui Dong;Junyu Dong;Huiyu Zhou;Jianyuan Sun;D. Tao
定位目的地地址块是邮件自动分拣的关键。由于中国大陆使用的中文信封的特点，我们在这里利用邻近线索，以描述信封上的调查区域。我们提出了两个邻近描述符编码的空间分布的连接组件从二进制包络图像。为了定位目的地址块，这些描述符与合作利润随机森林（CPRF）一起使用。实验结果表明，所提出的接近度描述符是上级的两个组件描述符，它只利用单个组件的形状特征，和CPRF分类器产生更高的召回值比7个国家的最先进的分类器。这些有希望的结果是由于这样一个事实，即所提出的描述符编码的二进制包络图像的邻近特性，和CPRF分类器使用一个有效的树节点分裂的方法。
Locating the destination address block is key to automated sorting of mails. Due to the characteristics of Chinese envelopes used in mainland China, we here exploit proximity cues in order to describe the investigated regions on envelopes. We propose two proximity descriptors encoding spatial distributions of the connected components obtained from the binary envelope images. To locate the destination address block, these descriptors are used together with cooperative profit random forests (CPRFs). Experimental results show that the proposed proximity descriptors are superior to two component descriptors, which only exploit the shape characteristics of the individual components, and the CPRF classifier produces higher recall values than seven state-of-the-art classifiers. These promising results are due to the fact that the proposed descriptors encode the proximity characteristics of the binary envelope images, and the CPRF classifier uses an effective tree node split approach.