Address Block Localization for Chinese Postal Envelopes with Clutter Background

摘要：

　　In this paper we propose a novel supervised model to localize the address block for Chinese postal envelopes.The problem is formulated as a binary classification problem.We get the probability map via joint Conditional Random Field(CRF)training and dictionary learning.Histograms of Oriented Gradients(HOG)are used as descriptors.We evaluate our model on a challenging Chinese postal envelope database with clutter background.Experiment results demonstrate our model performs well and is robust to appearance variations in illumination,rotation,and clutter background.

关键词： Address block localization Histogram of oriented gradient Conditional random field Dictionary learning

作者: Meiling Cheng Jinhua Xu

作者单位: Department of Computer Science and Technology,East China normal university 200241

会议类型: 国际会议

会议名称: The 2014 10th International Conference on Natural Computation (ICNC 2014) and the 2014 11th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2014)(第十届自然计算和第十一届模糊系统与知识发现国际会议)

会议地点: 厦门

会议语种:英文

页码: 647-652

在线出版日期: 2014-08-19（万方平台首次上网日期，不代表论文的发表时间）