摘要: 提出一种综合利用文档图像的段落特征和局部像素分布相对差特征进行文档图像检索的方法。给出段落特征和局部像素分布相对差特征的定义、提取方法以及基于这2个特征结合使用的检索方法。段落特征这一全局特征以及局部像素分布相对差特征这一局部特征相结合能够较好地表征和区分文档图像,检索方法将两者充分结合取得较好的效果。
关键词:
文档图像检索,
全局特征,
段落特征,
局部特征,
局部像素分布相对差
Abstract: This paper proposes document image retrieval method based on the paragraph feature combining up with the local relative difference of pixel distributions. The definitions and extraction methods of paragraph feature and local relative difference of pixel distributions are given, and the retrieval method based on the two features are proposed. As a global feature, the paragraph feature combined with the local relative difference of pixel distributions, which is a local feature, could describe the document image sufficiently and give a good distinguish, and based on them, an efficient retrieval method is derived.
Key words:
document image retrieval,
global feature,
paragraph feature,
local feature,
local relative difference of pixel distributions
中图分类号:
张 田;王希常;尘昌华. 基于特征的文档图像检索[J]. 计算机工程, 2009, 35(22): 176-178.
ZHANG Tian; WANG Xi-chang; CHEN Chang-hua. Feature-based Document Image Retrieval[J]. Computer Engineering, 2009, 35(22): 176-178.