Learning Algorithms for Document Layout Analysis

摘要: Abstract In this chapter we describe several approaches that have been proposed to use learning algorithm analyze the layout of digitized documents. Layout analysis encompasses all techniques are used infer organization page document images. From a physical point view can be described as composed by blocks, in most cases rectangular, arranged and contain homogeneous content, such text, vectorial graphics, or illustrations. logical text blocks different meaning on basis their content position page. For instance, case technical papers correspond title, author, abstract paper. The algorithms adopted domain often related supervised classifiers at various processing levels label objects image according categories. classification performed for individual pixels, regions, even whole pages. using analyzed chapter.