Word Grouping in Document Images Based on Voronoi Tessellation
نویسندگان
چکیده
Voronoi tessellation of image elements provides an intuitive and appealing definition of proximity, which has been suggested as an effective tool for the description of relations among the neighboring objects in a digital image. In this paper, a Voronoi tessellation based method is presented for word grouping in document images. The Voronoi neighborhoods are generated from the Voronoi tessellation, with the information about the relations and distances of neighboring connected components, based on which word grouping is carried out. The proposed method has been evaluated on a variety of document images. The experimental results show that it has achieved promising results with a high accuracy, and is robust to various font types, styles, sizes, skew angles, as well as different text orientations.
منابع مشابه
Using the Voronoi Tessellation for Grouping Words and Multi-part Symbols in Documents
We examine the importance of the de nition of neighbors and neigh borhoods for grouping in document understanding and list some previous de nitions We present a number of bene ts to using the Voronoi neigh borhood de nition however we argue that de nitions based upon the point Voronoi diagrams are insu cient in the general case e g for group ing image elements in line drawings We give the de ni...
متن کاملDistinct element modelling of the mechanical behaviour of intact rocks using voronoi tessellation model
This paper aims to study the mechanical behaviour and failure mechanism of intact rocks under different loading conditions using the grain based model implemented in the universal distinct element code (UDEC). The grain based numerical model is a powerful tool to investigate complicated micro-structural mechanical behaviour of rocks. In the UDEC grain based model, the intact material is simulat...
متن کاملTexture segmentation using Voronoi polygons
Texture segmentation is one of the early steps towards identifying surfaces and objects in an image. Textures considered here are de ned in terms of primitives called tokens. In this paper we have developed a texture segmentation algorithm based on the Voronoi tessellation. The algorithm rst builds the Voronoi tessellation of the tokens that make up the textured image. It then computes a featur...
متن کاملGrouping Line Drawing Elements Based upon Their Area Voronoi Tessellation
We present an algorithm for grouping multipart symbols, dashed lines, and character strings for extraction from line drawings. Initially, the image undergoes a lossless raster-to-vector conversion creating as its vector representation an undirected graph, a so-called run graph. Next, during localization, the connected components of the run graph are extracted and classiied prob-abilistically fr...
متن کاملUnconstrained Tight Structure Extraction Using Voronoi Tesselation on Document Images
Document structure is the intermediary result obtained through page segmentation, which is used in the analysis of the document image. The structure serves the purpose of extracting the shape of the document from paragraph up to character level in a hierarchical exploratory methodology for understanding the layout structure of the document image. The extracted layout forms a dominant feature wh...
متن کامل