A Bottom-Up Layout Analysis Algorithm Based On Multi-Level Confidence

The digital information is the most precious resources in the mankind along with the coming of information age, More and more information is recorded on the Paper is inconvenience of research, searches and data mining. The traditional way of input the information on the paper into computer by hand is unpractical. Along with the development of OCR(optical character recognition), some documents had been Processed by computer automatically, It saves great amount of labor and money, and greatly improves the Processing efficiency.Document processing includes two stages: document layout understanding and OCR recognition. The OCR is trend to apply because of decades of research, but document understanding is attached the important attention in 90's. The deficiency of document understanding is restricted the application of document understanding. Based on plenty of papers, technology reports and dissertations, this dissertation makes some research works on the theories of document image understanding. It is focus on document image skew recognition, form layout understanding and Chinese font recognition (OFR). The main works is as follows:Document image processing has become an increasingly important technology in the automation office documentation tasks. Automatic document transaction are an essential component of OCR (Optical Character Recognition) of systems . One of the problems in this field is that the document to be read is not always placed correctly on a flat-bed scanner bed, resulting in a skewed image. This skew has a detrimental effect on document analysis, document understanding, and character segmentation and recognition. Consequently, detecting the skew of a document image and correcting it are important issues in realizing a practical document reader. This paper presents the use of analyzing the connected components extracted from the binary image of a document page. Such an analysis provides a lot of useful information, and will be used to perform skew correction,segmentation and classification of the document. Moreover, we describe a new skew correction algorithm with fast and accurate properties. Experiments show that the method works well on a wide variety of layouts.layout analysis is a key problem in the document digitalization. In this paper, layout analysis algorithms are classified to two categories: shape-based method and texture-based method. Then a layout analysis model based on multi-level primitives is proposed and the problem of layout analysis is simplified to compute the best partition on each level. Based on this model, the concept of multi-level confidence is introduced and bottom-up algorithm based on multi-level confidence is described. Analysis under the Multi-level confidence is very flexible for all kinds of documents. Experimental results have proved that the algorithm proposed by this paper is very effective.