Multithresholding of mixed-type documents

Abstract

Mixed-type documents include text, drawings and graphics regions. It is obvious that a technique that can reduce the number of the gray-levels in accordance with the type of each document region could be important for many document applications, such as storage, transmission and recognition. To solve this problem, this paper proposes a new method, called the document multithresholding technique. The method is based on a page layout analysis (PLA) technique and on a neural-network multilevel threshold-selection approach. The proposed technique is applicable to any mixed-type document and achieves document multithresholding by taking advantage of the types of the document blocks. Thus, in the final document different block types are stored with the appropriate and limited numbers of gray-level values. The proposed method includes two main steps. First, a PLA technique is applied, which classifies the document blocks into text, line-drawing and graphics regions. In the second stage, a new neural-network multithresholding technique is applied to each of the document blocks. In text and line-drawing blocks, only one threshold is determined, whereas in the graphics blocks the optimal number of thresholds is first determined. The performance of the method has been extensively tested on a variety of documents. Several examples illustrate the strength and the effectiveness of the proposed methodology.