Separating Lines of Text in Free-Form Handwritten Historical Documents

Abstract

We present an approach to finding (and separating) lines of text in free-form handwritten historical document images. After preprocessing, our method uses the count of foreground/background transitions in a binarized image to determine areas of the document that are likely to be text lines. Alternatively, an Adaptive Local Connectivity Map (ALCM) found in the literature can be used for this step of the process. We then use a min-cut/max-flow graph cut algorithm to split up text areas that appear to encompass more than one line of text. After removing text lines containing relatively little text information (or merging them with nearby text lines), we create output images for each line. A grayscale output image is created, as well as a special mask image containing both the foreground and information flagging ambiguous pixels. Foreground pixels that belong to other text lines are removed from the output images to provide cleaner line images useful for further processing. While some refinement is still necessary, the result of early experimentation with our method is encouraging.

Text line and word segmentation of handwritten documents

“…The adaptive RLSA is an extension of the classical RLSA [8] in the sense that additional smoothing constraints are set in regard to the geometrical properties of neighboring CCs. Other methodologies include the use of the adaptive local connectivity map [9] by summing the intensities of each pixel's neighbors in the horizontal direction, the use of foreground/background transitions counting combined with a min-cut/max-flow graph cut algorithm [10] as well as of the theory of Kalman filtering to detect text lines on low resolution images [11]. An overview of text line segmentation methods is presented in Table 1.…”

Line Segmentation for Degraded Handwritten Historical Documents

“…Most of the existing text-line segmentation methods are applicable only to binary images [3]. Very few of them are suitable for direct gray scale segmentation (e.g, [6], [7]). For a recent survey on text-line segmentation in historical documents, please refer to [3].…”

Text line detection in handwritten documents

“…In Ref. [11], the method to segment text lines uses the count of foreground/background transitions in a binarized image to determine areas of the document that are likely to be text lines. Also, a min-cut/max-flow graph cut algorithm is used to split up text areas that appear to encompass more than one line of text.…”