Poorly Structured Handwritten Documents Segmentation using Continuous Probabilistic Feature Grammars

TL;DR: This paper used the Collins model for parsing non-textual information into hierarchical content, and assigned labels to lines that indicate how the lines relate to one another in a hierarchical content representation.

TL;DR: This chapter presents the approach for recognition of Malayalam documents, both printed and handwritten, and classification results as well as ongoing activities are presented.

TL;DR: Improvements concern the handling of this complexity using genetic algorithms, the definition of performance measurements that are adapted to the segmentation of on-line documents, and the evaluation of this segmentation approach on a collection of documents of various qualities.

TL;DR: A robust segmentation method to detect the regions in an unstructured on-line handwritten document and compute the most likely segmentation of the handwritten page using a Stochastic Context Free Grammar based parser.

TL;DR: The document spectrum (or docstrum), which is a method for structural page layout analysis based on bottom-up, nearest-neighbor clustering of page components, yields an accurate measure of skew, within-line, and between-line spacings and locates text lines and text blocks.

TL;DR: In this paper, an extension of Earley's parser for stochastic context-free grammars is presented, which computes probabilities of successive prefixes being generated by the grammar, probabilities of substrings being produced by the nonterminals, including the entire string, most likely (Viterbi) parse of the string, posterior expected number of applications of each grammar production, as required for reestimating rule probabilities.

TL;DR: In this article, the authors define stochastic attribute-value grammars and give an algorithm for computing the maximum-likelihood estimate of their parameters, which is adapted from Della Pietra and Lafferty (1995).