Two Geometric Algorithms for Layout Analysis
Thomas M. Breuel
- pp 188-199
Reads0
Chats0
TLDR
Geometric algorithms for solving two key problems in layout analysis: finding a cover of the background whitespace of a document in terms of maximal empty rectangles and finding constrained maximum likelihood matches of geometric text line models in the presence of geometric obstacles are presented.Abstract:
This paper presents geometric algorithms for solving two key problems in layout analysis: finding a cover of the background whitespace of a document in terms of maximal empty rectangles, and finding constrained maximum likelihood matches of geometric text line models in the presence of geometric obstacles. The algorithms are considerably easier to implement than prior methods, they return globally optimal solutions, and they require no heuristics. The paper also introduces an evaluation function that reliably identifies maximal empty rectangles corresponding to column boundaries. Combining this evaluation function with the two geometric algorithms results in an easy-to-implement layout analysis system. Reliability of the system is demonstrated on documents from the UW3 database.read more
Citations
More filters
Journal ArticleDOI
Performance Evaluation and Benchmarking of Six-Page Segmentation Algorithms
TL;DR: A vectorial score that is sensitive to, and identifies, the most important classes of segmentation errors (over, under, and mis-segmentation) and what page components (lines, blocks, etc.) are affected.
Posted Content
PubLayNet: largest dataset ever for document layout analysis.
TL;DR: The authors developed the PubLayNet dataset for document layout analysis by automatically matching the XML representations and the content of over 1 million PDF articles that are publicly available on PubMed Central, where typical document layout elements are annotated.
Proceedings ArticleDOI
PubLayNet: Largest Dataset Ever for Document Layout Analysis
TL;DR: The PubLayNet dataset for document layout analysis is developed by automatically matching the XML representations and the content of over 1 million PDF articles that are publicly available on PubMed Central and demonstrated that deep neural networks trained on Pub LayNet accurately recognize the layout of scientific articles.
Proceedings ArticleDOI
ICDAR 2003 page segmentation competition
TL;DR: The results indicate that although methods continue to mature, there is still a considerable need to develop robust methods that deal with everyday documents.
Journal ArticleDOI
The optical character recognition of Urdu-like cursive scripts
Saeeda Naz,Khizar Hayat,Muhammad Imran Razzak,Muhammad Waqas Anwar,Sajjad A. Madani,Samee U. Khan +5 more
TL;DR: The Urdu, Pushto, and Sindhi languages are discussed, with the emphasis being on the Nasta'liq and Naskh scripts, with an emphasis on the preprocessing, segmentation, feature extraction, classification, and recognition in OCR.
References
More filters
Journal ArticleDOI
Segmentation of Page Images Using the Area Voronoi Diagram
TL;DR: It is confirmed that the proposed method of page segmentation based on the approximated area Voronoi diagram is effective for extraction of body text regions, and it is as efficient as other methods based on connected component analysis.
Journal ArticleDOI
Statistical Approaches to Feature-Based Object Recognition
TL;DR: Evidence is presented indicating that, in some domains, normal (Gaussian) distributions are more accurate than uniform distributions for modeling feature fluctuations, which motivates the development of new maximum-likelihood and MAP recognition formulations which are based on normal feature models.
Proceedings ArticleDOI
Image segmentation by shape-directed covers
TL;DR: A technique for image segmentation using shape-directed covers is described and applied to the fully automatic analysis of complex printed-page layouts, which for some tasks is superior to strategies currently emphasized in the literature, including bottom-up and top-down.
Proceedings ArticleDOI
Fast recognition using adaptive subdivisions of transformation space
TL;DR: Its performance is better than that of alignment and Hough transform methods, and, as opposed to these methods; RAST finds solutions satisfying simple, well-defined bounded error criteria.
Journal ArticleDOI
Background structure in document images
TL;DR: In this article, a method for analyzing the structure of the white background in document images is described, along with applications to the problem of isolating blocks of machine-printed text, based on computational-geometry algorithms for off-line enumeration of maximal white rectangles and on-line rectangle unification.