scispace - formally typeset
Search or ask a question
Topic

Document layout analysis

About: Document layout analysis is a research topic. Over the lifetime, 1462 publications have been published within this topic receiving 34021 citations.


Papers
More filters
Patent
05 Dec 2013
TL;DR: In this article, a layout analysis method, comprising of extraction, collection of basic elements with respect to static area objects, analysis sequence determination, and logical paragraph analysis, is presented.
Abstract: Embodiments of the present invention provide a layout analysis method, comprising: extraction, collection of basic elements with respect to static area objects, analysis sequence determination and logical paragraph analysis, wherein the logical paragraph analysis comprises character analyzing, logical connection edge generating, line forming analyzing, paragraph forming analyzing, paragraph result filtering, basic elements collecting with respect to the dynamic area objects and basic element removing. According to the embodiments of the present invention, logical reference information and basic element data information are combined, and the logical reference information is fully used during layout analysis, such that a more accurate layout analysis result with respect to a fixed-layout document is acquired, and the layout analysis result is effectively improved.

4 citations

Proceedings ArticleDOI
25 Aug 2013
TL;DR: Experimental results show that the proposed approach for text line detection in document images outperforms a state-of-the-art text detector in a text/non-text classification task.
Abstract: We introduce a novel approach for text line detection in document images, keeping in mind the requirements of a portable text recognition system designed to support the blind. Challenges include shadows, cluttered backgrounds, and perspective distortion. Different from previous approaches, the proposed method does not segment the image. A text model is created by clustering SIFT features extracted from positive and negative examples. Text regions are located by matching the features extracted from the input image to the clusters in the text model. Regions around the correspondences are then analyzed, and text lines are identified based on features such as gradients and histogram distribution. Experimental results show that our approach outperforms a state-of-the-art text detector in a text/non-text classification task.

4 citations

Patent
08 Aug 1996
TL;DR: In this paper, a method for using a computer to provide justification for a plurality of characters and fonts in a text string within a document from a document system library is described, and the text string is then manipulated as required for a desired justification.
Abstract: A method is disclosed for using a computer to provide justification of a plurality of characters and fonts in a plurality of text strings within a document from a document system library. Document files from a document system library are obtained and relevant information is transferred to a dBase II relational database. Character and font information for each character in a text string is identified so that the location and length of a text string can be determined. The text string is then manipulated as required for a desired justification.

4 citations

Proceedings ArticleDOI
14 Nov 2005
TL;DR: This paper proposes an unsupervised classification method that involves no training or manual selection of algorithm parameters, and first represents each document page as an ordered labeled X-Y tree, then uses a tree matching algorithm to compute style dissimilarity between two document pages.
Abstract: Style classification of document page images is crucial for logical structure analysis of heterogeneous collections of documents. Both layout and contextual features contain significant information about document styles. Most existing methods are supervised methods in which specific document models or classifiers are learned from a training set of document page images with known class labels. In this paper, we propose an unsupervised classification method that involves no training or manual selection of algorithm parameters. In particular, we first represent each document page as an ordered labeled X-Y tree. A tree matching algorithm is then used to compute style dissimilarity between two document pages. We propose a set of tree edit cost functions based on Karl Pearson distance between two multivariate feature observations, which is robust to the over-segmentation problem and zone length variations of same logical entities. Finally, the K-medoids algorithm is used to find an optimal grouping of the trees into K clusters, each of which corresponds to a distinct document style. We evaluate our algorithm on test datasets with different cluster sizes and degrees of style similarity. Experimental results show our algorithm achieved an average classification accuracy of 95.69% over six datasets consisting of 150 pages of 11 different styles.

4 citations


Network Information
Related Topics (5)
Feature extraction
111.8K papers, 2.1M citations
82% related
Feature (computer vision)
128.2K papers, 1.7M citations
82% related
Object detection
46.1K papers, 1.3M citations
81% related
Image segmentation
79.6K papers, 1.8M citations
80% related
Convolutional neural network
74.7K papers, 2M citations
79% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
20235
202219
202134
202019
201914
20189