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
Journal ArticleDOI
TL;DR: This paper proposes an approach that first predicts the global image structure, and then uses the global structure for fine-grained pixel-level 3D layout extraction, and shows that employing the 3D structure prior information yields accurate 3D scene layout segmentation.
Abstract: Extracting the pixel-level 3D layout from a single image is important for different applications, such as object localization, image, and video categorization. Traditionally, the 3D layout is derived by solving a pixel-level classification problem. However, the image-level 3D structure can be very beneficial for extracting pixel-level 3D layout since it implies the way how pixels in the image are organized. In this paper, we propose an approach that first predicts the global image structure, and then we use the global structure for fine-grained pixel-level 3D layout extraction. In particular, image features are extracted based on multiple layout templates. We then learn a discriminative model for classifying the global layout at the image-level. Using latent variables, we implicitly model the sublevel semantics of the image, which enrich the expressiveness of our model. After the image-level structure is obtained, it is used as the prior knowledge to infer pixel-wise 3D layout. Experiments show that the results of our model outperform the state-of-the-art methods by 11.7% for 3D structure classification. Moreover, we show that employing the 3D structure prior information yields accurate 3D scene layout segmentation.

20 citations

Patent
Alex S. Taylor1, Ercan E. Kuruoglu1
19 Oct 2001
TL;DR: In this paper, a target document in a document processing system is annotated on the basis of annotations made previously to a source document, and the target document is searched to locate any of the keywords of interest to the user.
Abstract: A target document in a document processing system is annotated on the basis of annotations made previously to a source document. A source document (either a scanned image of a paper document or an electronic document) is annotated by a user to identify words or phrases of interest. The annotated words are extracted for use as keywords or phrases to search in future document. When a target document is processed, the target document is searched to locate any of the keywords of interest to the user. If any of the keywords are located, electronic annotations are applied to these in the target document for display or printing out and/or registered as keywords to the project. The automatically annotated words or phrases enable the user to locate regions of interest more quickly.

20 citations

Proceedings ArticleDOI
13 Dec 2007
TL;DR: Tamil Document Summarization using sub graph presents a method for extracting sentences from an individual document to serve as a document summary or a pre-cursor to creating a generic document abstract.
Abstract: Document summarization refers to the task of producing shorter version of the original document by selecting important sentences from the text. Tamil Document Summarization using sub graph presents a method for extracting sentences from an individual document to serve as a document summary or a pre-cursor to creating a generic document abstract. Language-Neutral Syntax (LNS), a system of representation for natural language sentences has been used for considering the semantics of the documents. Syntactic analysis of the text that produces a logical form analysis has been applied for each sentence. Subject-Object-Predicate (SOP) triples are extracted from individual sentences to create a semantic graph [2] of the original document and the corresponding human extracted summary. Semantic Normalization is applied to SOP triples to reduce the number of nodes in the semantic graph of the original document. Using the Support Vector Machine (SVM) learning algorithm, a classifier has been trained to identify SOP triples from the document semantic graph that belong to the summary. The classifier is then used for automatic extraction of summaries from the test documents.

20 citations

Proceedings ArticleDOI
18 Dec 2006
TL;DR: An algorithm that can automatically detect and extract text in digital document images and two criteria based on the geometrical property and high frequency content are adopted to kick-out non-text regions.
Abstract: The automatic text detection in document images is useful for many applications. This paper presents an algorithm that can automatically detect and extract text in digital document images. Firstly, we process and fuse Gabor filtered images at different orientations and scales and obtain an image that reflects the layout of the document image. Then, potential text regions are directly extracted from the resulting image. Finally, two criteria based on the geometrical property and high frequency content are adopted to kick-out those non-text regions. The experiments are performed on some representative images with different styles and with texts in different languages and fonts. Experimental results show that the algorithm works well on document images from a wide variety of source.

20 citations

Journal ArticleDOI
Hyung Il Koo1
TL;DR: A text-line detection algorithm for camera-captured document images, developed by incorporating state estimation (an extension of scale selection) into a connected component (CC)-based framework and works robustly for a range of scales.
Abstract: Camera-based text processing has attracted considerable attention and numerous methods have been proposed. However, most of these methods have focused on the scene text detection problem and relatively little work has been performed on camera-captured document images. In this paper, we present a text-line detection algorithm for camera-captured document images, which is an essential step toward document understanding. In particular, our method is developed by incorporating state estimation (an extension of scale selection) into a connected component (CC)-based framework. To be precise, we extract CCs with the maximally stable extremal region algorithm and estimate the scales and orientations of CCs from their projection profiles. Since this state estimation facilitates a merging process (bottom–up clustering) and provides a stopping criterion, our method is able to handle arbitrarily oriented text-lines and works robustly for a range of scales. Finally, a text-line/non-text-line classifier is trained and non-text candidates (e.g., background clutters) are filtered out with the classifier. Experimental results show that the proposed method outperforms conventional methods on a standard dataset and works well for a new challenging dataset.

20 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