Corpus ID: 16394485

Text-Image Separation in Document Images Using Boundary / Perimeter Detection

@inproceedings{Rege2012TextImageSI,
  title={Text-Image Separation in Document Images Using Boundary / Perimeter Detection},
  author={Priti P. Rege and Chanchal A. Chandrakar},
  year={2012}
}
Document analysis plays an important role in office automation, especially in intelligent signal processing. The proposed system consists of two modules: block segmentation and block identification. In this approach, first a document is segmented into several non-overlapping blocks by utilizing a novel recursive segmentation technique, and then extracts the features embedded in each segmented block are extracted. Two kinds of features, connected components and image boundary/perimeter features… Expand

Figures from this paper

Text Separation From Document Images
TLDR
This chapter compares various traditional as well as deep-learning techniques and uses a semantic segmentation method for separating text from Devanagari document images using U-Net and ResU-Net models. Expand
A Method for Segmentation of Vietnamese Identification Card Text Fields
TLDR
A method for pre-processing, text area extraction and segmentation of Vietnamese Identification Card, in order to improve the accuracy of Region of Interest detection and experiment results demonstrate the efficiency of the proposed method. Expand
A modified SWT based text-image separation in natural scene images
TLDR
Experimental results indicate that the features of SWT make it reliable and robust to detect text independent of scale, direction, background and font. Expand
Morphology Based Approach for Number Plate Extraction
TLDR
M morphological operation-based approach is presented for number plate area extraction and character identification, using histogram-based character segmentation method for effective segmentation of characters. Expand
An Improved Method for Edge Detection and Image Segmentation Using Fuzzy Cellular Automata
TLDR
This study proposes an improved method for edge detection and image segmentation using fuzzy cellular automata and demonstrates that the proposed method produces better output images in comparison with the separate segmentation and edge detection methods studied in the literature. Expand
Moving text line detection and extraction in TV video frames
TLDR
This work plans to detect and extract the moving text from the news video using hybrid technology in association of edge and connected component detection. Expand
Portable Camera based Text Label Reading
TLDR
This project mainly consists of three steps first is to take the image of the object, second thing is to extract the required text from the image by character recognition algorithm and finally the extracted text is processed to audio speaker which is audible to the user. Expand
Text and graphics segmentation of newspapers printed in Gurmukhi script: a hybrid approach
TLDR
A very simple and effective hybrid approach based on run length smoothing algorithm and projection profile to segment an image from text in Gurmukhi script newspaper articles is proposed. Expand
Natural Scene Text Detection using Deep Neural Networks
The text imparts a high level of information quickly and concisely. Therefore, retrieval of this information plays a vital role in learning and understanding for humans as it has various applicationsExpand
Text graphic separation in Indian newspapers
TLDR
A novel framework for learning optimal parameters for text graphic separation in the presence of complex layouts of Indian newspaper is proposed. Expand
...
1
2
...

References

SHOWING 1-10 OF 21 REFERENCES
Page segmentation and identification for intelligent signal processing
TLDR
The proposed system consists of two modules: block segmentation and block identification, which first segment a document into several non-overlapping blocks by utilizing a novel recursive segmentation technique, then extract the features embedded in each segmented block. Expand
Segmentation and classification of mixed text/graphics/image documents
TLDR
A feature-based document analysis system is presented which utilizes domain knowledge to segment and classify mixed text/graphics/image documents and proper use of domain knowledge is proved to be effective in accelerating the segmentation speed and decreasing the classification error. Expand
Page Segmentation and Classification Utilizing Bottom-Up Approach
TLDR
The use of analyzing the connected components extracted from the binary image of a document page provides a lot of useful information, and will be used to perform skew correction, segmentation and classification of the document. Expand
Text extraction from gray scale document images using edge information
  • Qingqing Yuan, C. Tan
  • Computer Science
  • Proceedings of Sixth International Conference on Document Analysis and Recognition
  • 2001
TLDR
A well designed method that makes use of edge information to extract textual blocks from gray scale document images by detecting textual regions on heavy noise infected newspaper images and separate them from graphical regions is presented. Expand
Text extraction from color documents-clustering approaches in three and four dimensions
TLDR
Two histogram-based color clustering algorithms are investigated, the first is based on the RGB color space exclusively, while the second takes spatial information into account, in addition to the colors, in order to improve the automatic retrieval of text information. Expand
Text block segmentation using pyramid structure
  • C. Tan, Z. Zhang
  • Computer Science, Engineering
  • IS&T/SPIE Electronic Imaging
  • 2000
TLDR
An algorithm and its implementation that segregates text block by block from the provided document, e.g. newspaper image, based on pyramid structure, which is amenable for parallel processing on output, is described in this paper. Expand
Features for printed document image analysis
TLDR
First, entropic discrimination is introduced, i.e., a simple separation using only one feature, and a brief recall on existing texture and geometric discriminant parameters proposed in previous research is included. Expand
Newspaper document analysis featuring connected line segmentation
  • P. E. Mitchell, Hong Yan
  • Computer Science
  • Proceedings of Sixth International Conference on Document Analysis and Recognition
  • 2001
TLDR
An algorithm designed to segment and classify newspaper documents is presented, with the ability to detect lines in the document - including lines that are connected to other components. Expand
Geometric Structure Analysis of Document Images: A Knowledge-Based Approach
TLDR
This paper presents a knowledge-based method for sophisticated geometric structure analysis of technical journal pages that takes the hybrid of top-down and bottom-up techniques and consists of two phases: region segmentation and identification. Expand
A methodology of separating images from text using an OCR approach
  • N. Bourbakis
  • Computer Science
  • Proceedings IEEE International Joint Symposia on Intelligence and Systems
  • 1996
TLDR
This paper presents a document processing methodology based on an OCR approach that separates text from images by keeping their relationships for a possible reconstruction of the original page. Expand
...
1
2
3
...